bostondiditeam/mv3d

Multi-View 3D Object Detection Network for Autonomous Driving

• This repo is for implementing MV3D from this paper: https://arxiv.org/abs/1611.07759 *

• The MV3D implementation progress report can be found here

To clone,

$git clone --recursive  https://github.com/bostondiditeam/MV3D.git

To pull, use

$git pull --recurse-submodules  

Contents

• Key facts
• Workflow
• How to run
• Todo
• Issues

Key facts

Workflow

Please refer to here

Key Dependency

• A Nvidia GPU card with computation capability > 3
• CUDA
• Python3.5 for MV3D related code
• Tensorflow-GPU(version>1.0)
• Python2.7 for ROS related script

File Structure

├── data   <-- all data is stored here. (Introduced in detail below)
│   ├── predicted  <-- after prediction, results will be saved here.
│   ├── preprocessed   <-- MV3D net will take inputs from here(after data.py) 
│   └── raw <-- raw data
├── environment_cpu.yml  <-- install cpu version.
├── README.md
├── saved_model                 <--- model and weights saved here. 
├── src        <-- MV3D net related source code 
│   ├── config.py
│   ├── data.py
│   ├── didi_data
│   ├── kitti_data
│   ├── lidar_data_preprocess
│   ├── make.sh
│   ├── model.py
│   ├── mv3d_net.py
│   ├── net
│   ├── play_demo.ipynb
│   ├── __pycache__
│   ├── tracking.py   <--- prediction after training. 
│   ├── tracklets
│   └── train.py    <--- training the whole network. 
│── utils    <-- all related tools put here, like ros bag data into kitti format
│    └── bag_to_kitti  <--- Take lidar value from ROS bag and save it as bin files.
└── external_models    <-- use as a submodule, basically code from other repos.
    └── didi-competition  <--- Code from Udacity's challenge repo with slightly modification, sync with Udacity's new
     updates regularly. 

Related data are organized in this way. (Under /data directory)

├── predicted <-- after prediction, results will be saved here.
│   ├── didi <-- when didi dataset is used, the results will be put here
│   └── kitti <-- When kitti dataset used for prediction, put the results here
│       ├── iou_per_obj.csv   <-- What will be evaluated for this competition, IoU score
│       ├── pr_per_iou.csv   <--precision and recall rate per iou, currently not be evaluated by didi's rule
│       └── tracklet_labels_pred.xml  <-- Tracklet generated from prediction pipeline. 
├── preprocessed  <-- Data will be fed into MV3D net (After processed by data.py)
│   ├── didi <-- When didi dataset is processed, save it here
│   └── kitti <-- When Kitti dataset is processed, save it here
│       ├── gt_boxes3d
│           └── 2011_09_26
│               └── 0005
|                   |___ 00000.npy
├       |── gt_labels
│           └── 2011_09_26
│               └── 0005 
|                   |___ 00000.npy
|       ├── rgb
│           └── 2011_09_26
│               └── 0005 
|                   |___ 00000.png
|       ├── top
│           └── 2011_09_26
│               └── 0005 
|                   |___ 00000.npy
|       └── top_image
|           └── 2011_09_26
|               └── 0005 
|                   |___ 00000.png
└── raw  <-- this strictly follow KITTI raw data file format, while seperated into didi and kitti dataset. 
    ├── didi <-- will be something similar to kitti raw data format below. 
    └── kitti
        └── 2011_09_26
            ├── 2011_09_26_drive_0005_sync
            │   ├── image_02
            │   │   ├── data
            │   │   │   └── 0000000000.png
            │   │   └── timestamps.txt
            │   ├── tracklet_labels.xml
            │   └── velodyne_points
            │       ├── data
            │       │   └── 0000000000.bin
            │       ├── timestamps_end.txt
            │       ├── timestamps_start.txt
            │       └── timestamps.txt
            ├── calib_cam_to_cam.txt
            ├── calib_imu_to_velo.txt
            └── calib_velo_to_cam.txt

Modification needed to run

After Tensorflow-GPU could work If you are not using Nvidia K520 GPU, you need to change "arch=sm_30" to other value in src/net/lib/setup.py and src/lib/make.sh in order to compiler *.so file right. Here is short list for arch values for different architecture.

# Which CUDA capabilities do we want to pre-build for?
# https://developer.nvidia.com/cuda-gpus
#   Compute/shader model   Cards
#   6.1		      P4, P40, Titan X so CUDA_MODEL = 61
#   6.0                    P100 so CUDA_MODEL = 60
#   5.2                    M40
#   3.7                    K80
#   3.5                    K40, K20
#   3.0                    K10, Grid K520 (AWS G2)
#   Other Nvidia shader models should work, but they will require extra startup
#   time as the code is pre-optimized for them.
CUDA_MODELS=30 35 37 52 60 61

Test your Tensorflow-GPU is running by"

import tensorflow as tf
sess = tf.Session()
print(tf.__version__) # version more than v1. 

It runs without error message and show　＂successfully opened CUDA library libcublas.so.8.0 locally＂, then it is in CUDA successfully.

source activate didi
sudo chmod 755 ./make.sh
./make.sh
# prerequisite for next step, i.e. running preprocessing using data.py, is to 
# follow steps in utils/bag_to_kitti if using didi data
python data.py # for process raw data to input network input format
python train.py # training the network. 

