def get_annotations(): annot_urls = [ '5458/bet_labels.json', '5459/shark_labels.json', '5460/dol_labels.json', '5461/yft_labels.json', '5462/alb_labels.json', '5463/lag_labels.json' ] cache_subdir = os.path.abspath(os.path.join(PATH, 'annos')) url_prefix = 'https://kaggle2.blob.core.windows.net/forum-message-attachments/147157/' os.makedirs(cache_subdir, exist_ok=True) for url_suffix in annot_urls: fname = url_suffix.rsplit('/', 1)[-1] get_data(url_prefix + url_suffix, f'{cache_subdir}/{fname}')
def download_cifar10(data_path): # (AS) TODO: put this into the fastai library def untar_file(file_path, save_path): if file_path.endswith('.tar.gz') or file_path.endswith('.tgz'): obj = tarfile.open(file_path) obj.extractall(save_path) obj.close() os.remove(file_path) cifar_url = 'http://files.fast.ai/data/cifar10.tgz' # faster download # cifar_url = 'http://pjreddie.com/media/files/cifar.tgz' io.get_data(cifar_url, args.data + '/cifar10.tgz') untar_file(data_path + '/cifar10.tgz', data_path) # Loader expects train and test folders to be outside of cifar10 folder shutil.move(data_path + '/cifar10/train', data_path) shutil.move(data_path + '/cifar10/test', data_path)
def download_cifar10(data_path): # (AS) TODO: put this into the fastai library def untar_file(file_path, save_path): if file_path.endswith('.tar.gz') or file_path.endswith('.tgz'): obj = tarfile.open(file_path) obj.extractall(save_path) obj.close() os.remove(file_path) cifar_url = 'http://files.fast.ai/data/cifar10.tgz' # faster download # cifar_url = 'http://pjreddie.com/media/files/cifar.tgz' io.get_data(cifar_url, args.data+'/cifar10.tgz') untar_file(data_path+'/cifar10.tgz', data_path) # Loader expects train and test folders to be outside of cifar10 folder shutil.move(data_path+'/cifar10/train', data_path) shutil.move(data_path+'/cifar10/test', data_path)
ft_words = sorted(ft_word_dict.keys(), key=lambda x: ft_word_dict[x]) len(ft_words) # In[17]: from fastai.io import get_data # In[18]: CLASSES_FN = 'imagenet_class_index.json' get_data(f'http://files.fast.ai/models/{CLASSES_FN}', TMP_PATH/CLASSES_FN) # In[19]: WORDS_FN = 'classids.txt' get_data(f'http://files.fast.ai/data/{WORDS_FN}', PATH/WORDS_FN) # In[20]: class_dict = json.load((TMP_PATH/CLASSES_FN).open()) classids_1k = dict(class_dict.values()) nclass = len(class_dict); nclass