YOLOv5 Series Multi-backbone(TPH-YOLOv5, Ghostnet, ShuffleNetv2, Mobilenetv3Small, EfficientNetLite, PP-LCNet, SwinTransformer YOLO), Module(CBAM, DCN), Pruning (EagleEye, Network Slimming), Quantization (MQBench) and Deployment (TensorRT, ncnn) Compression Tool Box.
991
stars
201
forks
source link
在update_yaml中的疑惑 #34
Closed
linklist2 closed 2 years ago
您好,请问在获取SPPF中的e参数时,为什么要在name等于cv1时乘以0.5,再除以cv2的输出通道c2呢? 而不是以下这种呢?