dataloader 报错

[nkstatly]

RuntimeError: Caught RuntimeError in DataLoader worker process 3.
Original Traceback (most recent call last):
File "/root/.local/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 198, in _worker_loop
data = fetcher.fetch(index)
File "/root/.local/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 47, in fetch
return self.collate_fn(data)
File "/root/liyang/yolodet-pytorch/yolodet/dataset/loader/build_dataloader.py", line 92, in collate
clt[k] = torch.stack(v, 0)
RuntimeError: stack expects each tensor to be equal size, but got [3, 640, 640] at entry 0 and [3, 1280, 1280] at entry 6

是loader/build_dataloader.py 里面collate的问题？

[www516717402]

@nkstatly 两种方案，稍微修改一下即可

• 在collate里面先padding，然后在cat
• 提前处理好数据

[nkstatly]

@nkstatly 两种方案，稍微修改一下即可

• 在collate里面先padding，然后在cat
• 提前处理好数据

cfg中我注释了RandomAffine这一行，没有修改collate，能进行训练不报错
会不会是随机仿射变换时导致的

[wuzhihao7788]

能把你的cfg文件粘贴出来，我看一眼吗？

[nkstatly]

能把你的cfg文件粘贴出来，我看一眼吗？

ppyolo_coco_100e.zip
多谢了