Some other readme.md files inside this repo:

• How to extract and sync data from ROS bags Under utils/bag_to_kitti
• How to generate tracklet files Under src/tracklets/

Issue

• Not related to this repo, but if you are using Amazon CarND AWS AMI (Ubuntu 16.04 and with tensorflow-gpu 0.12 installed), pip install --upgrade tensorflow won't work and will introduce driver/software conflict. Because CarND AMI has a nvidia 367 driver, but after running above line, it will install 375 driver. I think in this case, tensorflow-gpu (version >1.0) need to compiled from source code.
• If you already have a Tensorflow-GPU > 1, then the above ./make.sh works.
• If you see error message "tensorflow.python.framework.errors_impl.NotFoundError: YOUR_FOLDER/roi_pooling.so: undefined symbol: ZN10tensorflow7strings6StrCatB5cxx11ERKNS0_8AlphaNumES3", it is related to compilation of roi_pooling layer. A simple fix will be changing "GLIBCXX_USE_CXX11_ABI=1" to "GLIBCXX_USE_CXX11_ABI=0" in "src/net/lib/make.sh" (line 17)

mv3d's Issues

run train.py : At least two variables have the same name

Thanks for your work.

I managed to ./make.sh and then run data.py

When I try to run train.py file for KITTI dataset, errors like this shows up:

Use fusion-feature-2fc
Traceback (most recent call last):
  File "train.py", line 275, in <module>
    fast_test_mode=True if max_iter == 1 else False)
  File "/home/boom/MV3D/src/MV3D/src/mv3d.py", line 492, in __init__
    MV3D.__init__(self, top_shape, front_shape, rgb_shape, log_tag=log_tag)
  File "/home/boom/MV3D/src/MV3D/src/mv3d.py", line 156, in __init__
    checkpoint_dir=self.ckpt_dir)
  File "/home/boom/MV3D/src/MV3D/src/mv3d.py", line 86, in __init__
    self.saver=  tf.train.Saver(self.variables)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/saver.py", line 1338, in __init__
    self.build()
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/saver.py", line 1347, in build
    self._build(self._filename, build_save=True, build_restore=True)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/saver.py", line 1384, in _build
    build_save=build_save, build_restore=build_restore)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/saver.py", line 813, in _build_internal
    saveables = self._ValidateAndSliceInputs(names_to_saveables)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/saver.py", line 661, in _ValidateAndSliceInputs
    names_to_saveables = BaseSaverBuilder.OpListToDict(names_to_saveables)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/saver.py", line 638, in OpListToDict
    name)
ValueError: At least two variables have the same name: MV3D/top_view_rpn/feature-extract-resnet/MV3D/top_view_rpn/feature-extract-resnet/batch_normalization_1/moving_mean/biased

Could anyone offer me a help, please? I'm using Tensorflow 1.8.0 by the way. Is it because of the new version of Tensorflow?

data.py error

here: src/lidar_data_preprocess/Python_to_C_Interface/ver3/LidarTopPreprocess.so
data.py: calling main function ...
date 2011_09_26 and driver 0001
Traceback (most recent call last):
File "src/data.py", line 779, in
preproces(data_dir, frames_index)
File "src/data.py", line 703, in preproces
data_in_single_driver(cfg.RAW_DATA_SETS_DIR, key, driver, frames_index)
File "src/data.py", line 597, in data_in_single_driver
raise ValueError('read_objects error!!!!!')
ValueError: read_objects error!!!!!

I tried to run data.py and the program got this error. I tried to fix it but couldn't. Anyone here has the same problem please help me

So many conflict of module.

I got an error below.
from net.lib.utils.bbox import bbox_overlaps as box_overlaps File "__init__.pxd", line 872, in init utils.bbox ValueError: numpy.ufunc has the wrong size, try recompiling. Expected 192, got 216

so many conflict of numpy opencv and others.

Can you tell me pre-requisite module before train.py

Thanks.

License

Do you have any plan to license this code by Apache 2.0 or BSD?

How to test the MV3D work by already generated pretrained models?

I need to evaluate your model on KITTI dataset.
Is there is any scripts to evaluate pretrained model? Any pretrained model exists on MV3D?
Kindly let us know

make evaluation on the results ?

Hi !
I m writing evaluation codes recently. But when i translate the results to kitti_naive_eval codes. It turns out a very bad results. AP = 0. And when i write the codes, I found out the intersection of the boxes are below 0.5.
Also, The rcnn_nms is not according to iou_threshold but the score_threshold. That is a little different from the nms what i understand. Since it should be according to iou_threshold.

Can anyone help ?
Thanks a lot
@zxf8665905
@lancejchen
@patrickmpoon
@heroacool
@mandarup

can i train and test the MV3Dnet only use KITTIdatesets

No module named 'net.common' in test.py

I want to know which data the MATRIX_Mt and MATRIX_Kt are.

How to estimate orientation？

I want to get the azimuth angle of the object,what should i do?
Thank you very much!

how to visualize the result as lidar sight

Hello, i have finished training of the MV3D, but i don't find the test demo and the way which we project the 3dbox to the lidar point cloud
Hope for your response

psroi_pooling_op_gpu.cu.cc not compiling

System Specifications

OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Linux Ubuntu 18.04
TensorFlow version (use command below): tensorflow-gpu version 2.2
Python version: 3.6
Bazel version (if compiling from source): NA
GCC/Compiler version (if compiling from source): 8.4
CUDA/cuDNN version: 10.1
GPU model and memory: Tesla P100 (Google Colab)

Problem Description
I am trying to reproduce the results on Google Colab. However, I run into a host of warnings and a compilation error given below when I run make.sh file. I would really like to know how I can properly build the project!

