faster-rcnn.pytorch issues

Question: results of test base on my own dataset

8

Hello @jwyang , I met a problem with my custom dataset with only one class. I have modified the pascal_voc.py and voc_eval.py and factory.py to my dataset. And during the...

lyx190

"RuntimeError: The expanded size of the tensor (1200) must match the existing size (1199) at non-singleton dimension 1. Target sizes: [600, 1200, 3]. Tensor sizes: [600, 1199, 3] "

8

Hi All, got a Runtime error while training on the Open Images dataset after around 9000 iterations in the first epoch. issue in: https://github.com/jwyang/faster-rcnn.pytorch/blob/358cecacf876717ff13988dc6396de10e265279c/lib/roi_data_layer/roibatchLoader.py#L177 `File "/home/munzueta/Kaggle/ObjectDetection2019/faster-rcnn.pytorch/lib/roi_data_layer/roibatchLoader.py", line 177, in __getitem__...

marcunzueta

Zero mAP when testing

3

Similar to #671 I am getting all zeros for test results, but there is no answer as to why in that post. Like this previous post, it seems as though...

rkruegs123

Nan loss while using Adam

It always happens at the beginning of training，then returns to normal，then abnormal,and so on，SGD algorithm does not have this problem. backbone:Res-101 dataset:VOC2007 WARNING:root:NaN or Inf found in input tensor. WARNING:root:NaN...

ZZZ951008

python setup.py build develop error

4

1 error detected in the compilation of "C:/Users/VitaminE/AppData/Local/Temp/tmpxft_000043ec_00000000-10_nms.cpp1.ii". error: command 'C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v10.1\\bin\\nvcc.exe' failed with exit status 1

VitaminEBB