Open Sotatek-HoangTran opened 5 years ago
Did you use the input size of 112*112 ? If not, you should modify the size of last convolutional feature map.
yes, my dataset's input size is 112*112
25088 = 512 7 7; 32768 = 512 8 8; It seems that you are using 120 * 120 input. Can you give more details on the error message ?
Sorry, my bad. My input size is not 112112. but i got another issue:
`Traceback (most recent call last):
File "train.py", line 235, in
I got an error: RuntimeError: size mismatch, m1: [1 x 32768], m2: [25088 x 512] at /opt/conda/conda-bld/pytorch_1549628766161/work/aten/src/THC/generic/THCTensorMathBlas.cu:266. My backbone is Res50_IR. I dont know how to fix this. What should i do ?