Source code / logs

2020-05-29 13:49:51.008789: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1
/usr/local/lib/python3.6/dist-packages/tensorflow/include
/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/util/XprHelper.h(114): warning: host annotation is ignored on a function("no_assignment_operator") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/util/XprHelper.h(114): warning: device annotation is ignored on a function("no_assignment_operator") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/util/XprHelper.h(115): warning: host annotation is ignored on a function("no_assignment_operator") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/util/XprHelper.h(115): warning: device annotation is ignored on a function("no_assignment_operator") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/util/XprHelper.h(115): warning: host annotation is ignored on a function("~no_assignment_operator") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/util/XprHelper.h(115): warning: device annotation is ignored on a function("~no_assignment_operator") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1386): warning: calling a constexpr host function("real") from a host device function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1386): warning: calling a constexpr host function("imag") from a host device function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1386): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1386): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1391): warning: calling a constexpr host function("real") from a host device function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1391): warning: calling a constexpr host function("imag") from a host device function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1391): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1391): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1415): warning: calling a constexpr host function("real") from a host device function("exp") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1416): warning: calling a constexpr host function("imag") from a host device function("exp") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1417): warning: calling a constexpr host function("imag") from a host device function("exp") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1415): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1416): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1417): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1418): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1423): warning: calling a constexpr host function("real") from a host device function("exp") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1424): warning: calling a constexpr host function("imag") from a host device function("exp") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1425): warning: calling a constexpr host function("imag") from a host device function("exp") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1423): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1424): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1425): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1426): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/DenseBase.h(639): warning: host annotation is ignored on a function("DenseBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/DenseBase.h(639): warning: device annotation is ignored on a function("DenseBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MatrixBase.h(484): warning: host annotation is ignored on a function("MatrixBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MatrixBase.h(484): warning: device annotation is ignored on a function("MatrixBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MatrixBase.h(485): warning: host annotation is ignored on a function("MatrixBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MatrixBase.h(485): warning: device annotation is ignored on a function("MatrixBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MatrixBase.h(485): warning: host annotation is ignored on a function("~MatrixBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MatrixBase.h(485): warning: device annotation is ignored on a function("~MatrixBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayBase.h(156): warning: host annotation is ignored on a function("ArrayBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayBase.h(156): warning: device annotation is ignored on a function("ArrayBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayBase.h(157): warning: host annotation is ignored on a function("ArrayBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayBase.h(157): warning: device annotation is ignored on a function("ArrayBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayBase.h(157): warning: host annotation is ignored on a function("~ArrayBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayBase.h(157): warning: device annotation is ignored on a function("~ArrayBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(70): warning: host annotation is ignored on a function("CwiseUnaryView") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(70): warning: device annotation is ignored on a function("CwiseUnaryView") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(110): warning: host annotation is ignored on a function("CwiseUnaryViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(110): warning: device annotation is ignored on a function("CwiseUnaryViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(125): warning: host annotation is ignored on a function("CwiseUnaryViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(125): warning: device annotation is ignored on a function("CwiseUnaryViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(125): warning: host annotation is ignored on a function("~CwiseUnaryViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(125): warning: device annotation is ignored on a function("~CwiseUnaryViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(185): warning: host annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(185): warning: device annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(186): warning: host annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(186): warning: device annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(186): warning: host annotation is ignored on a function("~MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(186): warning: device annotation is ignored on a function("~MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(300): warning: host annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(300): warning: device annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(301): warning: host annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(301): warning: device annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(301): warning: host annotation is ignored on a function("~MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(301): warning: device annotation is ignored on a function("~MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Map.h(162): warning: host annotation is ignored on a function("Map") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Map.h(162): warning: device annotation is ignored on a function("Map") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Ref.h(90): warning: host annotation is ignored on a function("RefBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Ref.h(90): warning: device annotation is ignored on a function("RefBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Ref.h(232): warning: host annotation is ignored on a function("Ref") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Ref.h(232): warning: device annotation is ignored on a function("Ref") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(111): warning: host annotation is ignored on a function("Block") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(111): warning: device annotation is ignored on a function("Block") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(161): warning: host annotation is ignored on a function("BlockImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(161): warning: device annotation is ignored on a function("BlockImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(181): warning: host annotation is ignored on a function("BlockImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(181): warning: device annotation is ignored on a function("BlockImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(341): warning: host annotation is ignored on a function("BlockImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(341): warning: device annotation is ignored on a function("BlockImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/IndexedView.h(113): warning: host annotation is ignored on a function("IndexedView") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/IndexedView.h(113): warning: device annotation is ignored on a function("IndexedView") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(103): warning: host annotation is ignored on a function("Reshaped") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(103): warning: device annotation is ignored on a function("Reshaped") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(137): warning: host annotation is ignored on a function("ReshapedImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(137): warning: device annotation is ignored on a function("ReshapedImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(155): warning: host annotation is ignored on a function("ReshapedImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(155): warning: device annotation is ignored on a function("ReshapedImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(215): warning: host annotation is ignored on a function("ReshapedImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(215): warning: device annotation is ignored on a function("ReshapedImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(66): warning: host annotation is ignored on a function("Transpose") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(66): warning: device annotation is ignored on a function("Transpose") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(126): warning: host annotation is ignored on a function("TransposeImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(126): warning: device annotation is ignored on a function("TransposeImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(157): warning: host annotation is ignored on a function("TransposeImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(157): warning: device annotation is ignored on a function("TransposeImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(157): warning: host annotation is ignored on a function("~TransposeImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(157): warning: device annotation is ignored on a function("~TransposeImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Diagonal.h(78): warning: host annotation is ignored on a function("Diagonal") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Diagonal.h(78): warning: device annotation is ignored on a function("Diagonal") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(222): warning: host annotation is ignored on a function("TriangularView") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(222): warning: device annotation is ignored on a function("TriangularView") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(559): warning: host annotation is ignored on a function("TriangularViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(559): warning: device annotation is ignored on a function("TriangularViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(560): warning: host annotation is ignored on a function("TriangularViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(560): warning: device annotation is ignored on a function("TriangularViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(560): warning: host annotation is ignored on a function("~TriangularViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(560): warning: device annotation is ignored on a function("~TriangularViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reverse.h(90): warning: host annotation is ignored on a function("Reverse") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reverse.h(90): warning: