search

MedChaabane / DEFT

Joint detection and tracking model named DEFT, or ``Detection Embeddings for Tracking." Our approach relies on an appearance-based object matching network jointly-learned with an underlying object detection network. An LSTM is also added to capture motion constraints.
MIT License
269 stars 43 forks source link

The pretrained 'model_mot_lstm' is not included in Google drive #14

Open Vio1etovo opened 3 years ago

Vio1etovo commented 3 years ago

like this: model_kitti_lstm.pth、model_kitti.pth in this link: https://drive.google.com/drive/folders/1dlVoV-4fMYlttdj2ba0unn6WX-nxaC48?usp=sharing

Vio1etovo commented 3 years ago

This is an excellent job. But some errors appeared when I ran the code. After running ‘train.py’, there is an error in ‘train_prediction.py’: ''' Starting training... Traceback (most recent call last): File "/home/zbx/Anaconda3/envs/DEFT-main/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 779, in _try_get_data data = self._data_queue.get(timeout=timeout) File "/home/zbx/Anaconda3/envs/DEFT-main/lib/python3.6/queue.py", line 173, in get self.not_empty.wait(remaining) File "/home/zbx/Anaconda3/envs/DEFT-main/lib/python3.6/threading.py", line 299, in wait gotit = waiter.acquire(True, timeout) File "/home/zbx/Anaconda3/envs/DEFT-main/lib/python3.6/site-packages/torch/utils/data/_utils/signal_handling.py", line 66, in handler _error_if_any_worker_fails() RuntimeError: DataLoader worker (pid 29863) is killed by signal: Segmentation fault.

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "src/train_prediction.py", line 133, in main(opt) File "src/train_prediction.py", line 99, in main for iter_id, (inputs, targets) in enumerate(train_loader): File "/home/zbx/Anaconda3/envs/DEFT-main/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 363, in next data = self._next_data() File "/home/zbx/Anaconda3/envs/DEFT-main/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 974, in _next_data idx, data = self._get_data() File "/home/zbx/Anaconda3/envs/DEFT-main/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 931, in _get_data success, data = self._try_get_data() File "/home/zbx/Anaconda3/envs/DEFT-main/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 792, in _try_get_data raise RuntimeError('DataLoader worker (pid(s) {}) exited unexpectedly'.format(pids_str)) RuntimeError: DataLoader worker (pid(s) 29863) exited unexpectedly ''' After that, I modified batch_sized and num_works to (1, 0) But there was an error again: ''' Starting training... Segmentation fault (core dumped) ''' So I don't know how to modify it, please help me, thanks!

prabhuiitdhn commented 3 years ago

@Vio1etovo Have you fixed the issue, I am working on converting the model_mot to onnx. I am getting some kind of error. I can write it more If you are okay to help. Thank you.

hossamems commented 1 month ago

why did not chaabane solve it ?