nanguoyu

import torch
import torch.nn as nn
import torch.optim as optim
import matplotlib.pyplot as plt

def compute_rgn_from_gradients_and_params(gradients, parameters):
    """
    根据梯度值和参数值直接计算 RGN
    
    参数:

nanguoyu

Install Python env with Mamba in MacOS

Install Mamba

Mamba是一个智能版本的Conda，用来管理Python虚拟环境。详细介绍请参考：https://mamba.readthedocs.io/en/latest/user_guide/mamba.html

curl -L -O "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh"

nanguoyu

"""
@File :  fast_torchvision_dataloader.py
@Author: Dong Wang
@Date : 2024/06/25
@Description : a fast image dataloader for Pytorch models. It tries to use FFCV to speed up your dataloader for vision tasks.
You need first install FFCV in your Python ENV and run prepare_ffcv_dataset.py to prepare datasets in FFCV.
"""

import os
from torch.utils.data import DataLoader

nanguoyu

# Go to https://docs.conda.io/en/latest/miniconda.html and choose the suitable file link
wget https://repo.anaconda.com/miniconda/Miniconda3-py37_4.12.0-Linux-x86_64.sh

# install Miniconda
bash Miniconda3-py37_4.12.0-Linux-x86_64.sh

conda create -n env_name python=3.7
conda activate env_name
conda install pytorch==1.12.1 torchvision==0.13.1 torchaudio==0.12.1 cudatoolkit=11.3 -c pytorch

nanguoyu

panic(cpu 1 caller 0xfffffe0026801790): watchdog timeout: no checkins from watchdogd in 93 seconds (127 total checkins since monitoring last enabled)
Debugger message: panic
Memory ID: 0x6
OS release type: User
OS version: 22C65
Kernel version: Darwin Kernel Version 22.2.0: Fri Nov 11 02:04:44 PST 2022; root:xnu-8792.61.2~4/RELEASE_ARM64_T8103
Fileset Kernelcache UUID: ADB288150AFF2B26A022D2179A26F30C
Kernel UUID: D43063DF-7FAB-3E39-9807-2FC6A0C7F76A
Boot session UUID: BD64D3CE-D999-44A9-A66B-88DAF57DAA20
iBoot version: iBoot-8419.60.44

nanguoyu

hyper_output = []
with tqdm(range(-180, 181, 10), position=0) as t:
    for x in t:
        for y in tqdm(range(-180, 181, 10), disable=True):
            for z in tqdm(range(-180, 181, 10), disable=True):
            
                angles = torch.tensor([x,y,z])/180*torch.pi
                Hyper_x = transform_angles(angles=angles).to(device=gpu_computation)
                
                hyper_output.append(model.hyper_stack(Hyper_x).cpu().detach().numpy())

nanguoyu

git clone https://github.com/nanguoyu/GenoCAE.git
cd GenoCAE/
docker build -t gcae/genocae:build -f docker/build.dockerfile .
docker run -it --rm -v ${PWD}:/workspace gcae/genocae:build python3 run_gcae.py --help

nanguoyu

apt-get update && apt-get upgrade -y &&\
    apt-get install -y wget \
    build-essential zlib1g-dev libncurses5-dev libgdbm-dev libnss3-dev libssl-dev libreadline-dev libffi-dev 
    
    
wget https://www.python.org/ftp/python/3.8.0/Python-3.8.0.tgz &&\
    tar -xf Python-3.8.0.tgz &&\
    cd Python-3.8.0 &&\
    ./configure --enable-optimizations &&\
    make -j8 &&\

nanguoyu

yum install gcc-c++

Download CMake from: https://cmake.org/download/

wget https://cmake.org/files/v3.12/cmake-3.12.3.tar.gz

nanguoyu

sudo apt-get install qt5-default
sudo apt-get install opencl-headers
sudo pip install pylint
# Install minimal prerequisites (Ubuntu 18.04 as reference)
sudo apt update && sudo apt install -y cmake g++ wget unzip
# Download and unpack sources
wget -O opencv.zip https://github.com/opencv/opencv/archive/master.zip
wget -O opencv_contrib.zip https://github.com/opencv/opencv_contrib/archive/master.zip
unzip opencv.zip
unzip opencv_contrib.zip