Comments (7)
Thank you for finding this issue! I was not aware that every user must have git-lfs installed to download the file. I will update the README.
Please let me know if you have anymore concerns
from trailmap.
Thank you for bringing up this issue. While testing at first, I found that the trailmap_model.hdf5 downloaded from the git repository does work on my computer. However, I also installed HDFView to inspect the file, and noticed that after opening the hdf5 file on HDFView, I received the same error as you did with the file being unable to be open when running segment_brain_batch.py.
It appears that HDFView is altering the trailmap_model.hdf5 file. This can be evidenced from the date modified updating when I open it. I also ran ubuntu's cmp command on the hdf5 file in comparison to a freshly downloaded hdf5 model, and it indeed does say the files are different.
Could you try downloading a fresh copy of trailmap_model.hdf5 again without opening it in HDFView? Please let me know if you continue to have issues.
from trailmap.
Hi Albert,
thanks for your reply. I did notice the problem first when running
python segment_brain_batch.py data/testing/example-chunk
on a freshly cloned repo. Only after running into errors there did I try to dig into the hdf5 file with HDFView and other tools.
I will try once more with a freshly cloned repo and report back.
from trailmap.
(base) vhil0002@MU00060589:~/Github$ mkdir tmp
(base) vhil0002@MU00060589:~/Github$ conda activate trailmap
(trailmap) vhil0002@MU00060589:~/Github$ cd tmp
(trailmap) vhil0002@MU00060589:~/Github/tmp$ git clone https://github.com/AlbertPun/TRAILMAP
Cloning into 'TRAILMAP'...
remote: Enumerating objects: 76, done.
remote: Counting objects: 100% (76/76), done.
remote: Compressing objects: 100% (50/50), done.
remote: Total 455 (delta 21), reused 66 (delta 21), pack-reused 379
Receiving objects: 100% (455/455), 53.30 MiB | 12.06 MiB/s, done.
Resolving deltas: 100% (30/30), done.
(trailmap) vhil0002@MU00060589:~/Github/tmp$ cd TRAILMAP/
(trailmap) vhil0002@MU00060589:~/Github/tmp/TRAILMAP$ ls -l data/
model-weights/ registration-paramaters/ testing/ tf-logs/ training/ validation/
(trailmap) vhil0002@MU00060589:~/Github/tmp/TRAILMAP$ ls -l data/
model-weights/ registration-paramaters/ testing/ tf-logs/ training/ validation/
(trailmap) vhil0002@MU00060589:~/Github/tmp/TRAILMAP$ ls -l data/model-weights/trailmap_model.hdf5
-rw-r--r-- 1 vhil0002 vhil0002 134 Feb 11 14:11 data/model-weights/trailmap_model.hdf5
(trailmap) vhil0002@MU00060589:~/Github/tmp/TRAILMAP$ python segment_brain_batch.py data/testing/example-chunk/
/home/vhil0002/anaconda3/envs/trailmap/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:523: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
/home/vhil0002/anaconda3/envs/trailmap/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:524: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/home/vhil0002/anaconda3/envs/trailmap/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint16 = np.dtype([("qint16", np.int16, 1)])
/home/vhil0002/anaconda3/envs/trailmap/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:526: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/home/vhil0002/anaconda3/envs/trailmap/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:527: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
/home/vhil0002/anaconda3/envs/trailmap/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:532: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
np_resource = np.dtype([("resource", np.ubyte, 1)])
2020-02-11 14:12:54.135352: W tensorflow/core/util/tensor_slice_reader.cc:95] Could not open /home/vhil0002/Github/tmp/TRAILMAP/data/model-weights/trailmap_model.hdf5: Data loss: not an sstable (bad magic number): perhaps your file is in a different file format and you need to use a different restore operator?
Traceback (most recent call last):
File "segment_brain_batch.py", line 22, in <module>
model.load_weights(weights_path)
File "/home/vhil0002/anaconda3/envs/trailmap/lib/python3.6/site-packages/tensorflow/python/keras/engine/network.py", line 1385, in load_weights
with h5py.File(filepath, 'r') as f:
File "/home/vhil0002/anaconda3/envs/trailmap/lib/python3.6/site-packages/h5py/_hl/files.py", line 408, in __init__
swmr=swmr)
File "/home/vhil0002/anaconda3/envs/trailmap/lib/python3.6/site-packages/h5py/_hl/files.py", line 173, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5f.pyx", line 88, in h5py.h5f.open
OSError: Unable to open file (file signature not found)
from trailmap.
note though that in contrast to your instructions I do not have h5py version 2.1
pip3 install h5py==2.1
as this version is no longer available on PyPI for installation with pip nor is it available with conda-forge. I tried to build version 2.1 from sources but haven't had luck so far. I also doubt that 2.1 would have produced incompatible hdf5 files.
Edited to add:
I have tested h5py version 2.6 and version 2.10 on Linux. HDFView was an older install on Windows.
from trailmap.
Ok, I think figured out the problem.
You seem to be using git-lfs (large file store) for storing the model weights. If one (like me) just has regular git installed, there will only be a placeholder file cloned.
After I installed git-lfs according to the instructions here the correct file was cloned. This might be worth a mention in the Readme.
from trailmap.
Hi,
I am getting the following error when trying to download the weights
git lfs pull
batch response: This repository is over its data quota. Account responsible for LFS bandwidth should purchase more data packs to restore access.
error: failed to fetch some objects from 'https://github.com/AlbertPun/TRAILMAP.git/info/lfs'
from trailmap.
Related Issues (14)
- Install instructions HOT 2
- Labeling method HOT 2
- Blas SGEMM launch failed when predicting with GPU HOT 5
- `get_dir` gets thrown off by created `seg-` folder HOT 7
- A few questions HOT 1
- Hi, your work is good, and where can I find your training dataset? HOT 4
- Error during inference HOT 3
- Threshold and cells HOT 12
- Cuda / Cudnn
- Inconsistent environment
- note though that in contrast to your instructions I do not have h5py version 2.1 HOT 4
- VisibleDeprecationWarning for segment_brain.py HOT 1
- Model weights cannot be downloaded (`This repository is over its data quota`) HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from trailmap.