search

joe-siyuan-qiao / DetectoRS

DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution
Apache License 2.0
1.13k stars 178 forks source link

An issue on re-implementation with COCO2017 dataset #68

Open rose-jinyang opened 4 years ago

rose-jinyang commented 4 years ago

Hello How are you? Thanks for contributing this project. I have searched related issues but cannot get the expected help. The bug has not been fixed in the latest version. I cloned the latest version of this project and tried to train a model with COCO2017 dataset. I used the following command. python tools/train.py configs/DetectoRS/DetectoRS_mstrain_400_1200_r50_40e.py I did not modify your code. My environment is following.

image

I installed Pytorch 1.4.0 with conda command. The environment variables are following. image image image

The issue track is following:

Traceback (most recent call last): File "tools/train.py", line 142, in main() File "tools/train.py", line 138, in main meta=meta) File "/mnt/Jin/DetectoRS/mmdet/apis/train.py", line 111, in train_detector meta=meta) File "/mnt/Jin/DetectoRS/mmdet/apis/train.py", line 242, in _non_dist_train runner.run(data_loaders, cfg.workflow, cfg.total_epochs) File "/home/vishwam/anaconda3/envs/py37/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 122, in run epoch_runner(data_loaders[i], **kwargs) File "/home/vishwam/anaconda3/envs/py37/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 27, in train for i, data_batch in enumerate(data_loader): File "/home/vishwam/anaconda3/envs/py37/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 345, in next data = self._next_data() File "/home/vishwam/anaconda3/envs/py37/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 856, in _next_dat return self._process_data(data) File "/home/vishwam/anaconda3/envs/py37/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 881, in process data.reraise() File "/home/vishwam/anaconda3/envs/py37/lib/python3.7/site-packages/torch/_utils.py", line 394, in reraise raise self.exc_type(msg) TypeError: Caught TypeError in DataLoader worker process 0. Original Traceback (most recent call last): File "/home/vishwam/anaconda3/envs/py37/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worke data = fetcher.fetch(index) File "/home/vishwam/anaconda3/envs/py37/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/vishwam/anaconda3/envs/py37/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in <listcom data = [self.dataset[idx] for idx in possibly_batched_index] File "/mnt/Jin/DetectoRS/mmdet/datasets/custom.py", line 132, in getitem data = self.prepare_train_img(idx) File "/mnt/Jin/DetectoRS/mmdet/datasets/custom.py", line 145, in prepare_train_img return self.pipeline(results) File "/mnt/Jin/DetectoRS/mmdet/datasets/pipelines/compose.py", line 24, in call data = t(data) File "/mnt/Jin/DetectoRS/mmdet/datasets/pipelines/transforms.py", line 323, in call self._pad_masks(results) File "/mnt/Jin/DetectoRS/mmdet/datasets/pipelines/transforms.py", line 310, in _pad_masks for mask in results[key] File "/mnt/Jin/DetectoRS/mmdet/datasets/pipelines/transforms.py", line 310, in for mask in results[key] TypeError: impad() takes 1 positional argument but 2 positional arguments (and 1 keyword-only argument) were given

Please let me know the reason of this issue asap. Thanks

joe-siyuan-qiao commented 4 years ago

It seems to be a dependency issue. Please consider using the implementation of DetectoRS provided by MMDetection if the problem is not resolved after checking conda_env.md.