Faster-rcnn.pytorch: torch.FatalError: invalid argument 2: out of range at /pytorch/aten/src/THC/generic/THCTensor.c:23

[hongdayu]

[hongdayu]

how to resolve this problem?

[jwyang]

@hongdayu it might because the rois exceed the input feature map. set a breakpoint to see when this happens.

[liveway6]

Hi, can you fixed this problem? Thanks.

[hongdayu]

Hi, can you fixed this problem? Thanks.

this is my solution

[liveway6]

Thank for your reply. this code lied in lib/model/fpn/fpn.py 131 and 147 ？ I follow you, but another problem is occur:

Traceback (most recent call last):
File "trainval_net.py", line 324, in
data = data_iter.next()
File "/home/wangshaoju/.conda/envs/ycy/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 264, in __next__
batch = self.collate_fn([self.dataset[i] for i in indices])
File "/home/wangshaoju/.conda/envs/ycy/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 264, in
batch = self.collate_fn([self.dataset[i] for i in indices])
File "/home/wangshaoju/jwyang/fpn.pytorch/lib/roi_data_layer/roibatchLoader.py", line 150, in __getitem__
gt_boxes[:, 0] = gt_boxes[:, 0] - x_s
TypeError: sub() received an invalid combination of arguments - got (numpy.int64), but expected one of:

• (Tensor other, float alpha)
• (float other, float alpha)

Thanks!

[hongdayu]

Thank for your reply. this code lied in lib/model/fpn/fpn.py 131 and 147 ？ I follow you, but another problem is occur:

Traceback (most recent call last):
File "trainval_net.py", line 324, in
data = data_iter.next()
File "/home/wangshaoju/.conda/envs/ycy/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 264, in next
batch = self.collate_fn([self.dataset[i] for i in indices])
File "/home/wangshaoju/.conda/envs/ycy/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 264, in
batch = self.collate_fn([self.dataset[i] for i in indices])
File "/home/wangshaoju/jwyang/fpn.pytorch/lib/roi_data_layer/roibatchLoader.py", line 150, in getitem
gt_boxes[:, 0] = gt_boxes[:, 0] - x_s
TypeError: sub() received an invalid combination of arguments - got (numpy.int64), but expected one of:

• (Tensor other, float alpha)
• (float other, float alpha)

Thanks!
the error
TypeError! The error occurred during the data loading phase.. the type of x_s is numpy.int64 , not tensor or float

[hongdayu]

Thank for your reply. this code lied in lib/model/fpn/fpn.py 131 and 147 ？ I follow you, but another problem is occur:
Traceback (most recent call last):
File "trainval_net.py", line 324, in
data = data_iter.next()
File "/home/wangshaoju/.conda/envs/ycy/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 264, in next
batch = self.collate_fn([self.dataset[i] for i in indices])
File "/home/wangshaoju/.conda/envs/ycy/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 264, in
batch = self.collate_fn([self.dataset[i] for i in indices])
File "/home/wangshaoju/jwyang/fpn.pytorch/lib/roi_data_layer/roibatchLoader.py", line 150, in getitem
gt_boxes[:, 0] = gt_boxes[:, 0] - x_s
TypeError: sub() received an invalid combination of arguments - got (numpy.int64), but expected one of:

• (Tensor other, float alpha)
• (float other, float alpha)

Thanks!
the error
TypeError! The error occurred during the data loading phase.. the type of x_s is numpy.int64 , not tensor or float

Thank for your reply. this code lied in lib/model/fpn/fpn.py 131 and 147 ？ I follow you, but another problem is occur:
Traceback (most recent call last):
File "trainval_net.py", line 324, in
data = data_iter.next()
File "/home/wangshaoju/.conda/envs/ycy/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 264, in next
batch = self.collate_fn([self.dataset[i] for i in indices])
File "/home/wangshaoju/.conda/envs/ycy/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 264, in
batch = self.collate_fn([self.dataset[i] for i in indices])
File "/home/wangshaoju/jwyang/fpn.pytorch/lib/roi_data_layer/roibatchLoader.py", line 150, in getitem
gt_boxes[:, 0] = gt_boxes[:, 0] - x_s
TypeError: sub() received an invalid combination of arguments - got (numpy.int64), but expected one of:

• (Tensor other, float alpha)
• (float other, float alpha)

Thanks!
the error
TypeError! The error occurred during the data loading phase.. the type of x_s is numpy.int64 , not tensor or float

Thank for your reply. this code lied in lib/model/fpn/fpn.py 131 and 147 ？ I follow you, but another problem is occur:
Traceback (most recent call last):
File "trainval_net.py", line 324, in
data = data_iter.next()
File "/home/wangshaoju/.conda/envs/ycy/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 264, in next
batch = self.collate_fn([self.dataset[i] for i in indices])
File "/home/wangshaoju/.conda/envs/ycy/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 264, in
batch = self.collate_fn([self.dataset[i] for i in indices])
File "/home/wangshaoju/jwyang/fpn.pytorch/lib/roi_data_layer/roibatchLoader.py", line 150, in getitem
gt_boxes[:, 0] = gt_boxes[:, 0] - x_s
TypeError: sub() received an invalid combination of arguments - got (numpy.int64), but expected one of:

• (Tensor other, float alpha)
• (float other, float alpha)

Thanks!
the error
TypeError! The error occurred during the data loading phase.. the type of x_s is numpy.int64 , not tensor or float

float(x_s)

[Karthik-Suresh93]

Hi @hongdayu @liveway6, did you solve this issue? If so, can you please elaborate on the solution?

[E-Dreamer-LQ]

@hongdayu @jwyang @liveway6 @Karthik-Suresh93 @severian I changed the code :idx_l = (roi_level == l).nonzero().view(-1) , but the error still exit. Could you tell me how to fix it. Help!!!

[Marcus208]

@hongdayu @jwyang @liveway6 @Karthik-Suresh93 @severian I changed the code :idx_l = (roi_level == l).nonzero().view(-1) , but the error still exit. Could you tell me how to fix it. Help!!!

i have used your method and it works