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

Data damage? #24

Open
YangSiri opened this issue Sep 30, 2019 · 4 comments
Open

Data damage? #24

YangSiri opened this issue Sep 30, 2019 · 4 comments

Comments

@YangSiri
Copy link

Hi, @xingyul , thanks for your sharing codes and it is great. But i got a little trouble while testing it, could you or anyone help me?
I downloaded the processed data of flyingtings3d which is around 11GB, i extracted it and put the folder under data_processing, and then i run 'sh command_train.sh" as you suggested.There is the error :

2019-09-30 13:38:13.146499: W tensorflow/core/framework/allocator.cc:108] Allocation of 33554432 exceeds 10% of system memory.
-- 010 / 032 --
mean loss: 1.026778
Traceback (most recent call last):
File "train.py", line 283, in
train()
File "train.py", line 155, in train
train_one_epoch(sess, ops, train_writer)
File "train.py", line 201, in train_one_epoch
batch_data, batch_label, batch_mask = get_batch(TRAIN_DATASET, train_idxs, start_idx, end_idx)
File "train.py", line 173, in get_batch
pc1, pc2, color1, color2, flow, mask1 = dataset[idxs[i+start_idx]]
File "/home/py001/cyz/flownet3d/flying_things_dataset.py", line 36, in getitem
data = np.load(fp)
File "/home/py001/anaconda3/envs/cyzpy35/lib/python3.5/site-packages/numpy/lib/npyio.py", line 426, in load
pickle_kwargs=pickle_kwargs)
File "/home/py001/anaconda3/envs/cyzpy35/lib/python3.5/site-packages/numpy/lib/npyio.py", line 182, in init
_zip = zipfile_factory(fid)
File "/home/py001/anaconda3/envs/cyzpy35/lib/python3.5/site-packages/numpy/lib/npyio.py", line 112, in zipfile_factory
return zipfile.ZipFile(file, *args, **kwargs)
File "/home/py001/anaconda3/envs/cyzpy35/lib/python3.5/zipfile.py", line 1026, in init
self._RealGetContents()
File "/home/py001/anaconda3/envs/cyzpy35/lib/python3.5/zipfile.py", line 1093, in _RealGetContents
raise BadZipFile("File is not a zip file")
zipfile.BadZipFile: File is not a zip file
Exception ignored in: <bound method NpzFile.del of <numpy.lib.npyio.NpzFile object at 0x7f3f12e80630>>
Traceback (most recent call last):
File "/home/py001/anaconda3/envs/cyzpy35/lib/python3.5/site-packages/numpy/lib/npyio.py", line 219, in del
self.close()
File "/home/py001/anaconda3/envs/cyzpy35/lib/python3.5/site-packages/numpy/lib/npyio.py", line 210, in close
if self.zip is not None:
AttributeError: 'NpzFile' object has no attribute 'zip

Is there anything wrong with the data i downloaded ?

@xingyul
Copy link
Owner

xingyul commented Oct 7, 2019

Can you print out the filename of the .npz file that cause the problem?

@YangSiri
Copy link
Author

YangSiri commented Oct 8, 2019

Hi @xingyul , Thanks for answering me. But I think none file is in processing... Doesn't this problem occur as long as the first data file is read?

@xingyul
Copy link
Owner

xingyul commented Oct 9, 2019

Hi, if you take a look at the dataset file, the code read each npz file one by one. From the error message you showed, it seems like there is an error during the reading of the npz file. It would be helpful to check if the npz filename is correct.

@YangSiri
Copy link
Author

2019-11-10 15-33-59屏幕截图

Hi @xingyul thanks for your attention.
This is the processed data folder, i dont spot any mistake?

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

2 participants