Fine-Tuning

[astonzhang]

https://d2l.ai/chapter_computer-vision/fine-tuning.html

[yuezhuang1387]

I find hotdog is 934 in ImageNet

[min_xu]

in Exercises4:
in my opinion, we can copy the hotdog_w into the parameters of fc.

when i use xavier_uniform_ only, the training process is

when i copy hotdog_w into fc in the begining of training, the loss is smaller than before.