Export in the wrong place ?

[Cdk29]

I am not 100 % sure it is a bug.

Running code from here : https://github.com/Cdk29/Cassava/blob/main/Xresnet.md

Particularly :

I create the learner using :

learnR <- dataloader %>% cnn_learner(xresnet50(), metrics = accuracy(), model_dir="Xresnet_files/") #prettier

But fastai export it elsewhere :

erolland@erolland-GL75-9SE:~/Bureau$ locate xresnet_50.pkl

/home/erolland/Bureau/Cassava/cassava-leaf-disease-classification/train_images/xresnet_50.pkl

I am not sure but I don't think it is the normal behavior of the export of fastai to use the directory of the training set and not the model_dir to export its model.

[turgut090]

Could you do the same but with python and see that works as you intended? However, here is the path argument, could specify ur path here, as well? https://github.com/henry090/fastai/blob/a37c463c7ab9494729089924ac0f933439730651/R/image_loaders.R#L368-L373

[Cdk29]

Sorry I did not understood, my post was not maybe perfectly clear.

The export is made here :

learnR$export(fname = "xresnet_50.pkl")

Since the learner is created like this :

model_dir="Xresnet_files/")

I expected the exported model to go in the model directory.

[turgut090]

Yes, I got it. I am not sure why. Could you run this code from the python side? If it works fine (same folder), then I can take a look