Hi,
I used a few times the Label-free prediction (fnet) on google colab from ZeroCostDL4Mic and it was working great.
But now when I Install Fnet and dependencies I get :
1.15.2
Tensorflow enabled.
Collecting scipy==1.2.0
Downloading https://files.pythonhosted.org/packages/67/e6/6d4edaceee6a110ecf6f318482f5229792f143e468b34a631f5a0899f56d/scipy-1.2.0-cp36-cp36m-manylinux1_x86_64.whl (26.6MB)
|████████████████████████████████| 26.6MB 114kB/s
Requirement already satisfied, skipping upgrade: numpy>=1.8.2 in /usr/local/lib/python3.6/dist-packages (from scipy==1.2.0) (1.18.2)
ERROR: albumentations 0.1.12 has requirement imgaug<0.2.7,>=0.2.5, but you'll have imgaug 0.2.9 which is incompatible.
Installing collected packages: scipy
Found existing installation: scipy 1.4.1
Uninstalling scipy-1.4.1:
Successfully uninstalled scipy-1.4.1
Successfully installed scipy-1.2.0
WARNING: The following packages were previously imported in this runtime:
[scipy]
You must restart the runtime in order to use newly installed versions.
I do as it says and I restart the runtime. But later when I select paths and parameters I get :
FileNotFoundError Traceback (most recent call last)
<ipython-input-1-faa72f65f213> in <module>()
26 #Here we replace values in the old files
27 #Change maximum pixel number
---> 28 replace("/content/gdrive/My Drive/pytorch_fnet/fnet/transforms.py",'n_max_pixels=9732096','n_max_pixels=20000000')
29 replace("/content/gdrive/My Drive/pytorch_fnet/predict.py",'6000000','20000000')
30
<ipython-input-1-faa72f65f213> in replace(file_path, pattern, subst)
14 fh, abs_path = mkstemp()
15 with fdopen(fh,'w') as new_file:
---> 16 with open(file_path) as old_file:
17 for line in old_file:
18 new_file.write(line.replace(pattern, subst))
FileNotFoundError: [Errno 2] No such file or directory: '/content/gdrive/My Drive/pytorch_fnet/fnet/transforms.py'
Is there a way of fixing this ?
Thanks a lot for your help