A repository that shares tuning results of trained models generated by TensorFlow / Keras. Post-training quantization (Weight Quantization, Integer Quantization, Full Integer Quantization, Float16 Quantization), Quantization-aware training. TensorFlow Lite. OpenVINO. CoreML. TensorFlow.js. TF-TRT. MediaPipe. ONNX. [.tflite,.h5,.pb,saved_model,tfjs,tftrt,mlmodel,.xml/.bin, .onnx]
reproduce simple cv project including classification, object detection, segmentation, keypoint detection, tracking, attention mechanism:smile: etc.
MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB:fire::fire::fire:
This Repository is implementation of majority of Semantic Segmentation Loss Functions
Semantic image segmentation network with pyramid atrous convolution and boundary-aware loss for Tensorflow.
This repository contains code for CNN-based segmentation of medical images/volumes.
Segmentation models with pretrained backbones. Keras and TensorFlow Keras.