lyk125 / caffe-int8-convert-tools
This convert tools is base on TensorRT 2.0 Int8 calibration tools,which use the KL algorithm to find the suitable threshold to quantize the activions from Float32 to Int8(-128 - 127).
☆27Updated 6 years ago
Alternatives and similar repositories for caffe-int8-convert-tools:
Users that are interested in caffe-int8-convert-tools are comparing it to the libraries listed below
- ☆147Updated 6 years ago
- ☆38Updated 8 years ago
- mobilenet 与darknet yolo☆97Updated 7 years ago
- YOLOv2 object detection based on Caffe☆39Updated 6 years ago
- mobilenet ssd @ ncnn☆72Updated 7 years ago
- This is caffe implementation of shuffleNet V2☆69Updated 6 years ago
- Merge Batch Norm caffe☆64Updated 6 years ago
- A caffe implementation of Mnasnet: MnasNet: Platform-Aware Neural Architecture Search for Mobile.☆52Updated 6 years ago
- Caffe implementation of ReLU6 Layer☆46Updated 7 years ago
- Conversion of yolo from DarkNet to Caffe☆26Updated 6 years ago
- A C++ API of the LFFD with ncnn☆99Updated 5 years ago
- a caffe implementation of mobilefacenet,with the record of trainnig log☆115Updated 7 years ago
- ☆122Updated 6 years ago
- Caffe Implementation of MobileNets V3☆130Updated 5 years ago
- The benchmark of ncnn that is a high-performance neural network inference framework optimized for the mobile platform☆72Updated 6 years ago
- caffe implementation of insightface's combined margin method☆92Updated 5 years ago
- A simple example implementing mobilefacenet for face recognition on ncnn☆59Updated 6 years ago
- ncnn is a high-performance neural network inference framework optimized for the mobile platform☆14Updated 2 years ago
- Real-time iris detector. Only need 8ms on Intel i5 CPU!☆21Updated 6 years ago
- The implementation of Focal-Loss Using Caffe☆37Updated 7 years ago
- Convert MXNet model to Caffe model☆113Updated 5 years ago
- MobileNet-v2 experimental network description for caffe☆99Updated 6 years ago
- Caffe: a fast open framework for deep learning.☆38Updated 6 years ago
- 对yolo模型进行网络压缩、修剪等实验☆51Updated 7 years ago
- Retinaface caffe with mnetv2 0.25(and many more)☆57Updated 5 years ago
- faster-rcnn c++ python model☆14Updated 7 years ago
- ☆34Updated 6 years ago
- Merge convolution and batchnorm layers in both Caffe and PyTorch using Python☆18Updated 6 years ago
- ☆35Updated 7 years ago
- ncnn vs2015 examples demo☆68Updated 7 years ago