GitHub

conda activate ./env

python <file>
python -m pip install <package>
conda install <library>

conda deactivate

Setup

Download Miniforge3 (Conda installer) for macOS arm64 chips (M1, M1 Pro, M1 Max).
Install Miniforge3 into home directory.

chmod +x ~/Downloads/Miniforge3-MacOSX-arm64.sh
sh ~/Downloads/Miniforge3-MacOSX-arm64.sh
source ~/miniforge3/bin/activate

Restart terminal.
Make and activate Conda environment. Note: Python 3.8 is the most stable for using the following setup.

conda create --prefix ./env python=3.8
conda activate ./env

conda install pytorch-nightly::pytorch torchvision torchaudio -c pytorch-nightly
conda install pandas numpy matplotlib scikit-learn notebook

https://colab.research.google.com/github/ - open any notebook from github in colab select GPU and train faster
jupyter nbconvert --clear-output --inplace notebook.ipynb - clear notebook output in all cells

Name		Name	Last commit message	Last commit date
Latest commit History 132 Commits
datasets		datasets
.gitignore		.gitignore
SDXL_autotrain_dreambooth.ipynb		SDXL_autotrain_dreambooth.ipynb
SDXL_gradio.py		SDXL_gradio.py
SDXL_sketch2img.ipynb		SDXL_sketch2img.ipynb
SDXL_txt2img.ipynb		SDXL_txt2img.ipynb
diffusers.ipynb		diffusers.ipynb
gograd.go		gograd.go
gpus_comparison.ipynb		gpus_comparison.ipynb
lstm.py		lstm.py
makemore.py		makemore.py
makemore_v2.py		makemore_v2.py
micrograd.py		micrograd.py
readme.md		readme.md
self_attention.ipynb		self_attention.ipynb
style_transfer_by_stas.json		style_transfer_by_stas.json
transformer.py		transformer.py
txt2audio.ipynb		txt2audio.ipynb
utils.py		utils.py

Provide feedback