janeann's repositories
cs230-code-examples
Code examples in pyTorch and Tensorflow for CS230
Accelerating-CNN-with-FPGA
This project accelerates CNN computation with the help of FPGA, for more than 50x speed-up compared with CPU.
AOWS
Code repositoy for "AOWS: Adaptive and optimal network width search with latency constraints", CVPR 2020
baiduxueshu
paper abstract spider
C2D
PyTorch implementation of "Contrast to Divide: self-supervised pre-training for learning with noisy labels"
CNNAF-CNN-Accelerator
CNN-Accelerator based on FPGA developed by verilog HDL.
deeplearning-assignment
吴恩达-深度学习-课后作业-答案与总结
DNN-Chip-Predictor
[ICASSP'20] DNN-Chip Predictor: An Analytical Performance Predictor for DNN Accelerators with Various Dataflows and Hardware Architectures
Double-Win-Quant
[ICML 2021] "Double-Win Quant: Aggressively Winning Robustness of Quantized DeepNeural Networks via Random Precision Training and Inference" by Yonggan Fu, Qixuan Yu, Meng Li, Vikas Chandra, Yingyan Lin
mnist_fpga
using xilinx xc6slx45 to implement mnist net
mobile-vision
Mobile vision models and code
Paddle-Lite
Multi-platform high performance deep learning inference engine (『飞桨』多平台高性能深度学习预测引擎）
PaddleDetection
Object detection and instance segmentation toolkit based on PaddlePaddle.
PC-DARTS
PC-DARTS:Partial Channel Connections for Memory-Efficient Differentiable Architecture Search
pool_row_input
CNN_FPGA_acclerator
proxylessnas
[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
PYNQ_softmax
achieve softmax in PYNQ with heterogeneous computing.
pytorch_resnet_cifar10
Proper implementation of ResNet-s for CIFAR10/100 in pytorch that matches description of the original paper.
self-training-pytorch
Semi-supervised models based on deep neural networks implemented in PyTorch.
SIGMA
RTL implementation of Flex-DPE.
Single-Path-One-Shot-NAS-MXNet
Single Path One-Shot NAS MXNet implementation with full training and searching pipeline. Support both Block and Channel Selection. Searched models better than the original paper are provided.
test
仓库jjj
Verilog-FixedPoint
Verilog fixed-point lib: custom bit width, arithmetic, converting to float, with single cycle & pipeline version.