Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

AssertionError #36

Closed
why4101130 opened this issue Jun 10, 2018 · 2 comments
Closed

AssertionError #36

why4101130 opened this issue Jun 10, 2018 · 2 comments

Comments

@why4101130
Copy link

When I change the dataset to my own dataset, I will run this error when I run train.py.

I c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\stream_executor\dso_loader.cc:135] successfully opened CUDA library nvcuda.dll locally
I c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\stream_executor\dso_loader.cc:135] successfully opened CUDA library curand64_80.dll locally
Loaded dataset voc_2007_trainval for training
Set proposal method: gt
Appending horizontally-flipped training examples...
Traceback (most recent call last):
voc_2007_trainval gt roidb loaded from D:\python\project\FasterRcnn\FasterRcnn\Faster-RCNN-TensorFlow-Python3.5-master\data\cache\voc_2007_trainval_gt_roidb.pkl
File "D:/python/project/FasterRcnn/FasterRcnn/Faster-RCNN-TensorFlow-Python3.5-master/train.py", line 209, in
train = Train()
File "D:/python/project/FasterRcnn/FasterRcnn/Faster-RCNN-TensorFlow-Python3.5-master/train.py", line 69, in init
self.imdb, self.roidb = combined_roidb("voc_2007_trainval")
File "D:/python/project/FasterRcnn/FasterRcnn/Faster-RCNN-TensorFlow-Python3.5-master/train.py", line 48, in combined_roidb
roidbs = [get_roidb(s) for s in imdb_names.split('+')]
File "D:/python/project/FasterRcnn/FasterRcnn/Faster-RCNN-TensorFlow-Python3.5-master/train.py", line 48, in
roidbs = [get_roidb(s) for s in imdb_names.split('+')]
File "D:/python/project/FasterRcnn/FasterRcnn/Faster-RCNN-TensorFlow-Python3.5-master/train.py", line 45, in get_roidb
roidb = get_training_roidb(imdb)
File "D:/python/project/FasterRcnn/FasterRcnn/Faster-RCNN-TensorFlow-Python3.5-master/train.py", line 25, in get_training_roidb
imdb.append_flipped_images()
File "D:\python\project\FasterRcnn\FasterRcnn\Faster-RCNN-TensorFlow-Python3.5-master\lib\datasets\imdb.py", line 119, in append_flipped_images
assert (boxes[:, 2] >= boxes[:, 0]).all()
AssertionError

Process finished with exit code 1

@lccate
Copy link

lccate commented Jun 20, 2018

Perhaps you didn't deleate the voc_2007_trainval_gt_roidb.pkl under data/cache

@gwspotex
Copy link

You can Comment out the" append_flipped_images "

@dBeker dBeker closed this as completed Apr 2, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants