AI automatically models based on pictures

I gave up temporarily, there is no graphics card, so I can’t install it directly

I used an old project on git 3 years ago, recently updated 6 months ago, developed by facebook

GitHub - facebookresearch/pifuhd: High-Resolution 3D Human Digitization from A Single Image.

The environment he needs is

• Python 3
• PyTorch tested on 1.4.0, 1.5.0
• json
• PIL
• skimage
• tqdm
• cv2

First we install python3 (the environment must be greater than 3.6 and less than 3.9)

Then install the conda environment, because pytorch must be installed in the conda environment

1. existing environment

• conda (must be greater than 3.6 and less than 3.9)

Download address: Miniconda — conda documentation

 Remember to configure environment variables

• Needless to say, python3.8 is available on the whole network

    2.pytorch installation

 Open cmd with administrator
conda install pytorch==1.4.0 -c pytorch

Reference article:

SOLVING ENVIRONMENT: FAILED WITH INITIAL FROZEN SOLVE. RETRYING WITH FLEXIBLE SOLVE solution_No one will really lie flat Blog-CSDN Blog

GitHub - facebookresearch/pifuhd: High-Resolution 3D Human Digitization from A Single Image.

https://chat.openai.com/c/bde2662e-83a8-4fee-8d6d-4356ed39d0de

Install conda to build a python environment (nanny-level tutorial)_Conda installs python_Q_fairy's Blog-CSDN Blog

Previous PyTorch Versions | PyTorch