hemp110
hemp110
稀疏训练指标异常
训练过程如下 ``` [Epoch 0/20, Batch 13/2302] [Losses: x 0.204015, y 0.214396, w 4.140403, h 1.606703, conf 30.286903, cls 0.171045, total 36.623466, recall: 0.00000, precision: 0.00000] [Epoch 0/20, Batch 23/2302] [Losses:...
@ChriswooTalent could you please provide a yolov3 prototxt explain how to implement the special layers in yolov3, e.g., shortcut, route, upsample explain the difference between yolov3Detection_layer and yolov3DetectResult_layer
Thanks for sharing the code. When I run the BGAN code, I find that the pretrained vgg19-like model is crucial. So how to train the model on ImageNet since it...
I mean mAP and NDS in the second table.