11 results found Sort:

tensorflow
model-optimization tensorflow
324
1.5k
apache-2.0
120
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.
ml keras pruning sparsity tensorflow compression optimization quantization deep-learning machine-learning model-compression quantized-networks quantized-training quantized-neural-networks
Created 2018-10-31
834 commits to master branch, last one 5 days ago
larq
larq larq
85
710
apache-2.0
30
An Open-Source Library for Training Binarized Neural Networks
larq keras binder python tensorflow deep-learning machine-learning binarized-neural-networks quantized-neural-networks
Created 2019-03-18
736 commits to main branch, last one 4 months ago
google
qkeras google
103
543
apache-2.0
31
QKeras: a quantization deep learning library for Tensorflow Keras
fpga keras tensorflow accelerator asic-design quantization deep-learning fpga-accelerator machine-learning quantized-networks hardware-acceleration quantized-neural-networks
Created 2019-08-06
439 commits to master branch, last one about a month ago
Zhen-Dong
HAWQ Zhen-Dong
82
419
mit
15
Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.
tvm 4-bit 8-bit hessian pytorch tensorcore distillation quantization hardware-aware mixed-precision model-compression efficient-neural-networks quantized-neural-networks
Created 2020-11-24
48 commits to main branch, last one about a year ago
hailo-ai
hailo_model_zoo hailo-ai
47
347
mit
23
The Hailo Model Zoo includes pre-trained models and a full building and evaluation environment
hailo hailo8 edge-ai quantization deep-learning ai-accelerators computer-vision quantized-neural-networks
Created 2021-07-13
625 commits to master branch, last one about a month ago
amirgholami
ZeroQ amirgholami
56
274
unknown
17
[CVPR'20] ZeroQ: A Novel Zero Shot Quantization Framework
compression quantization efficient-model efficient-neural-networks quantized-neural-networks
Created 2019-11-20
21 commits to master branch, last one 4 years ago
fastmachinelearning
qonnx fastmachinelearning
40
131
apache-2.0
21
QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX
fpga onnx inference quantization deep-learning machine-learning quantized-neural-networks
Created 2021-07-07
674 commits to main branch, last one a day ago
megvii-research
megvii-tsinghua-dl-course megvii-research
2
57
unknown
8
Slides with modifications for a course at Tsinghua University.
deep-learning image-signal-processing quantized-neural-networks
Created 2022-05-25
27 commits to main branch, last one 2 years ago
Zhen-Dong
BitPack Zhen-Dong
11
50
mit
11
BitPack is a practical tool to efficiently save ultra-low precision/mixed-precision quantized models.
memory pytorch quantization mixed-precision model-compression quantized-neural-networks
Created 2021-02-08
19 commits to main branch, last one about a year ago
mrusci
training-mixed-precision-quantized-networks mrusci
16
49
unknown
2
This repository containts the pytorch scripts to train mixed-precision networks for microcontroller deployment, based on the memory contraints of the target device.
qnn edge-ai pytorch low-power-mcu integer-arithmetic mixed-precision-training quantized-neural-networks
Created 2019-06-12
3 commits to master branch, last one 5 years ago
htqin
QuantSR htqin
2
43
apache-2.0
3
[NeurIPS 2023 Spotlight] This project is the official implementation of our accepted NeurIPS 2023 (spotlight) paper QuantSR: Accurate Low-bit Quantization for Efficient Image Super-Resolution.
super-resolution model-quantization quantized-neural-networks
Created 2023-10-19
3 commits to main branch, last one 7 months ago