from fastai.vision import *
from fastai.widgets import DatasetFormatter, ImageCleaner, ImageDownloader, download_google_images
from fastai.gen_doc.nbdoc import *

%reload_ext autoreload
%autoreload 2

path = untar_data(URLs.MNIST_SAMPLE)
data = ImageDataBunch.from_folder(path)

learn = cnn_learner(data, models.resnet18, metrics=error_rate)

learn.fit_one_cycle(2)

learn.save('stage-1')

db = (ImageList.from_folder(path)
                   .split_none()
                   .label_from_folder()
                   .databunch())

learn = cnn_learner(db, models.resnet18, metrics=[accuracy])
learn.load('stage-1');

show_doc(DatasetFormatter)

show_doc(DatasetFormatter.from_similars)

from fastai.gen_doc.nbdoc import *
from fastai.widgets.image_cleaner import * 

show_doc(DatasetFormatter.from_toplosses)

show_doc(ImageCleaner)

ds, idxs = DatasetFormatter().from_toplosses(learn)

ImageCleaner(ds, idxs, path)

df = pd.read_csv(path/'cleaned.csv', header='infer')

# We create a databunch from our csv. We include the data in the training set and we don't use a validation set (DatasetFormatter uses only the training set)
np.random.seed(42)
db = (ImageList.from_df(df, path)
                   .split_none()
                   .label_from_df()
                   .databunch(bs=64))

learn = cnn_learner(db, models.resnet18, metrics=error_rate)
learn = learn.load('stage-1')

ds, idxs = DatasetFormatter().from_similars(learn, layer_ls=[0,7,1], pool=None)

ImageCleaner(ds, idxs, path, duplicates=True)

show_doc(ImageDownloader)

path = Config.data_path()/'image_downloader'
os.makedirs(path, exist_ok=True)
ImageDownloader(path)

path = Config.data_path()/'image_downloader'
files = download_google_images(path, 'aussie shepherd', size='>1024*768', n_images=30)

len(files)

show_doc(download_google_images)

# Setup path and labels to search for
path = Config.data_path()/'image_downloader'
labels = ['boston terrier', 'french bulldog']

# Download images
for label in labels: 
    download_google_images(path, label, size='>400*300', n_images=50)

# Build a databunch and train! 
src = (ImageList.from_folder(path)
       .split_by_rand_pct()
       .label_from_folder()
       .transform(get_transforms(), size=224))

db  = src.databunch(bs=16, num_workers=0)

learn = cnn_learner(db, models.resnet34, metrics=[accuracy])
learn.fit_one_cycle(3)

show_doc(ImageCleaner.make_dropdown_widget)

show_doc(ImageCleaner.next_batch)

show_doc(DatasetFormatter.sort_idxs)

show_doc(ImageCleaner.make_vertical_box)

show_doc(ImageCleaner.relabel)

show_doc(DatasetFormatter.largest_indices)

show_doc(ImageCleaner.delete_image)

show_doc(ImageCleaner.empty)

show_doc(ImageCleaner.empty_batch)

show_doc(DatasetFormatter.comb_similarity)

show_doc(ImageCleaner.get_widgets)

show_doc(ImageCleaner.write_csv)

show_doc(ImageCleaner.create_image_list)

show_doc(ImageCleaner.render)

show_doc(DatasetFormatter.get_similars_idxs)

show_doc(ImageCleaner.on_delete)

show_doc(ImageCleaner.make_button_widget)

show_doc(ImageCleaner.make_img_widget)

show_doc(DatasetFormatter.get_actns)

show_doc(ImageCleaner.batch_contains_deleted)

show_doc(ImageCleaner.make_horizontal_box)

show_doc(DatasetFormatter.get_toplosses_idxs)

show_doc(DatasetFormatter.padded_ds)