| 666DZY666/micronet |
2,129 |
|
0 |
0 |
over 4 years ago |
46 |
October 06, 2021 |
70 |
mit |
Python |
| micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape |
| microsoft/LQ-Nets |
230 |
|
0 |
0 |
over 3 years ago |
0 |
|
5 |
mit |
Python |
| LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks |
| submission2019/cnn-quantization |
126 |
|
0 |
0 |
over 5 years ago |
0 |
|
11 |
|
Python |
| Quantization of Convolutional Neural networks. |
| blueardour/model-quantization |
116 |
|
0 |
0 |
over 5 years ago |
0 |
|
0 |
other |
Python |
| Collections of model quantization algorithms |
| TropComplique/trained-ternary-quantization |
87 |
|
0 |
0 |
over 8 years ago |
0 |
|
4 |
mit |
Jupyter Notebook |
| Reducing the size of convolutional neural networks |
| uber-research/permute-quantize-finetune |
79 |
|
0 |
0 |
over 5 years ago |
0 |
|
0 |
other |
Python |
| Using ideas from product quantization for state-of-the-art neural network compression. |
| TexasInstruments/jacinto-ai-devkit |
74 |
|
0 |
0 |
over 4 years ago |
0 |
|
9 |
other |
|
| Training & Quantization of embedded friendly Deep Learning / Machine Learning / Computer Vision models |
| TF2-Engine/TF2 |
74 |
|
0 |
0 |
almost 6 years ago |
0 |
|
12 |
apache-2.0 |
Python |
| An Open Source Deep Learning Inference Engine Based on FPGA |
| sithu31296/sota-backbones |
64 |
|
0 |
0 |
almost 4 years ago |
0 |
|
0 |
mit |
Python |
| A collection of SOTA Image Classification Models in PyTorch |
| pp-Innovate/FPGA-ZynqNet |
56 |
|
0 |
0 |
almost 9 years ago |
0 |
|
3 |
gpl-3.0 |
C++ |
| FPGA-based ZynqNet CNN accelerator developed by Vivado_HLS |
