Pinned Repositories
model-compression
model compression based on pytorch (1、quantization: 8/4/2bits(dorefa)、ternary/binary value(twn/bnn/xnor-net)；2、 pruning: normal、regular and group convolutional channel pruning；3、 group convolution structure；4、batch-normalization folding for binary value of feature(A))
PI-DECODER
precise iris segmentation
yolov5
YOLOv5 in PyTorch > ONNX > CoreML > TFLite
Ryz-dl's Repositories
Ryz-dl/model-compression
model compression based on pytorch (1、quantization: 8/4/2bits(dorefa)、ternary/binary value(twn/bnn/xnor-net)；2、 pruning: normal、regular and group convolutional channel pruning；3、 group convolution structure；4、batch-normalization folding for binary value of feature(A))
Ryz-dl/PI-DECODER
precise iris segmentation
Ryz-dl/yolov5
YOLOv5 in PyTorch > ONNX > CoreML > TFLite