device annotation is ignored on a function("Reverse") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayWrapper.h(47): warning: host annotation is ignored on a function("ArrayWrapper") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayWrapper.h(47): warning: device annotation is ignored on a function("ArrayWrapper") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayWrapper.h(145): warning: host annotation is ignored on a function("MatrixWrapper") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayWrapper.h(145): warning: device annotation is ignored on a function("MatrixWrapper") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/src/Tensor/TensorRandom.h(143): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/src/Tensor/TensorRandom.h(148): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/src/Tensor/TensorRandom.h(256): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/src/Tensor/TensorRandom.h(261): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/util/XprHelper.h(114): warning: host annotation is ignored on a function("no_assignment_operator") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/util/XprHelper.h(114): warning: device annotation is ignored on a function("no_assignment_operator") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/util/XprHelper.h(115): warning: host annotation is ignored on a function("no_assignment_operator") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/util/XprHelper.h(115): warning: device annotation is ignored on a function("no_assignment_operator") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/util/XprHelper.h(115): warning: host annotation is ignored on a function("~no_assignment_operator") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/util/XprHelper.h(115): warning: device annotation is ignored on a function("~no_assignment_operator") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/DenseBase.h(639): warning: host annotation is ignored on a function("DenseBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/DenseBase.h(639): warning: device annotation is ignored on a function("DenseBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MatrixBase.h(484): warning: host annotation is ignored on a function("MatrixBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MatrixBase.h(484): warning: device annotation is ignored on a function("MatrixBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MatrixBase.h(485): warning: host annotation is ignored on a function("MatrixBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MatrixBase.h(485): warning: device annotation is ignored on a function("MatrixBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MatrixBase.h(485): warning: host annotation is ignored on a function("~MatrixBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MatrixBase.h(485): warning: device annotation is ignored on a function("~MatrixBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayBase.h(156): warning: host annotation is ignored on a function("ArrayBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayBase.h(156): warning: device annotation is ignored on a function("ArrayBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayBase.h(157): warning: host annotation is ignored on a function("ArrayBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayBase.h(157): warning: device annotation is ignored on a function("ArrayBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayBase.h(157): warning: host annotation is ignored on a function("~ArrayBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayBase.h(157): warning: device annotation is ignored on a function("~ArrayBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(70): warning: host annotation is ignored on a function("CwiseUnaryView") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(70): warning: device annotation is ignored on a function("CwiseUnaryView") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(110): warning: host annotation is ignored on a function("CwiseUnaryViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(110): warning: device annotation is ignored on a function("CwiseUnaryViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(125): warning: host annotation is ignored on a function("CwiseUnaryViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(125): warning: device annotation is ignored on a function("CwiseUnaryViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(125): warning: host annotation is ignored on a function("~CwiseUnaryViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(125): warning: device annotation is ignored on a function("~CwiseUnaryViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(185): warning: host annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(185): warning: device annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(186): warning: host annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(186): warning: device annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(186): warning: host annotation is ignored on a function("~MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(186): warning: device annotation is ignored on a function("~MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(300): warning: host annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(300): warning: device annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(301): warning: host annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(301): warning: device annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(301): warning: host annotation is ignored on a function("~MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(301): warning: device annotation is ignored on a function("~MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Map.h(162): warning: host annotation is ignored on a function("Map") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Map.h(162): warning: device annotation is ignored on a function("Map") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Ref.h(90): warning: host annotation is ignored on a function("RefBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Ref.h(90): warning: device annotation is ignored on a function("RefBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Ref.h(232): warning: host annotation is ignored on a function("Ref") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Ref.h(232): warning: device annotation is ignored on a function("Ref") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(111): warning: host annotation is ignored on a function("Block") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(111): warning: device annotation is ignored on a function("Block") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(161): warning: host annotation is ignored on a function("BlockImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(161): warning: device annotation is ignored on a function("BlockImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(181): warning: host annotation is ignored on a function("BlockImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(181): warning: device annotation is ignored on a function("BlockImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(341): warning: host annotation is ignored on a function("BlockImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(341): warning: device annotation is ignored on a function("BlockImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/IndexedView.h(113): warning: host annotation is ignored on a function("IndexedView") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/IndexedView.h(113): warning: device annotation is ignored on a function("IndexedView") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(103): warning: host annotation is ignored on a function("Reshaped") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(103): warning: device annotation is ignored on a function("Reshaped") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(137): warning: host annotation is ignored on a function("ReshapedImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(137): warning: device annotation is ignored on a function("ReshapedImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(155): warning: host annotation is ignored on a function("ReshapedImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(155): warning: device annotation is ignored on a function("ReshapedImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(215): warning: host annotation is ignored on a function("ReshapedImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(215): warning: device annotation is ignored on a function("ReshapedImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(66): warning: host annotation is ignored on a function("Transpose") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(66): warning: device annotation is ignored on a function("Transpose") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(126): warning: host annotation is ignored on a function("TransposeImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(126): warning: device annotation is ignored on a function("TransposeImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(157): warning: host annotation is ignored on a function("TransposeImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(157): warning: device annotation is ignored on a function("TransposeImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(157): warning: host annotation is ignored on a function("~TransposeImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(157): warning: device annotation is ignored on a function("~TransposeImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Diagonal.h(78): warning: host annotation is ignored on a function("Diagonal") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Diagonal.h(78): warning: device annotation is ignored on a function("Diagonal") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(222): warning: host annotation is ignored on a function("TriangularView") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(222): warning: device annotation is ignored on a function("TriangularView") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(559): warning: host annotation is ignored on a function("TriangularViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(559): warning: device annotation is ignored on a function("TriangularViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(560): warning: host annotation is ignored on a function("TriangularViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(560): warning: device annotation is ignored on a function("TriangularViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(560): warning: host annotation is ignored on a function("~TriangularViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(560): warning: device annotation is ignored on a function("~TriangularViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reverse.h(90): warning: host annotation is ignored on a function("Reverse") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reverse.h(90): warning: device annotation is ignored on a function("Reverse") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayWrapper.h(47): warning: host annotation is ignored on a function("ArrayWrapper") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayWrapper.h(47): warning: device annotation is ignored on a function("ArrayWrapper") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayWrapper.h(145): warning: host annotation is ignored on a function("MatrixWrapper") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayWrapper.h(145): warning: device annotation is ignored on a function("MatrixWrapper") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/util/XprHelper.h(114): warning: host annotation is ignored on a function("no_assignment_operator") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/util/XprHelper.h(114): warning: device annotation is ignored on a function("no_assignment_operator") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/util/XprHelper.h(115): warning: host annotation is ignored on a function("no_assignment_operator") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/util/XprHelper.h(115): warning: device annotation is ignored on a function("no_assignment_operator") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/util/XprHelper.h(115): warning: