app.py

import fastbook
fastbook.setup_book()
from fastbook import *
from fastai.vision.widgets import *
key = os.environ.get('AZURE_SEARCH_KEY', 'XXX')
search_images_bing
search_images_ddg

doc(search_images_ddg)
def search_images(term):
  url ='https://duckduckgo.com/'
  res = urlread(url,data={'q':term})
  searchObj=re.search(r'vqd=([\d-]+)\&',res)
  requestUrl = url + 'i.js'
  params = dict(l='us-en',o='json', q= term, vqd=searchObj.group(1), f=',,,', p='1', v7exp='a')
  urls,data = set(),{'next':1}
  while len(urls)<max_images and 'next' in data:
    data = urljson(requestUrl,data=params)
    urls.update(L(data['results']).itemgot('image'))
    requestUrl = url + data['next']
    time.sleep(0.2)
  return L(urls)[:max_images]
ims = ['http://3.bp.blogspot.com/-S1scRCkI3vY/UHzV2kucsPI/AAAAAAAAA-k/YQ5UzHEm9Ss/s1600/Grizzly%2BBear%2BWildlife.jpg']
dest = 'images/grizzly.jpg'
download_url(ims[0], dest)
im = Image.open(dest)
im.to_thumb(128,128)
bear_types = 'grizzly','black','teddy'
path = Path('bears')

doc(Path)
if not path.exists():
    path.mkdir()
    for o in bear_types:
        dest = (path/o)
        dest.mkdir(exist_ok=True)
        results = search_images_ddg(f'{o} bear', 150)
        print(results)
        download_images(dest, urls=results)
fns = get_image_files(path)
fns
failed = verify_images(fns)
failed
#??verify_images
failed = verify_images(fns)
failed
class DataLoaders(GetAttr):
    def __init__(self, *loaders): self.loaders = loaders
    def __getitem__(self, i): return self.loaders[i]
    train,valid = add_props(lambda i,self: self[i])
bears = DataBlock(
    blocks=(ImageBlock, CategoryBlock),
    get_items=get_image_files,
    splitter=RandomSplitter(valid_pct=0.2, seed=42),
    get_y=parent_label,
    item_tfms=Resize(128))

doc(DataBlock)
# Create a DataLoaders object from source
dls = bears.dataloaders(path)
dls.valid.show_batch(max_n=6, nrows=2)
doc(bears.new)
bears = bears.new(item_tfms=Resize(128, ResizeMethod.Squish))
dls = bears.dataloaders(path)
dls.valid.show_batch(max_n=6, nrows=1)
doc(bears.new)
bears = bears.new(item_tfms=Resize(128, ResizeMethod.Pad, pad_mode='zeros'))
dls = bears.dataloaders(path)
dls.valid.show_batch(max_n=6, nrows=2)
bears = bears.new(item_tfms=RandomResizedCrop(128, min_scale=0.3))
dls = bears.dataloaders(path)

doc(dls.train.show_batch)

# unique
dls.train.show_batch(max_n=3, nrows=1)
dls.train.show_batch(max_n=3, nrows=1, unique=True)
bears = bears.new(item_tfms=Resize(128), batch_tfms=aug_transforms(mult=2))
dls = bears.dataloaders(path)
dls.train.show_batch(max_n=8, nrows=2, unique=True)
bears = bears.new(
    item_tfms=RandomResizedCrop(128, min_scale=0.3),
    batch_tfms=aug_transforms())


dls = bears.dataloaders(path)

#dls.train.show_batch(max_n=8, nrows=2, unique=True)
learn = vision_learner(dls, resnet18, metrics=error_rate)
learn.fine_tune(4)
interp = ClassificationInterpretation.from_learner(learn)
interp.plot_confusion_matrix()
interp.plot_top_losses(3, nrows=2)

doc(interp.plot_top_losses)
#??interp.plot_top_losses

# According to the matplot docs it’s the image size in inches.
interp.plot_top_losses(3, nrows=2, figsize=(10,10))
#doc(ImageClassifierCleaner)
cleaner = ImageClassifierCleaner(learn)
cleaner
for idx in cleaner.delete(): cleaner.fns[idx].unlink()
for idx,cat in cleaner.change(): shutil.move(str(cleaner.fns[idx]), path/cat)
for idx in cleaner.delete(): cleaner.fns[idx].unlink()