How to train on the full dataset using ImageClassifierData.from_csv

Part 1 (2018)
41

@jamesrequa Thanks. Actually that was just loading the pretrained model from scatch so it should work. Pulling from github solved it :slight_smile:

1 Like
42

Yes you are correct that it will work with Precompute=True if you do it from scratch without ever creating those activations previously but I don’t think you would ever want to do that since you should never start by training with all of the data :slight_smile:

2 Likes
43

Is there any similar thing forImageClassifierData.from_paths api . If I leave validation folder empty , the code doesn’t like it very much.

1 Like
44

I had the same question and found the answer here (How to train on the full dataset using ImageClassifierData.from_csv)

The transforms downsize the images to 224 or 299. Reading the jpgs and resizing is slow for big images, so resizing them all to 340 first saves time.

45

Hi, for ImageClassifierData.from_paths() is there any alternative to copying the validation set back into the training path?