Aleksei Bochkovskii
Aleksei Bochkovskii
@WongKinYiu Hi, This is already done: https://github.com/AlexeyAB/darknet/blob/d51d89053afc4b7f50a30ace7b2fcf1b2ddd7598/src/dropout_layer_kernels.cu#L28-L31 * May be we should increase drop probability during whole training instead of half the training process * Or may be drop-block requires...
@WongKinYiu Hi, > Do you need an ImageNet pre-trained model which has more layers + more parameters + more outputs ? If yes, I can train a model. Or if...
@WongKinYiu All with MISH-activation and **608x608** network resolution on GeForce RTX 2070: * csresnext50.cfg - **51.2 FPS** * csdarknet53.cfg - **53.6 FPS** * csresnext50morelayers.cfg.txt - **44.0 FPS** * csresnext50sub.cfg.txt -...
@WongKinYiu Thanks! So SpineNet-49 is worse than csdarknet53 and csresnext50 **at least for ImageNet** * spinenet49.cfg.txt - 43.2 FPS - 78.3% | 94.6% * csdarknet53.cfg - 53.6 FPS - 78.7%...
Yes, SpineNet-49 has fewer params and flops, but CSPDarkNet-53 faster and more accurate for Classifier. But may be SpineNet-49 more accurate for Detector.
@WongKinYiu Thanks! Do you mean `csresnext50morelayers.cfg` or CSPDarkNet-53-morelayers? https://github.com/WongKinYiu/CrossStagePartialNetworks/issues/6#issuecomment-584406057
@WongKinYiu So `csresnext50morelayers.cfg` is worse than `csresnext50.cfg` (Top1 79.4% vs 79.8%) on ImageNet. https://github.com/WongKinYiu/CrossStagePartialNetworks/blob/master/imagenet/results.md But I think `csresnext50morelayers.cfg` will be better as backbone for Detector.
@WongKinYiu Ok, I can make 2 cfg-files, with `[net] mosaic=1 dynamic_minibatch=1` and mish-activation: 1. csresnext50morelayers + SPP_PAN 2. csresnext50morelayers + SPP+ASFF+BiFPN ---- Will we try to test new label_smoothing for...
@glenn-jocher > I implemented cosine lr scheduler a couple weeks ago, it worked well (+0.3 mAP) though I noticed it worked better if I raised the initial LR. Before with...
@glenn-jocher >  Why does MAP grow sharply at the very end?