Comments (7)
when you install detectron2 first and using "from detectron2 import xxx", the files of original detectron2 package is invoked instead of our modified mask head file.
from transfiner.
"The checkpoint state_dict contains keys that are not used by the model:..." This suggests that the pretrained model and your mask head file has a dismatch. Can you make sure you install transfiner correctly? I guess you are using the default mask head by mrcnn provided by detectron2.
from transfiner.
Thanks.
I installed detectron2 using pip first and then installed transfiner by doing python3 setup.py build develop
..
Let me follow the instructions in this repo fully and try again (I remember I had some installation issues on the colab which is why I installed detectron2 separately.). Are you aware of any compatability issues with different detectron2 versions?
from transfiner.
It indeed seems to be an issue with some dependency compatability issue.
Earlier I was installing detectron2 first which is installing a bunch of dependecies unlike the instructions in the readme of this repo..
that somehow led to the issue of model not getting loaded properly.
The reason that I was donig that is that the package "omegaconf" is getting installed by the transfiner installation script at a place that is not visible in colab.
Things are working as expected if If I dont' install detectron2 first. And the output masks are much much better :)
I would still like to understand where the problem is exactly, but please feel free to close this issue.
from transfiner.
Hi @lkeab
While the outputs are much better, I still see these logs now while trying to use the demo.py in Colab.
I suppose that this is also not supposed to happen, any idea what might be wrong (note the lines about roi_heads.mask_head*)?
fpn input shapes: {'res2': ShapeSpec(channels=256, height=None, width=None, stride=4), 'res3': ShapeSpec(channels=512, height=None, width=None, stride=8), 'res4': ShapeSpec(channels=1024, height=None, width=None, stride=16), 'res5': ShapeSpec(channels=2048, height=None, width=None, stride=32)}
[06/15 07:28:33 fvcore.common.checkpoint]: [Checkpointer] Loading from ./pretrained_models/output_3x_transfiner_r101_deform.pth ...
WARNING [06/15 07:28:33 fvcore.common.checkpoint]: Some model parameters or buffers are not found in the checkpoint:
roi_heads.mask_head.deconv_bo.{bias, weight}
roi_heads.mask_head.predictor_bo.{bias, weight}
0% 0/1 [00:00<?, ?it/s]/content/transfiner/detectron2/modeling/roi_heads/fast_rcnn.py:154: UserWarning: This overload of nonzero is deprecated:
nonzero()
Consider using one of the following signatures instead:
nonzero(*, bool as_tuple) (Triggered internally at /pytorch/torch/csrc/utils/python_arg_parser.cpp:882.)
filter_inds = filter_mask.nonzero()
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3063: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
"See the documentation of nn.Upsample for details.".format(mode))
configs/transfiner/mask_rcnn_R_101_FPN_3x_deform.yaml is the config being used.
I have followed the instructions from the readme and the python version is also 3.7. Could this still be because of some installation issue?
from transfiner.
Are you using the correct model? "Some model parameters or buffers are not found in the checkpoint:" indicates a mismatch between config file and the model weights.
from transfiner.
I downloaded the latest checkpoint from drive and I don't see these warnings any longer. Thanks.
I was using a checkpoint that I downloaded a couple of months back (April).. I am not sure if something changed or If I downloaded it wrong.
from transfiner.
Related Issues (20)
- Could you wirte a document about how to fine-tune your pre-trianed weight plz? HOT 4
- Strange visualization result. HOT 1
- how to export trained weights to onnx HOT 1
- Asking for code component HOT 3
- Question about segmentation fault HOT 1
- CUDA out of memory HOT 5
- RuntimeError: torch.nn.functional.binary_cross_entropy and torch.nn.BCELoss are unsafe to autocast HOT 2
- how to generate a polygon label for "polygons in polygons" HOT 1
- Visual error HOT 1
- ImportError: DLL load failed: The specified module cannot be found. HOT 1
- ImportError: cannot import name 'Caffe2Tracer' from 'detectron2.export' HOT 1
- compile fail HOT 1
- if i have a few hundred images to do , will it run on small dataset ? I mean can I train it on small dataset? Thank you for your amazing work HOT 1
- model questions HOT 2
- How to contribute?
- semi-supervised learning HOT 1
- AssertionError: COCOAPI does not support empty polygons HOT 2
- Does the model support exporting onnx?
- What kind of Feature fusion operation does RoI Feature and Coarse Masks do?
- bdd100k support
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from transfiner.