host annotation is ignored on a function("~no_assignment_operator") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/util/XprHelper.h(115): warning: device annotation is ignored on a function("~no_assignment_operator") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1386): warning: calling a constexpr host function("real") from a host device function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1386): warning: calling a constexpr host function("imag") from a host device function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1386): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1386): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1391): warning: calling a constexpr host function("real") from a host device function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1391): warning: calling a constexpr host function("imag") from a host device function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1391): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1391): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1415): warning: calling a constexpr host function("real") from a host device function("exp") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1416): warning: calling a constexpr host function("imag") from a host device function("exp") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1417): warning: calling a constexpr host function("imag") from a host device function("exp") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1415): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1416): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1417): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1418): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1423): warning: calling a constexpr host function("real") from a host device function("exp") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1424): warning: calling a constexpr host function("imag") from a host device function("exp") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1425): warning: calling a constexpr host function("imag") from a host device function("exp") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1423): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1424): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1425): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1426): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/DenseBase.h(639): warning: host annotation is ignored on a function("DenseBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/DenseBase.h(639): warning: device annotation is ignored on a function("DenseBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MatrixBase.h(484): warning: host annotation is ignored on a function("MatrixBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MatrixBase.h(484): warning: device annotation is ignored on a function("MatrixBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MatrixBase.h(485): warning: host annotation is ignored on a function("MatrixBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MatrixBase.h(485): warning: device annotation is ignored on a function("MatrixBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MatrixBase.h(485): warning: host annotation is ignored on a function("~MatrixBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MatrixBase.h(485): warning: device annotation is ignored on a function("~MatrixBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayBase.h(156): warning: host annotation is ignored on a function("ArrayBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayBase.h(156): warning: device annotation is ignored on a function("ArrayBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayBase.h(157): warning: host annotation is ignored on a function("ArrayBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayBase.h(157): warning: device annotation is ignored on a function("ArrayBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayBase.h(157): warning: host annotation is ignored on a function("~ArrayBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayBase.h(157): warning: device annotation is ignored on a function("~ArrayBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(70): warning: host annotation is ignored on a function("CwiseUnaryView") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(70): warning: device annotation is ignored on a function("CwiseUnaryView") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(110): warning: host annotation is ignored on a function("CwiseUnaryViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(110): warning: device annotation is ignored on a function("CwiseUnaryViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(125): warning: host annotation is ignored on a function("CwiseUnaryViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(125): warning: device annotation is ignored on a function("CwiseUnaryViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(125): warning: host annotation is ignored on a function("~CwiseUnaryViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/CwiseUnaryView.h(125): warning: device annotation is ignored on a function("~CwiseUnaryViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(185): warning: host annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(185): warning: device annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(186): warning: host annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(186): warning: device annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(186): warning: host annotation is ignored on a function("~MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(186): warning: device annotation is ignored on a function("~MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(300): warning: host annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(300): warning: device annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(301): warning: host annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(301): warning: device annotation is ignored on a function("MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(301): warning: host annotation is ignored on a function("~MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MapBase.h(301): warning: device annotation is ignored on a function("~MapBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Map.h(162): warning: host annotation is ignored on a function("Map") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Map.h(162): warning: device annotation is ignored on a function("Map") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Ref.h(90): warning: host annotation is ignored on a function("RefBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Ref.h(90): warning: device annotation is ignored on a function("RefBase") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Ref.h(232): warning: host annotation is ignored on a function("Ref") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Ref.h(232): warning: device annotation is ignored on a function("Ref") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(111): warning: host annotation is ignored on a function("Block") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(111): warning: device annotation is ignored on a function("Block") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(161): warning: host annotation is ignored on a function("BlockImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(161): warning: device annotation is ignored on a function("BlockImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(181): warning: host annotation is ignored on a function("BlockImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(181): warning: device annotation is ignored on a function("BlockImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(341): warning: host annotation is ignored on a function("BlockImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Block.h(341): warning: device annotation is ignored on a function("BlockImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/IndexedView.h(113): warning: host annotation is ignored on a function("IndexedView") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/IndexedView.h(113): warning: device annotation is ignored on a function("IndexedView") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(103): warning: host annotation is ignored on a function("Reshaped") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(103): warning: device annotation is ignored on a function("Reshaped") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(137): warning: host annotation is ignored on a function("ReshapedImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(137): warning: device annotation is ignored on a function("ReshapedImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(155): warning: host annotation is ignored on a function("ReshapedImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(155): warning: device annotation is ignored on a function("ReshapedImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(215): warning: host annotation is ignored on a function("ReshapedImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reshaped.h(215): warning: device annotation is ignored on a function("ReshapedImpl_dense") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(66): warning: host annotation is ignored on a function("Transpose") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(66): warning: device annotation is ignored on a function("Transpose") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(126): warning: host annotation is ignored on a function("TransposeImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(126): warning: device annotation is ignored on a function("TransposeImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(157): warning: host annotation is ignored on a function("TransposeImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(157): warning: device annotation is ignored on a function("TransposeImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(157): warning: host annotation is ignored on a function("~TransposeImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Transpose.h(157): warning: device annotation is ignored on a function("~TransposeImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Diagonal.h(78): warning: host annotation is ignored on a function("Diagonal") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Diagonal.h(78): warning: device annotation is ignored on a function("Diagonal") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(222): warning: host annotation is ignored on a function("TriangularView") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(222): warning: device annotation is ignored on a function("TriangularView") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(559): warning: host annotation is ignored on a function("TriangularViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(559): warning: device annotation is ignored on a function("TriangularViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(560): warning: host annotation is ignored on a function("TriangularViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(560): warning: device annotation is ignored on a function("TriangularViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(560): warning: host annotation is ignored on a function("~TriangularViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/TriangularMatrix.h(560): warning: device annotation is ignored on a function("~TriangularViewImpl") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reverse.h(90): warning: host annotation is ignored on a function("Reverse") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/Reverse.h(90): warning: device annotation is ignored on a function("Reverse") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayWrapper.h(47): warning: host annotation is ignored on a function("ArrayWrapper") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayWrapper.h(47): warning: device annotation is ignored on a function("ArrayWrapper") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayWrapper.h(145): warning: host annotation is ignored on a function("MatrixWrapper") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/ArrayWrapper.h(145): warning: device annotation is ignored on a function("MatrixWrapper") that is explicitly defaulted on its first declaration

