Deep Learning model papers

The following papers I have read:

    Image generation:

    1. Stable diffusion

    2. Taiyi model

    3. CLIP (FLIP)

    4. Fooocus

    5. ControlNet

    6. T2I Adaptor

    7. BDM

    8. Laion 5B dataset

    9. Dalle 2 / Dalle 3

    10. Imagen

    NLP:

    1. Transformer

    2. BERT

    3. GPT / GPT2 / GPT3

    CV:

    1. ResNet

    2. ViT

 

How to setup a server (including ubuntu / Nvidia GPU)

1. install ubuntu 20.04

        

2. install ssh and nettool

        sudo apt install openssh-client ssh net-tools

3. install Nvidia driver 535:

        sudo apt update -y && sudo apt upgrade -y && sudo apt install vim gcc g++ make python3-pip -y

        use nvidia-detector or ubuntu-drivers devices to check available version

        sudo apt install nvidia-driver-535 -y

        use nvidia-smi to check if it install successfully

4. install docker-nvidia:

curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg \ && curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | \ sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \ sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list \ && \ sudo apt-get update

sudo apt-get install -y nvidia-container-toolkit

sudo nvidia-ctk runtime configure --runtime=docker

sudo systemctl restart docker

docker run --rm --runtime=nvidia --gpus all ubuntu nvidia-smi

a demo for Gradio

Here is a demo for Gradio:

1. how to install Gradio:

    pip install gradio

2. demo:

import gradio as gr
import cv2

def to_black(image):
    output = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    return output

interface = gr.Interface(fn=to_black, inputs="image", outputs="image")
interface.launch()

        .launch(share=True): can create a public ip

        .launch(server_name=“0.0.0.0”): can use local ip to access