Error deploying on Google App Engine - Missing key(s)

[Bliss]

Hi,
I have had several issues when deploying on Google App Engine and solved them thanks to this forum but I am not sure how to progress with the following one:

I am deploying a modified version of the bear classification. The “gcloud app deploy” command throws the error below (it seems as is the model is not properly loaded?)

Any hint that may point me to the right path will be welcome.
Thanks!

File “/usr/local/lib/python3.6/site-packages/torch/nn/modules/module.py”, line 769, in load_state_dict
self.class.name, “\n\t”.join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for Sequential:
Missing key(s) in state_dict: “0.0.weight”, “0.1.weight”, “0.1.bias”, “0.1.running_mean”, “0.1.running_var”, …

Unexpected key(s) in state_dict: “opt_func”, “loss_func”, “metrics”, “true_wd”, “bn_wd”, “wd”, “train_bn”, “model_dir”, “callback_fns”, “cb_state”, “model”, “data”, “cls”.
The command ‘/bin/sh -c python app/server.py’ returned a non-zero code: 1

[jinudaniel]

I think even I ran into this error while deploying my app to App Engine. Try to use export.pkl file instead of the pth file. Also use the method load_learner instead of ImageDataBunch.single_from_classes. Do refer my previous answer for more details

Gcloud app engine error

Thanks for the help. I was able to download the model via wget but i encountered a another issue while deploying the app. It was related to transforms. While debugging i could see that the starter code for Google App Engine uses a deprecated method for making inference ImageDataBunch.single_from_classes. Check the source code for mode details. So I have modified my server.py to use load_learner and used export.pkl file instead of using model.pth file. After that I was able to deploy the app to …

Also refer the below post and see if it helps you.

[SOLVED] Error when trying to deploy model on Google App Engine (and locally)

Thank you very much for the useful info. I am now able to get rid of the transform related problem by referring to your post. However, now I got another error, AttributeError, complaining about an non-existant attribute ImageItemList. It appears to me as a code version problem of my fastai package, but I am already using the latest version 1.0.46. Have you encounter such problem in your case? /Users/ji/anaconda3/envs/test-app/lib/python3.7/site-packages/torch/serialization.py:435: SourceChangeW…

[Bliss]

Thanks a lot!
It was the deprecated ImageDataBunch.single_from_classes … also your code example was very useful. It is now deployed

Now I have another problem… it stays in “Analyzing” and I have an error in the log (TypeError: Object of type ‘Category’ is not JSON serializable) … but I will look for this in the forum or open a new thread, as it is not related to app deployment.

Thanks!

[jinudaniel]

Do refer this post. It contains the answer you are looking for.

[SOLVED] Error when trying to deploy model on Google App Engine (and locally)

[Solved] It turns out that the reason that I am getting the error AttributeError: Can't get attribute 'ImageItemList' is because I was using a different version of fastai to generate export.pkl (fastai 1.0.42) from the one used in production (fastai 1.0.46). Thanks to the explanation here. After I update my development env to use fastai 1.0.46 and retrained the model, the error is no more. Other complications that I have overcome to deploy the app on Google App Engine: server.py: setup_lea…