-
Notifications
You must be signed in to change notification settings - Fork 931
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
all_hrnet_v2_w18.pth #63
Comments
The model may not be fully downloaded. I have uploaded the model again and you can download it again. |
Thanks. I run it with the new model and the issue still exists. I think the problem is with the parameter “--arch hrnet_18”. Even the model “all_dla34.pth” does not work with this parameter but work without it. When I run the model “” without parameter “--arch hrnet_18” as follows: python demo.py mot --load_model ../models/all_hrnet_v2_w18.pth --reid_dim 128 --conf_thres 0.4 I receive the warning as below. The code runs but the output video has no bboxes. No param base.level4.tree2.tree2.conv1.weight. If you see this, your model does not fully load the pre-trained weight. Please make sure you have correctly specified --arch xxx or set the correct --num_classes for your own dataset. |
I meet the same problem, even after i commented dcn in model.py, the info is as follows: |
The real error information is above the ffmpeg: '2020-04-27 16:32:27 [INFO]: ../models/hrnetv2_w18_imagenet_pretrained.pth is not exist!'. You need to first download the imagenet pretrained model and put it in the models directory. Or you can set pretrained=False of HRNet and do not load the imagenet pretrained model. Just loading my baseline model is OK. |
@ifzhang Thanks for answering, and, where to set pretrained=False of HRNet? |
You can set PRETRAINED: '' here:
|
@ifzhang It works! |
@ifzhang I set pretrained: False. However, it threw error: Please help me. Thank you. |
Thanks for your excellent work. I run the demo with model “all_dla34.pth” using the below script and all is ok.
python demo.py mot --load_model ../models/ all_dla34.pth --reid_dim 128 --conf_thres 0.4
but, when I use the model “all_hrnet_v2_w18.pth” with the following commands using the model that you have recently uploaded.
python demo.py mot --load_model ../models/all_hrnet_v2_w18.pth --arch hrnet_18 --reid_dim 128 --conf_thres 0.4
i receive the following error:
Creating model...
2020-04-24 10:01:09 [INFO]: unexpected EOF, expected 6133124 more bytes. The file might be corrupted.
terminate called after throwing an instance of 'c10::Error'
what(): owning_ptr == NullType::singleton() || owning_ptr->refcount_.load() > 0 INTERNAL ASSERT FAILED at /pytorch/c10/util/intrusive_ptr.h:348, please report a bug to PyTorch. intrusive_ptr: Can only intrusive_ptr::reclaim() owning pointers that were created using intrusive_ptr::release(). (reclaim at /pytorch/c10/util/intrusive_ptr.h:348)
frame #0: c10::Error::Error(c10::SourceLocation, std::string const&) + 0x33 (0x7f73cc075193 in /usr/local/lib/python3.6/dist-packages/torch/lib/libc10.so)
frame #1: + 0x18cd59f (0x7f73cdd9559f in /usr/local/lib/python3.6/dist-packages/torch/lib/libtorch.so)
frame #2: THStorage_free + 0x17 (0x7f73ce55dba7 in /usr/local/lib/python3.6/dist-packages/torch/lib/libtorch.so)
frame #3: + 0x55d65d (0x7f7416fc665d in /usr/local/lib/python3.6/dist-packages/torch/lib/libtorch_python.so)
frame #4: python3() [0x54f6e6]
frame #5: python3() [0x5734e0]
frame #6: python3() [0x4b1a28]
frame #7: python3() [0x589078]
frame #8: python3() [0x5ade68]
frame #9: python3() [0x5ade7e]
frame #10: python3() [0x5ade7e]
frame #11: python3() [0x5ade7e]
frame #12: python3() [0x5ade7e]
frame #13: python3() [0x5ade7e]
frame #14: python3() [0x5ade7e]
frame #15: python3() [0x5ade7e]
frame #16: python3() [0x590669]
frame #17: python3() [0x590943]
frame #19: python3() [0x509d48]
frame #20: python3() [0x50aa7d]
frame #22: python3() [0x508245]
frame #24: python3() [0x635222]
frame #29: __libc_start_main + 0xe7 (0x7f74310b8b97 in /lib/x86_64-linux-gnu/libc.so.6)
would you please tell me why?
The text was updated successfully, but these errors were encountered: