How to get an empty ConvLearner for single image prediction?

Part 1 (2019)
12

I got it working!

I had to basically trick the ImageDataBunch constructor by feeding it some fake filenames, but I appear to have managed to deploy a pre-calculated model on a non-GPU machine!

Here’s the rough outline I used. I had to hard-code in my list of labels:

cat_images_path = Path("/tmp")
cat_fnames = [
    "/{}_1.jpg".format(c)
    for c in [
        "Bobcat",
        "Mountain-Lion",
        "Domestic-Cat",
        "Western-Bobcat",
        "Canada-Lynx",
        "North-American-Mountain-Lion",
        "Eastern-Bobcat",
        "Central-American-Ocelot",
        "Ocelot",
        "Jaguar",
    ]
]
cat_data = ImageDataBunch.from_name_re(
    cat_images_path,
    cat_fnames,
    r"/([^/]+)_\d+.jpg$",
    ds_tfms=get_transforms(),
    size=224,
)
cat_learner = ConvLearner(cat_data, models.resnet34)
cat_learner.model.load_state_dict(
    torch.load("usa-inaturalist-cats.pth", map_location="cpu")
)

Now I can evaluate a new image like so:

img = open_image(BytesIO(bytes))
losses = img.predict(cat_learner)
prediction = cat_learner.data.classes[losses.argmax()]

Note that I’m loading models.resnet34 (which means downloading it the first time the code is imported) even though I don’t think it’s actually needed since I’m using the model from disk. I couldn’t figure out how to call the ConvLearner constructor without it.

14 Likes