What is the correct folder structure for the dataset?
debvrat opened this issue · 1 comments
debvrat commented
Hi,
As per the README.txt, I've setup my CLEVR dataset to look like this -
IODINE-master/data/CLEVR/
images/
train/
CLEVR_train_xxxxxx.png
CLEVR_train_xxxxxx.png
.
.
test/
.
.
.
val/
.
.
.
questions/
scenes/
COPYRIGHT.txt
LICENSE.txt
README.txt
Is this the right folder structure? Because I'm getting the following error, which I think is probably because the png files are not accessible.
Traceback (most recent call last):
File "/Volumes/GoogleDrive/My Drive/IS 800 - Deep Learning [Project]/IODINE-master/tools/train_net.py", line 90, in <module>
train_net(cfg)
File "/Volumes/GoogleDrive/My Drive/IS 800 - Deep Learning [Project]/IODINE-master/tools/train_net.py", line 83, in train_net
evaluator=evaluator
File "./lib/engine/train.py", line 48, in train
for iter, data in enumerate(dataloader):
File "/Users/akv/anaconda3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 345, in __next__
data = self._next_data()
File "/Users/akv/anaconda3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 385, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "/Users/akv/anaconda3/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/Users/akv/anaconda3/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in <listcomp>
data = [self.dataset[idx] for idx in possibly_batched_index]
File "./lib/data/clevr.py", line 25, in __getitem__
img = io.imread(img_path)[:, :, :3]
File "/Users/akv/anaconda3/lib/python3.7/site-packages/skimage/io/_io.py", line 48, in imread
img = call_plugin('imread', fname, plugin=plugin, **plugin_args)
File "/Users/akv/anaconda3/lib/python3.7/site-packages/skimage/io/manage_plugins.py", line 210, in call_plugin
return func(*args, **kwargs)
File "/Users/akv/anaconda3/lib/python3.7/site-packages/skimage/io/_plugins/imageio_plugin.py", line 10, in imread
return np.asarray(imageio_imread(*args, **kwargs))
File "/Users/akv/anaconda3/lib/python3.7/site-packages/imageio/core/functions.py", line 265, in imread
reader = read(uri, format, "i", **kwargs)
File "/Users/akv/anaconda3/lib/python3.7/site-packages/imageio/core/functions.py", line 182, in get_reader
"Could not find a format to read the specified file in %s mode" % modename
ValueError: Could not find a format to read the specified file in single-image mode
debvrat commented
Added the 'mode' while searching for images.
Line 17 of \lib\data\clevr.py:
for file in os.scandir(os.path.join(root, 'images', mode)):