Skip to content
This repository has been archived by the owner on Jun 25, 2024. It is now read-only.

Re-implemented SSD has high loss and low acc during training #158

Open
Yurodidon opened this issue Dec 7, 2019 · 3 comments
Open

Re-implemented SSD has high loss and low acc during training #158

Yurodidon opened this issue Dec 7, 2019 · 3 comments

Comments

@Yurodidon
Copy link

I implemented the SSD follow this project, but when I was training on PASCAL VOC2007 dataset, the acc became smaller and smaller, at the same time the loss is around 4.0.

The codes are available on https://github.com/CeLaMbDa/keras_SSD

@Ryo-Kawanami
Copy link

I'm also same situation...
I have trained during 16 epoch, but loss, acc, val_loss, val_acc are almost same.

@Ryo-Kawanami
Copy link

Could anybody who knows this situation help?

@Yurodidon
Copy link
Author

Hi Ryo-Kawanam, I think I found the reason of this situation!
Check these:

  1. Do not use metrics in training, I don't know why, but still, when I delete those metrics, the network works much better.
  2. You should compile model after freezing layers, this was pointed out in the official document, please refer to https://keras.io/getting-started/faq/#how-can-i-freeze-keras-layers
  3. Use a fit learning rate, the can't be to small or too big, if it is too small it might lead the weights can't change.

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants