xyz

Question in DET_train_30classes.txt

3

Why every file root ends with a one? like train/ILSVRC2013_train/n02391049/n02391049_8321 1 train/ILSVRC2013_train/n02391049/n02391049_8340 1 train/ILSVRC2013_train/n02391049/n02391049_835 1 Useless? Am i right? Thanks?

想问一下light_cnn_small是什么？

1

您好，请问这个light_cnn_small的怎么样的模型？没有参考可以看？

> RuntimeError: Error(s) in loading state_dict for DFF: Missing key(s) in state_dict: "ada_learner.conv1.0.weight", "ada_learner.conv1.0.bias", "ada_learner.conv1.1.weight", "ada_learner.conv1.1.bias", "ada_learner.conv1.1.running_mean", "ada_learner.conv1.1.running_var", "ada_learner.conv2.0.weight", "ada_learner.conv2.0.bias", "ada_learner.conv2.1.weight", "ada_learner.conv2.1.bias", "ada_learner.conv2.1.running_mean", "ada_learner.conv2.1.running_var", "ada_learner.conv3.0.weight", "ada_learner.conv3.0.bias", "ada_learner.conv3.1.weight", "ada_learner.conv3.1.bias", "ada_learner.conv3.1.running_mean", "ada_learner.conv3.1.running_var",...

Hi, I am very curious about you training method, you return a new ADAM and reload the best model for next stage. It seems different from the other traditional methods...

validation的选择

13

请问您这个是不是只有train test，没有val？