When studying a course, I find I prefer learning through labs rather than videos or slides. Therefore, I created this repository to gather useful labs from various open-source courses.
This section will introduce the basic knowledge of deep learning.
This lab use python to develop Multilayer Perceptrons (MLP).
This lab from AI Computing System and reference lab github.
This lab use python to develop VGG19 network.
This lab from AI Computing System and reference lab github.
The imagenet-vgg-verydeep-19.mat can be download from website.
This lab use pytorch framework to develop VGG19 network.
This lab from AI Computing System and reference lab github.
This lab will practice pruning and quantizing a classical neural network model to reduce both model size and latency.
You can upload .ipynb to Google Colab to use jupyter notebook and pytorch environment.
This lab from TinyML and Efficient Deep Learning Computing and reference lab github.
This lab learn how to search for a tiny neural network that can run efficiently on a microcontroller.
This lab from TinyML and Efficient Deep Learning Computing and reference lab github.
This lab contain some useful models, such as ResNet, MobileNet, YOLO, LSTM / GRU, Transformer, SNN.
The code of ResNet and LSTM / GRU from Deep Learning Models.
This lab from UCB CS61C.
This lab from ETHz Computer Architecture.
This lab based on SystemC.
This lab is a basic introduction lab with Verilog/System Verilog, which consist of FIFO, pipeline, handshake and FSM.
This lab from Hardware Accelerator for Machine Learning in SystemVerilog.
This lab from UVM Verification of VLSI Digital Designs.
This lab include some protocol controllers, such as UART, I2C, SPI.
This lab from USC EE577B: VLSI System Design and reference lab github.
This lab from ARM Introduction-to-SoC-Design-Education-Kit.