-
Notifications
You must be signed in to change notification settings - Fork 5
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
'run.py' line44 #3
Comments
Did you train the full 30 epochs of "augmentation+smoothing+pretrain_cnn+freeze_cnn"? So this is actually searching for the model that saved in the previous training. You should train the full 30 epoch, and you should find a 20.pt in the folder. For your last question, it is ok to load models/18.pt, which gives you the model of the 18th epoch of the aforementioned training. |
I fixed the problem. It was my mistake. after running 1 epoch, there was error on evaluating SPICE metric(I didn't run .sh file in coco_caption). Thank you |
Hi @jiminbot20, no problem! Glad you succeed :). |
This is line 44 in run.py
![image](https://user-images.githubusercontent.com/63258184/93317729-c5e9f780-f848-11ea-965a-89b163fda73b.png)
caption_model_path ='models/augmentation+smoothing+pretrain_cnn+freeze_cnn/20.pt'
Then this error occurs
FileNotFoundError: [Errno 2] No such file or directory: 'models/augmentation+smoothing+pretrain_cnn+freeze_cnn/20.pt'
there is no '20.pt' then '18.pt'. so is it fine to change line 44 to code below?
caption_model_path ='models/18.pt'
The text was updated successfully, but these errors were encountered: