#hide
! [ -e /content ] && pip install -Uqq fastbook
import fastbook
fastbook.setup_book()

#hide
from fastbook import *

from fastai.vision.all import *
path = untar_data(URLs.IMAGENETTE)

dblock = DataBlock(blocks=(ImageBlock(), CategoryBlock()),
                   get_items=get_image_files,
                   get_y=parent_label,
                   item_tfms=Resize(460),
                   batch_tfms=aug_transforms(size=224, min_scale=0.75))
dls = dblock.dataloaders(path, bs=64)

model = xresnet50(n_out=dls.c)
learn = Learner(dls, model, loss_func=CrossEntropyLossFlat(), metrics=accuracy)
learn.fit_one_cycle(5, 3e-3)

x,y = dls.one_batch()
x.mean(dim=[0,2,3]),x.std(dim=[0,2,3])

def get_dls(bs, size):
    dblock = DataBlock(blocks=(ImageBlock, CategoryBlock),
                   get_items=get_image_files,
                   get_y=parent_label,
                   item_tfms=Resize(460),
                   batch_tfms=[*aug_transforms(size=size, min_scale=0.75),
                               Normalize.from_stats(*imagenet_stats)])
    return dblock.dataloaders(path, bs=bs)

dls = get_dls(64, 224)

x,y = dls.one_batch()
x.mean(dim=[0,2,3]),x.std(dim=[0,2,3])

model = xresnet50(n_out=dls.c)
learn = Learner(dls, model, loss_func=CrossEntropyLossFlat(), metrics=accuracy)
learn.fit_one_cycle(5, 3e-3)

dls = get_dls(128, 128)
learn = Learner(dls, xresnet50(n_out=dls.c), loss_func=CrossEntropyLossFlat(), 
                metrics=accuracy)
learn.fit_one_cycle(4, 3e-3)

learn.dls = get_dls(64, 224)
learn.fine_tune(5, 1e-3)

preds,targs = learn.tta()
accuracy(preds, targs).item()

church = PILImage.create(get_image_files_sorted(path/'train'/'n03028079')[0])
gas = PILImage.create(get_image_files_sorted(path/'train'/'n03425413')[0])
church = church.resize((256,256))
gas = gas.resize((256,256))
tchurch = tensor(church).float() / 255.
tgas = tensor(gas).float() / 255.

_,axs = plt.subplots(1, 3, figsize=(12,4))
show_image(tchurch, ax=axs[0]);
show_image(tgas, ax=axs[1]);
show_image((0.3*tchurch + 0.7*tgas), ax=axs[2]);