fferroni / pointpillars Goto Github PK
View Code? Open in Web Editor NEWPoint Pillars 3D detection network implementation in Tensorflow
License: GNU General Public License v3.0
Point Pillars 3D detection network implementation in Tensorflow
License: GNU General Public License v3.0
Can show some detial of this code ?
Hi Francesco,
Do you reproduce the results of the point pillars paper on kitti dataset (I have not seen some metrics, like mAP) ?
In a first time, I have implemented on the side a non maximum suppression after the network to compare the predicted box and GT. But I have a doubt on your angle implementation. Like in second paper, I have tried Yawlabel - YanAnchor in ground truth generation and then something like soomthL1(sin(Ypred - Ygt)) but the network doesn't seem to be able to predict angles at all.
Do you test it on your side ?
best regards
Pierre
Cannot find any possible results on KITTI, I am wondering if someone already reproduce the results of original paper.
Hello, I'm new to tensorflow keras api and 3d object detection.
When I call tf.keras.models.load_model() func after training the model, got the following error msg which make me confusion:
Traceback (most recent call last):
File "/home/xxx/tensorflow/PointPillars-master/test.py", line 24, in <module>
pillar_net_trained = tf.keras.models.load_model(os.path.join(log_dir, "finished.h5"))
File "/home/xxx/.local/lib/python2.7/site-packages/tensorflow/python/keras/engine/saving.py", line 235, in load_model
model = model_from_config(model_config, custom_objects=custom_objects)
File "/home/xxx/.local/lib/python2.7/site-packages/tensorflow/python/keras/engine/saving.py", line 325, in model_from_config
return deserialize(config, custom_objects=custom_objects)
File "/home/xxx/.local/lib/python2.7/site-packages/tensorflow/python/keras/layers/serialization.py", line 74, in deserialize
printable_module_name='layer')
File "/home/xxx/.local/lib/python2.7/site-packages/tensorflow/python/keras/utils/generic_utils.py", line 192, in deserialize_keras_object
list(custom_objects.items())))
File "/home/xxx/.local/lib/python2.7/site-packages/tensorflow/python/keras/engine/network.py", line 1273, in from_config
process_node(layer, node_data)
File "/home/xxx/.local/lib/python2.7/site-packages/tensorflow/python/keras/engine/network.py", line 1231, in process_node
layer(input_tensors[0], **kwargs)
File "/home/xxx/.local/lib/python2.7/site-packages/tensorflow/python/keras/engine/base_layer.py", line 554, in __call__
outputs = self.call(inputs, *args, **kwargs)
File "/home/xxx/.local/lib/python2.7/site-packages/tensorflow/python/keras/layers/core.py", line 743, in call
return self.function(inputs, **arguments)
File "/home/xxx/tensorflow/PointPillars-master/network.py", line 33, in <lambda>
if batch_size > 1:
TypeError: 'unicode' object is not callable
In File "/home/xxx/tensorflow/PointPillars-master/network.py", there are these codes around line 33:
if batch_size > 1:
corrected_indices = tf.keras.layers.Lambda(lambda t: correct_batch_indices(t, batch_size))(input_indices)
else:
corrected_indices = input_indices
Hi,
I modified the point_pillars_training.py file to save the model as pb as follows: pillar_net.save('point_pillars1.pb')
I also changed the parameters in config.py to a batch size of 2 and to run 20 epochs for training. After I run the training on an RTX 2080, I tried running the point_pillars_prediction.py file to get the following output:
File "<dir_to_pointpillars>/PointPillars/processors.py", line 155, in getitem
lidar = self.data_reader.read_lidar(self.lidar_files[i])
IndexError: list index out of range
Here is what I have installed:
Tensorflow: 2.1.0
Keras: 2.4.3
OpenCV-Python: 4.2.0.34
CUDA: 10.1
I have the save_model.pb saved in the root dir, while the model.h5 is saved under '/logs'. Anyone know what the issue is?
My decode process of the network is wrong even if with the ground truth as input. The bounding boxes of the decode output were not in the right place. Could any one share me a copy of the decode code?
My email is [email protected].
Thanks very much!
when i run
python setup.py build
it outputs
(tf1.15) sc@sc:~/disk/git/PointPillars$ python setup.py build
running build
running build_ext
CMake Error at CMakeLists.txt:3 (add_subdirectory):
The source directory
/home/sc/disk/git/PointPillars/pybind11
does not contain a CMakeLists.txt file.
CMake Error at CMakeLists.txt:4 (pybind11_add_module):
Unknown CMake command "pybind11_add_module".
-- Configuring incomplete, errors occurred!
See also "/home/sc/disk/git/PointPillars/build/temp.linux-x86_64-3.6/CMakeFiles/CMakeOutput.log".
Traceback (most recent call last):
File "setup.py", line 67, in <module>
zip_safe=False,
File "/home/sc/anaconda3/envs/tf1.15/lib/python3.6/site-packages/setuptools/__init__.py", line 144, in setup
return distutils.core.setup(**attrs)
File "/home/sc/anaconda3/envs/tf1.15/lib/python3.6/distutils/core.py", line 148, in setup
dist.run_commands()
File "/home/sc/anaconda3/envs/tf1.15/lib/python3.6/distutils/dist.py", line 955, in run_commands
self.run_command(cmd)
File "/home/sc/anaconda3/envs/tf1.15/lib/python3.6/distutils/dist.py", line 974, in run_command
cmd_obj.run()
File "/home/sc/anaconda3/envs/tf1.15/lib/python3.6/distutils/command/build.py", line 135, in run
self.run_command(cmd_name)
File "/home/sc/anaconda3/envs/tf1.15/lib/python3.6/distutils/cmd.py", line 313, in run_command
self.distribution.run_command(command)
File "/home/sc/anaconda3/envs/tf1.15/lib/python3.6/distutils/dist.py", line 974, in run_command
cmd_obj.run()
File "setup.py", line 33, in run
self.build_extension(ext)
File "setup.py", line 57, in build_extension
subprocess.check_call(['cmake', ext.sourcedir] + cmake_args, cwd=self.build_temp, env=env)
File "/home/sc/anaconda3/envs/tf1.15/lib/python3.6/subprocess.py", line 311, in check_call
raise CalledProcessError(retcode, cmd)
subprocess.CalledProcessError: Command '['cmake', '/home/sc/disk/git/PointPillars', '-DCMAKE_LIBRARY_OUTPUT_DIRECTORY=/home/sc/disk/git/PointPillars/build/lib.linux-x86_64-3.6', '-DPYTHON_EXECUTABLE=/home/sc/anaconda3/envs/tf1.15/bin/python', '-DCMAKE_BUILD_TYPE=Release']' returned non-zero exit status 1.
how to solve this?
My training process stucked at the second epoch, did anyone encounter this problem?
In config.py, the yaws are written in radians, but in point_pillars_test.py they're in degrees.
Is this a bug or am I missing something ?
Hello,I‘ve get error msg:
Traceback (most recent call last):
File "point_pillars_training_run.py", line 52, in
workers=1)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/keras/_impl/keras/engine/training.py", line 2312, in fit_generator
callbacks.on_epoch_begin(epoch)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/keras/_impl/keras/callbacks.py", line 80, in on_epoch_begin
callback.on_epoch_begin(epoch, logs)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/keras/_impl/keras/callbacks.py", line 596, in on_epoch_begin
lr = self.schedule(epoch)
TypeError: () missing 1 required positional argument: 'lr'
Could u please tell us the right version ?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.