-
Notifications
You must be signed in to change notification settings - Fork 47
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
Strange missing arguments problem #5
Comments
I believe you did not generate the segmentation results. Before tracking, please generate the segmentation first. As we can see in 'datasets.KittiMOTSDataset.MOTSTrackCarsValOffset', at Line 198, segmentation results should be available at 'os.path.join(systemRoot, 'SpatialEmbeddings/car_SE_val_prediction')'. |
I do generate with command |
If I do not generate the segmentation results, there will be no data in 'dataset_it'. Thus, 'embeds = model(points, None, xyxys, infer=True)' will not run because the loop 'for sample in dataset_it' is omitted. |
@lyuweiwang Hi , I have the same problem as you. Because two of the four GPUs in the server are occupied, I try to change 4gpu parallelism into 2gpu parallelism in the code. But it still failed. Finally, the program can run normally after changing the multi GPU to a single GPU. But the result is a little strange, we can see that the indicators of 0013 video sequence seem to be incorrect. |
@RandomFool123 However, I only use one GPU. |
@lyuweiwang You can try to set |
Finally, I realized that "./pointTrack_weights/PointTrack.pthCar" should be copied to "./car_finetune_tracking/checkpoint.pth" before I run "test_tracking.py". So, the problem is caused because the model has no parameters. |
@RandomFool123 My result is similar to yours. Maybe we should visualize the result of 0013. |
@lyuweiwang Hi, I am also facing some strange error about check_point, i have correctly set the path to "pointTrack.pthCar" when i run "python test_tracking.py car_test_tracking_val". Can you tell what's causing this? @detectRecog |
@tehseenmayar You need to change the path that load the segmentation result in datasets/KittiMOTSDataset.py line199, 200 |
Hi. I have copyed "./pointTrack_weights/PointTrack.pthCar" to "./car_finetune_tracking/checkpoint.pth" . But it still met “TypeError: forward() missing 3 required positional arguments: 'points', 'labels', and 'xyxys'” when I run |
Hi. @detectRecog i tried to run the code (myenv) C:\Users\Bharath\PointTrack>python -u test_mots_se.py car_test_se_to_save File "C:\Users\Bharath\PointTrack\datasets\KittiMOTSDataset.py", line 129, in getitem it is not taking the right path for the instance directory |
Dear Author,
When I run
python test_tracking.py car_test_tracking_val
, I met this problem:Traceback (most recent call last):
File "test_tracking.py", line 102, in
embeds = model(points, None, xyxys, infer=True)
File "/tmp-data/lyuwei/miniconda3/envs/pointtrack/lib/python3.6/site-packages/torch/nn/modules/module.py", line 541, in call
result = self.forward(*input, **kwargs)
TypeError: forward() missing 3 required positional arguments: 'points', 'labels', and 'xyxys'
However, as it shows, no argument is missing when I call forward function the same as your implementation. How can I solve this problem?
Thanks
The text was updated successfully, but these errors were encountered: