RuntimeError: invalid argument 2: Input tensor must have same size as output tensor apart from the specified dimension at /opt/conda/conda- about cascade-rcnn_pytorch HOT 2 CLOSED

I found that the code runs normally on faster-rcnn. But if I use the code of fpn, it failed. So I guess the problem happens in fpn.py, but I still can't find out why.
What's more, I used this model to train my personal dataset, if I changed the dataset back to original Voc2007, it works. That's strange. I just changed my personal data into the form of Voc2007.
Here is one of my annotation file:

train
VIRAT_S_000000.mp4_0
C:/Users/Kevin Qian/Downloads/images/train/VIRAT_S_000000.mp4_0.jpg

and here is the annotation file in original voc2007

VOC2007
009962.jpg

The VOC2007 Database
PASCAL VOC2007
flickr
246788553


Tool - Wroclaw
Milosz J.


500
375
3

0

chair
Right
1
0

211
192
324
326



person
Unspecified
1
0

162
72
273
248



person
Right
1
0

250
68
473
312



person
Right
1
0

4
2
253
374



diningtable
Unspecified
1
1

358
216
500
375

from cascade-rcnn_pytorch.

This project is not that stable. If your regression generates an bbox that is totally out of the image, the code will collapse like that. The algorithm is unstable while training.

from cascade-rcnn_pytorch.