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/src/Tensor/TensorRandom.h(143): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/src/Tensor/TensorRandom.h(148): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/src/Tensor/TensorRandom.h(256): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/usr/local/lib/python3.6/dist-packages/tensorflow/include/unsupported/Eigen/CXX11/src/Tensor/TensorRandom.h(261): warning: calling a constexpr host function from a host device function is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

cuda_kernel_helper.h(49): error: class "Eigen::GpuDevice" has no member "getNumCudaMultiProcessors"

cuda_kernel_helper.h(49): error: class "Eigen::GpuDevice" has no member "maxCudaThreadsPerMultiProcessor"

cuda_kernel_helper.h(48): error: no instance of overloaded function "std::min" matches the argument list
argument types are: (, const int)

cuda_kernel_helper.h(51): error: class "Eigen::GpuDevice" has no member "maxCudaThreadsPerBlock"

cuda_kernel_helper.h(51): error: no instance of overloaded function "std::min" matches the argument list
argument types are: (int, )

cuda_kernel_helper.h(54): error: class "Eigen::GpuDevice" has no member "getNumCudaMultiProcessors"

cuda_kernel_helper.h(81): error: class "Eigen::GpuDevice" has no member "getNumCudaMultiProcessors"

cuda_kernel_helper.h(81): error: class "Eigen::GpuDevice" has no member "maxCudaThreadsPerMultiProcessor"

cuda_kernel_helper.h(83): error: no instance of overloaded function "std::max" matches the argument list
argument types are: (, int)

cuda_kernel_helper.h(90): error: no instance of overloaded function "std::min" matches the argument list
argument types are: (, const int)

10 errors detected in the compilation of "/tmp/tmpxft_000002c2_00000000-6_psroi_pooling_op_gpu.cu.cpp1.ii".
g++: error: psroi_pooling_op.cu.o: No such file or directory
make: 'LidarTopPreprocess.so' is up to date.

[problem] roi_pooling.so: undefined symbol: _ZN10tensorflow

hi all.

I successfully run the ./src/make.sh and ./src/data.py with multiple modifications :(

Now I am trying to execute the train.py. however, I got following error : "roi_pooling.so: undefined symbol: _ZN10tensorflow"

The roi_pooling.so is not a symbolic link, I copied it according the previous report.

Does anyone solve this problem?

Thanks in advanced.

---

my environment

• Google Cloud GPU (Tesla K80)
• Ubuntu 16.04
• Cuda 8.0
• python 3.5
• tensorflow-gpu

What does this sentence mean? - Change numpy array to be loaded into 'raw' to LidarTopPreprocess.so in ExampleUsage_Top.py line 126.

in src/lidar_data_preprocess/Python_to_C_Interface/ver3/README.md
there is a sentence : Change numpy array to be loaded into 'raw' to LidarTopPreprocess.so in ExampleUsage_Top.py line 126.
can i modify the ExampleUsage_Top.py as followoing?
raw = np.load("LidarTopPreprocess.so",allow_pickle=True)
However, it report error : OSError: Failed to interpret file 'LidarTopPreprocess.so' as a pickle
how can i fix this issue? thank for your help!

If I want to train the net only use lidar data (BV + FV ), what should I do? Thank you!

Hi:
For some reason, the data captured from lidar and camera can not be calibrated very well, I want to use MV3D only on lidar data, what should I do? Thank you very much!

What kind of data do I need to download in KITTI to train?

There are too many dataset to download ,I do not know which one is needed in this code
Thanks for your help

"as_list() is not defined on an unknown TensorShape."

When I run the train.py. I got following error message.

as_list() is not defined on an unknown TensorShape.

Does anyone know this problem?

---

my environment

• Google Cloud GPU (Tesla K80)
• Ubuntu 16.04
• Cuda 8.0
• python 3.5
• tensorflow-gpu

When I run "python data.py", I get this problem: AssertionError .

here: src\lidar_data_preprocess/Python_to_C_Interface/ver3/LidarTopPreprocess.so
Traceback (most recent call last):
File "src/data.py", line 27, in
assert (os.path.exists(so_path))
AssertionError

The link in download_weights.txt not working

I am trying to download the model check point to evaluate it on another dataset but the link in download_weights.txt https://pan.baidu.com/s/1capzfK not working it gives : https://pan.baidu.com/error/404.html

train with kitti data

When I do "python train.py". It gives "NameError: name 'data_splitter' is not defined".
But data_splitter is only defined when data is didi.
How to run train.py with kitti data?

