I transfer the backend of yolov3 into Mobilenetv1,VGG16,ResNet101 and ResNeXt101
:zap: Yolo universal target detection model combined with EfficientNet-lite, the calculation amount is only 230Mflops(0.23Bflops), and the model size is 1.3MB
Train and predict your model on pre-trained deep learning models through the GUI (web app). No more many parameters, no more data preprocessing.
Samples for CUDA Developers which demonstrates features in CUDA Toolkit
Implementation of popular deep learning networks with TensorRT network definition APIs
Pesteh-Set, the pistachios dataset from the paper https://arxiv.org/abs/2005.03990