detection_coco datamodule issue

[paNikitin]

Description

1. '39614e195.jpg' file`s name converts to a number,
2. train works cpu only with torch 1.12.1cu, torchvision 0.13.1 (windows), error raised on an attempt to run train.py on gpu

Information

1. 2023-04-01 00:19:51,711 - shapely.geos - DEBUG - Found GEOS DLL: <CDLL 'C:\Users\nikit\AppData\Local\pypoetry\Cache\virtualenvs\innofw-TKoQE3jM-py3.9\lib\site-packages\Shapely.libs\geos_c-84d02d5b10aa37e3ab60a885dc5b531b.dll', handle 7ffdfeb00000 at 0x28222bb87f0>, using it.
   [ WARN:0@2.184] global D:\a\opencv-python\opencv-python\opencv\modules\imgcodecs\src\loadsave.cpp (239) cv::findDecoder imread_('C:\Users\nikit\Downloads\innofw-main\innofw-main\data\wheat\train\train\train\3.9614E+199.jpg'): can't open/read file: check file path/integrity
   Epoch 0: 0%|█ | 1/212 [01:09<4:03:34, 69.26s/it, loss=5.85]

2. NotImplementedError: Could not run 'torchvision::nms' with arguments from the 'CUDA' backend. This could be because the operator doesn't exist for this backend, or was omitted during the selective/custom build process (if using custom build). If you are a Facebook employee using PyTorch on mobile, please visit https://fburl.com/ptmfixes for possible resolutions. 'torchvision::nms' is only available for these backends: [Dense, Negative, UNKNOWN_TENSOR_TYPE_ID, QuantizedXPU, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, SparseCPU, SparseCUDA, SparseHIP, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, SparseVE, UNKNOWN_TENSOR_TYPE_ID, NestedTensorCUDA, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID].

Screenshots

No response