carpedm20 / carpedm20/DCGAN-tensorflow
image error
- Dominant language
- JavaScript
- Stars
- 7.2k
- Forks
- 2.6k
- PR merge metrics
- No merged PRs in 30d
Description
Hello,
I've been able to run this with batches of images I made from myself. I know put all those images together and I get constant errors like below. I've already deleted like 30 of those and still they come up.
What does this mean?
```
python main.py --dataset=folderboxingunclean --input_height=306 --train --crop
{'batch_size': 64,
'beta1': 0.5,
'checkpoint_dir': 'checkpoint',
'crop': True,
'dataset': 'folderboxingunclean',
'epoch': 25,
'input_fname_pattern': '*.jpg',
'input_height': 306,
'input_width': None,
'learning_rate': 0.0002,
'output_height': 64,
'output_width': None,
'sample_dir': 'samples',
'train': True,
'train_size': inf,
'unrolled_lstm': False,
'visualize': False}
Traceback (most recent call last):
File "main.py", line 97, in
tf.app.run()
File "/home/quinten/anaconda2/envs/carpedm20/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 43, in run
sys.exit(main(sys.argv[:1] + flags_passthrough))
File "main.py", line 75, in main
sample_dir=FLAGS.sample_dir)
File "/home/quinten/Documents/DCGAN-tensorflow/model.py", line 78, in __init__
imreadImg = imread(self.data[0]);
File "/home/quinten/Documents/DCGAN-tensorflow/utils.py", line 39, in imread
return scipy.misc.imread(path).astype(np.float)
File "/home/quinten/anaconda2/envs/carpedm20/lib/python2.7/site-packages/scipy/misc/pilutil.py", line 156, in imread
im = Image.open(name)
File "/home/quinten/anaconda2/envs/carpedm20/lib/python2.7/site-packages/PIL/Image.py", line 2519, in open
% (filename if filename else fp))
IOError: cannot identify image file './data/folderboxingunclean/img433.jpg'
```
Contributor guide
No contributing guide indexed for this repository
Research direction
Start with the traceback through main.py, model.py, and utils.py, then inspect the referenced dataset file ./data/folderboxingunclean/img433.jpg and the image-loading call in utils.py. Run the provided training command with the dataset to reproduce the failure. Done means the cause of the image-loading error is identified and the command can proceed past the failing file.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, tensorflow
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100