DECIMER Image Transformer is a deep-learning-based tool designed for automated recognition of chemical structure images. Leveraging transformer architectures, the model converts chemical images into SMILES strings, enabling the digitization of chemical data from scanned documents, literature, and patents.
MIT License
214
stars
52
forks
source link
setup.py tensor flow install for macOS not working for macOS Montery (Apple M1) #102
(STOUT) rachaelskyner@Rachaels-MacBook-Air IWOMI_Tutorials % pip install git+https://github.com/Kohulan/DECIMER-Image_Transformer.git
Collecting git+https://github.com/Kohulan/DECIMER-Image_Transformer.git
Cloning https://github.com/Kohulan/DECIMER-Image_Transformer.git to /private/var/folders/f2/fm_kr1g93tv15s6bj55fdqd40000gn/T/pip-req-build-pnwxeyw2
Running command git clone --filter=blob:none --quiet https://github.com/Kohulan/DECIMER-Image_Transformer.git /private/var/folders/f2/fm_kr1g93tv15s6bj55fdqd40000gn/T/pip-req-build-pnwxeyw2
Resolved https://github.com/Kohulan/DECIMER-Image_Transformer.git to commit 41138bead4a0e234f83e73f65639331b81aa32a8
Preparing metadata (setup.py) ... done
INFO: pip is looking at multiple versions of decimer to determine which version is compatible with other requirements. This could take a while.
ERROR: Could not find a version that satisfies the requirement tensorflow-macos<=2.15.0,>=2.10.0 (from decimer) (from versions: none)
ERROR: No matching distribution found for tensorflow-macos<=2.15.0,>=2.10.0
I can get it to work if I manually pip install tensorflow and change the setup.py to:
# if (
# platform.processor() == "arm" or platform.processor() == "i386"
#) and platform.system() == "Darwin":
# tensorflow_os = "tensorflow-macos>=2.10.0,<=2.15.0"
#else:
tensorflow_os = "tensorflow>=2.12.0,<=2.15.0"
Which images caused the issue? (This is mandatory for images related issues)
Issue Type
Bug
Source
GitHub (source)
DECIMER Image Transformer Version
master branch
OS Platform and Distribution
macOS Monterey v12.6.5
Python version
3.10
Current Behaviour?
I can get it to work if I manually pip install tensorflow and change the setup.py to:
Which images caused the issue? (This is mandatory for images related issues)
No response
Standalone code to reproduce the issue
Relevant log output
No response
Code of Conduct