Can I use data set as jpg??

I want to preprocess Image as .jpg because png file is too big to write.

For that purpose, where should I have to convert in code??

I already change the 'write' command extension as jpg. but, Image tint is wielded.

Does anybody know the solutions? Thanks ahead.

cudaCheckError() failed : invalid device function

I have already changed compute value in make.sh & setup.py file, anyone met this problem?

replicate results

Did you try and replicate results from the original paper? Does your implementation match the paper?

run train.py error

i successfully run make.sh and data.py
when i run train.py, i meet this error
tensorflow.python.framework.errors_impl.InvalidArgumentError: No OpKernel was registered to support Op 'RoiPoolGrad' with these attrs. Registered devices: [CPU], Registered kernels:
device='GPU'; T in [DT_FLOAT]

anyone can help me ?thanks l lot

what are the versions of Tensorflow and python?

my environment : python3.9 ,tensorflow 2.9

LIDAR Bird View

Hello,

Is the LIDAR Bird View obtained from the LIDAR Front View or is it extracted from the Kitti dataset? I am a bit confused how the data pre-processing works.

Thank you!

How to implement upsample2D layer?

Hi, how do we implement the upsample2D layer ? did any of you manage to implement it successfully ??

errors when running python train.py

Using TensorFlow backend.
Namespace(continue_train=False, max_iter=1000, tag='unknown_tag', targets='top_view_rpn,image_feature,fusion', weights='')

Enter log tag : 1
Set log tag :"1" ok !!
Traceback (most recent call last):
File "train.py", line 106, in
data_splitter = TrainingValDataSplitter(training_dataset)
File "/home1/liumeng/MV3D/src/utils/training_validation_data_splitter.py", line 44, in init
self.split_bags_by_tag_name()
File "/home1/liumeng/MV3D/src/utils/training_validation_data_splitter.py", line 65, in split_bags_by_tag_name
self.bags = shuffle(self.bags, random_state=0)
File "/home/deepwork/workspace/tensorflow-env-vary/tensorflow1.0-py3.5/lib/python3.5/site-packages/sklearn/utils/init.py", line 343, in shuffle
return resample(*arrays, **options)
File "/home/deepwork/workspace/tensorflow-env-vary/tensorflow1.0-py3.5/lib/python3.5/site-packages/sklearn/utils/init.py", line 269, in resample
resampled_arrays = [safe_indexing(a, indices) for a in arrays]
File "/home/deepwork/workspace/tensorflow-env-vary/tensorflow1.0-py3.5/lib/python3.5/site-packages/sklearn/utils/init.py", line 269, in
resampled_arrays = [safe_indexing(a, indices) for a in arrays]
File "/home/deepwork/workspace/tensorflow-env-vary/tensorflow1.0-py3.5/lib/python3.5/site-packages/sklearn/utils/init.py", line 164, in safe_indexing
return [X[idx] for idx in indices]
File "/home/deepwork/workspace/tensorflow-env-vary/tensorflow1.0-py3.5/lib/python3.5/site-packages/sklearn/utils/init.py", line 164, in
return [X[idx] for idx in indices]
KeyError: 0

@zxf8665905 @lancejchen

non maximum suppression

Hi,
could you please comment on, How are you performing NMS for oriented bounding boxes.

Best Regards,
Ansab Sheikh

how to Change numpy array to be loaded into 'raw' to LidarTopPreprocess.so in ExampleUsage_Top.py line 126.

i follow the readme.md in ver3/ to Change numpy array to be loaded into 'raw' to LidarTopPreprocess.so in ExampleUsage_Top.py line 126.

just like this: raw=np.load("LidarTopPreprocess.so",allowo_pickle=True)
however , python report error:
Traceback (most recent call last):
File "/home/siat/Downloads/ENTER/envs/mv3d/lib/python3.9/site-packages/numpy/lib/npyio.py", line 448, in load
return pickle.load(fid, **pickle_kwargs)
_pickle.UnpicklingError: invalid load key, '\x7f'.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "/home/siat/work/object_detection/didi/code/MV3D/src/lidar_data_preprocess/Python_to_C_Interface/ver3/ExampleUsage_Top.py", line 127, in
raw = np.load("LidarTopPreprocess.so",allow_pickle=True)
File "/home/siat/Downloads/ENTER/envs/mv3d/lib/python3.9/site-packages/numpy/lib/npyio.py", line 450, in load
raise IOError(
OSError: Failed to interpret file 'LidarTopPreprocess.so' as a pickle

so how can i do?

When i run "python data.py" in anaconda, I meet a read_objects error ! Thank you for your response。

I run "python data.py" in anaconda, i meet a trouble as follow :

here:  ./src/lidar_data_preprocess/Python_to_C_Interface/ver3/LidarTopPreprocess.so
data.py: calling main function ... 
date 2011_09_26 and driver 0001
Traceback (most recent call last):
  File "./src/data.py", line 779, in <module>
    preproces(data_dir, frames_index)
  File "./src/data.py", line 703, in preproces
    data_in_single_driver(cfg.RAW_DATA_SETS_DIR, key, driver, frames_index)
  File "./src/data.py", line 597, in data_in_single_driver
    raise ValueError('read_objects error!!!!!')
ValueError: read_objects error!!!!!

Because of the data set I put in anaconda, the program could not be found?
Or did I not place the data set in the specified file format order ?
Who can tell me the reason? Thank you very much !

can i see you conda list? i am trapped in the version of glib and cairo

i am trapped in the version of glib and cairo, and error report like these:
ImportError: /home/siat/Downloads/ENTER/envs/mv3d2/bin/../lib/libgio-2.0.so.0: undefined symbol: g_spawn_async_with_fds
ImportError: /usr/lib/x86_64-linux-gnu/libharfbuzz.so.0: undefined symbol: FT_Get_Var_Blend_Coordinates
the version of those is
glib 2.56.4
cario 1.12.18

about using KITTI dataset

Hello all ～
I have successfully run the ./src/make.sh and ./src/data.py with some personal modifications， Now I am trying to execute the train.py. However, in train.py line 103 "with BatchLoading(data_splitter.training_bags, data_splitter.training_tags, require_shuffle=True) as training" ,as we can see,when i use kitti dataset,the variable"data_splitter" won't be defined,so the line will report an error "NameError: name 'data_splitter' is not defined",because "data_splitter " is only initialized in line 82 for didi2 dataset.

all in all，how should I initialize the class "data_splitter "when using kitti dataset.

