Category: Artificial Intelligence

Looks like I need to upgrade PyTorch! The error message:

NVIDIA GeForce RTX 3070 with CUDA capability sm_86 is not compatible with the current PyTorch installation. The current PyTorch install supports CUDA capabilities sm_37 sm_50 sm_60 sm_70. If you want to use the NVIDIA GeForce RTX 3070 GPU with PyTorch, please check the instructions at

https://pytorch.org/get-started/locally/

Install the latest CUDA version on Windows (3.0GB) – https://developer.nvidia.com/cuda-downloads?target_os=Windows&target_arch=x86_64&target_version=11&target_type=exe_local

Upgrade PyTorch:

conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch

Get arch list in Python.

import torch
torch.cuda.get_arch_list()

[‘sm_37’, ‘sm_50’, ‘sm_60’, ‘sm_61’, ‘sm_70’, ‘sm_75’, ‘sm_80’, ‘sm_86’, ‘compute_37’]

And works!

[Setting up Jupyter using Conda in WSL2]

[openpilot] is open source software built to improve upon the existing driver assistance in most new cars on the road today.

I started a TensorFlow notebook [TF_ImageScaleUp] to experiment with AI to deblur images.

[High Fidelity Image Generation Using Diffusion Models]

[esrgan-tf2]

[Deep Convolutional Generative Adversarial Network]

Udemy Course – [TensorFlow Developer Certificate in 2022: Zero to Mastery]

[Mr D. Bourke Github Repository]

[colab.research.google.com]

[Daniel Bourke YouTube Channel]

[Course Book Version]

[Seamless textures from a single image: style transfer and SGAN]

[Whisper] is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.

[AI model from OpenAI automatically recognizes speech and translates it to English]

[StableDiffusionApp]

[Miniconda Installer]

I commented out the following from requirements.txt:
#torch==1.12.1+cu113
#torchaudio==0.12.1+cu113
#torchvision==0.13.1+cu113

Run the terminal commands from the Conda terminal:
conda install pytorch==1.12.0 torchvision==0.13.0 torchaudio==0.12.0 cudatoolkit=11.3 -c pytorch

py -m pip install –upgrade pip
pip install -r requirements.txt
pip install customtkinter diffusers transformers ftfy

python app.py

[TensorFlow Datasets] (TFDS) provides a collection of ready-to-use datasets for use with TensorFlow, Jax, and other Machine Learning frameworks. It handles downloading and preparing the data deterministically and constructing a tf.data.Dataset (or np.array).

The [TensorFlow Datasets Catalog] has numerous datasets available through the API.

[Finding the Compute Compatibility Score for your GPU]

[ImageNet] is an image database organized according to the WordNet hierarchy (currently only the nouns), in which each node of the hierarchy is depicted by hundreds and thousands of images. The project has been instrumental in advancing computer vision and deep learning research. The data is available for free to researchers for non-commercial use.

[TensorFlow Hub] is a repository of trained machine learning models ready for fine-tuning and deployable anywhere. Reuse trained models like BERT and Faster R-CNN with just a few lines of code.

The [tfhub.dev] portal  lets you search and discover hundreds of trained, ready-to-deploy machine learning models in one place.

[app.wombo.art]