when i train my dataset model with the command : './experiments/scripts/rfcn_end2end_ohem.sh 3 ResNet-101 pascal_voc' , an error occured as follows:
Traceback (most recent call last):
File "./tools/train_net.py", line 112, in
max_iters=args.max_iters)
File "/home/data2/clxia1120/software/py-R-FCN/tools/../lib/fast_rcnn/train.py", line 207, in train_net
model_paths = sw.train_model(max_iters)
File "/home/data2/clxia1120/software/py-R-FCN/tools/../lib/fast_rcnn/train.py", line 155, in train_model
model_paths.append(self.snapshot())
File "/home/data2/clxia1120/software/py-R-FCN/tools/../lib/fast_rcnn/train.py", line 112, in snapshot
np.repeat(self.bbox_stds, repeat).reshape((orig_1.shape[0], 1, 1, 1)))
ValueError: total size of new array must be unchanged
who can tell me how to deal with?
when i train my dataset model with the command : './experiments/scripts/rfcn_end2end_ohem.sh 3 ResNet-101 pascal_voc' , an error occured as follows: Traceback (most recent call last): File "./tools/train_net.py", line 112, in
max_iters=args.max_iters)
File "/home/data2/clxia1120/software/py-R-FCN/tools/../lib/fast_rcnn/train.py", line 207, in train_net
model_paths = sw.train_model(max_iters)
File "/home/data2/clxia1120/software/py-R-FCN/tools/../lib/fast_rcnn/train.py", line 155, in train_model
model_paths.append(self.snapshot())
File "/home/data2/clxia1120/software/py-R-FCN/tools/../lib/fast_rcnn/train.py", line 112, in snapshot
np.repeat(self.bbox_stds, repeat).reshape((orig_1.shape[0], 1, 1, 1)))
ValueError: total size of new array must be unchanged
who can tell me how to deal with?