Thank you

Anyone can use the weight successful?

I have downloaded the weight, however, when I run the tracking.py, it seems there are some parameter in the network which is missing in the weight. The error is:

2021-11-09 16:34:01.956864: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Key MV3D/top_view_rpn/feature-extract-resnet/MV3D/top_view_rpn/feature-extract-resnet/batch_normalization_1/moving_mean/biased not found in checkpoint
2021-11-09 16:34:01.957170: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Key MV3D/top_view_rpn/feature-extract-resnet/MV3D/top_view_rpn/feature-extract-resnet/batch_normalization_1/moving_mean/local_step not found in checkpoint
2021-11-09 16:34:01.957264: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Key MV3D/top_view_rpn/feature-extract-resnet/MV3D/top_view_rpn/feature-extract-resnet/batch_normalization_1/moving_mean/biased not found in checkpoint
[[Node: save/RestoreV2 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]]
2021-11-09 16:34:01.957546: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Key MV3D/top_view_rpn/feature-extract-resnet/MV3D/top_view_rpn/feature-extract-resnet/batch_normalization_10/moving_mean/local_step not found in checkpoint
2021-11-09 16:34:01.957715: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Key MV3D/top_view_rpn/feature-extract-resnet/MV3D/top_view_rpn/feature-extract-resnet/batch_normalization_10/moving_mean/biased not found in checkpoint
2021-11-09 16:34:01.957756: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Key MV3D/top_view_rpn/feature-extract-resnet/MV3D/top_view_rpn/feature-extract-resnet/batch_normalization_1/moving_variance/local_step not found in checkpoint
2021-11-09 16:34:01.957791: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Key MV3D/top_view_rpn/feature-extract-resnet/MV3D/top_view_rpn/feature-extract-resnet/batch_normalization_1/moving_variance/biased not found in checkpoint
2021-11-09 16:34:01.957950: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Key MV3D/top_view_rpn/feature-extract-resnet/MV3D/top_view_rpn/feature-extract-resnet/batch_normalization_10/moving_variance/local_step not found in checkpoint

Is there any other special setting I need to use in this file?
Since there is an error in 'import utils.batch_loading as ub', I change it with 'import utils.batch_loading_for_data_py_output as ub'.
Is it the reason for the error?
If yes, where can I find the batch_loading class?

Thanks for any help

No OpKernel was registered to support Op 'RoiPoolGrad' with these attrs

InvalidArgumentError (see above for traceback): No OpKernel was registered to support Op 'RoiPoolGrad' with these attrs. Registered devices: [CPU], Registered kernels:
device='GPU'; T in [DT_FLOAT]

 [[Node: minimize_loss/gradients/MV3D/fusion/fuse-net/rgb-roi-pooling/rgb-roi_pooling_grad/RoiPoolGrad = RoiPoolGrad[T=DT_FLOAT, pooled_height=6, pooled_width=6, spatial_scale=0.125](MV3D/image_fe

Why not front features

I'm trying to reproduce the result of MV3D in PyTorch based on this repo. Find out that the implementation of this repo does not contain lidar front view features.

Could we know the reason for this absence? It's because of performance?

CPU-Mode

Hello guys. Is it possible to run the evaluation or inference in CPU-Mode without CUDA and gpu-support? If positive, could you please share your tips about modifying the code of project? I will appreciate your help.

Question about IOU between anchors and ground truth boxes

From my understanding, the 3d ground truth box can be tilted when projected on bird view, and the intersection between gt box and the anchor is usually not rectangular. However, inside bbox_overlaps it seems you assume that the intersection of two boxes is a rectangle of which the area is calculated by multiplying iw and ih?

error for running train.py

tensorflow.python.framework.errors_impl.NotFoundError: /home/lihua/MV3D/MV3D/src/net/roipooling_op/roi_pooling.so: cannot open shared object file: No such file or directory.
I think this matter due to the input to tensorflow. Please help me solve the problem. my email is [email protected]. thanks so much.

When running 'python data.py', error appears about name Matrix MT"

Traceback (most recent call last):
File "data.py", line 644, in
preproces(data_dir, frames_index)
File "data.py", line 565, in preproces
data_in_single_driver(cfg.RAW_DATA_SETS_DIR, key, driver, frames_index)
File "data.py", line 493, in data_in_single_driver
dump_bbox_on_camera_image(save_preprocess_dir, dataset, objects, date, drive, frames_index, overwrite=True)
File "data.py", line 394, in dump_bbox_on_camera_image
img = draw.draw_box3d_on_camera(rgb, gt_boxes3d)
File "/home/wuchengpeng/MV3D/src/net/utility/draw.py", line 35, in draw_box3d_on_camera
projections = box3d.box3d_to_rgb_box(boxes3d)
File "/home/wuchengpeng/MV3D/src/net/processing/boxes3d.py", line 120, in box3d_to_rgb_box
if Mt is None: Mt = np.array(MATRIX_Mt)
NameError: name 'MATRIX_Mt' is not defined

So, I search the data.py, boxes3d.py, draw.py, but I don't find the definition of MATRIX_MT and MATRIX_KT, where are them?

train_key_list

hello，I have an issue；I can't understand the meaning of "train_key_list" in the file named "training_validation_data_splitter.py";the "nissan_pulling_away" and others in the "train_key_list" have a special meaning?