finally:
pass
clean_all([input_path, output_path])
if __name__ == '__main__':
global upload_directory
global results_img_directory
global image_colorizer
upload_directory = '/data/upload/'
create_directory(upload_directory)
results_img_directory = '/data/result_images/'
create_directory(results_img_directory)
model_directory = '/data/models/'
create_directory(model_directory)
artistic_model_url = 'https://www.dropbox.com/s/zkehq1uwahhbc2o/ColorizeArtistic_gen.pth?dl=0'
get_model_bin(artistic_model_url,
os.path.join(model_directory, 'ColorizeArtistic_gen.pth'))
image_colorizer = get_image_colorizer(artistic=True)
image_colorizer.results_dir = Path(results_img_directory)
port = 5000
host = '0.0.0.0'
app.run(host=host, port=port, threaded=False)
global args
result_directory = '/src/results/'
create_directory(result_directory)
upload_directory = '/src/UGATIT/dataset/selfie2anime/testA/'
create_directory(upload_directory)
create_directory('/src/UGATIT/dataset/selfie2anime/testB/')
create_directory('/src/UGATIT/dataset/selfie2anime/trainA/')
create_directory('/src/UGATIT/dataset/selfie2anime/trainB/')
model_directory = '/src/checkpoint/'
create_directory(model_directory)
url_prefix = 'http://pretrained-models.auth-18b62333a540498882ff446ab602528b.storage.gra5.cloud.ovh.net/image/ugatit/selfie2anime/'
model_file_zip = 'ugatit-selfie2anime-pretrained.zip'
get_model_bin(url_prefix + model_file_zip,
os.path.join('/src', model_file_zip))
unzip(model_file_zip)
args = parse_args()
port = 5000
host = '0.0.0.0'
app.run(host=host, port=port, threaded=True)
create_directory(upload_directory)
create_directory('/src/UGATIT/dataset/selfie2anime/testB/')
create_directory('/src/UGATIT/dataset/selfie2anime/trainA/')
create_directory('/src/UGATIT/dataset/selfie2anime/trainB/')
model_directory = '/src/checkpoint/'
create_directory(model_directory)
url_prefix = 'http://pretrained-models.auth-18b62333a540498882ff446ab602528b.storage.gra5.cloud.ovh.net/image/'
model_file_rar = 'UGATIT_selfie2anime_lsgan_4resblock_6dis_1_1_10_10_1000_sn_smoothing.rar'
haarcascade_file = 'haarcascade_frontalface_default.xml'
get_model_bin(url_prefix + "ugatit/selfie2anime/" + model_file_rar,
os.path.join('/src', model_file_rar))
unrar(model_file_rar, model_directory)
get_model_bin(url_prefix + "haarcascade/" + haarcascade_file,
os.path.join('/src', haarcascade_file))
args = parse_args()
sess = tf.InteractiveSession(config=tf.ConfigProto(
allow_soft_placement=True, inter_op_parallelism_threads=1))
gan = UGATIT(sess, args)
gan.build_model()
gan.test_endpoint_init()
traceback.print_exc()
return {'message': 'input error'}, 400
finally:
clean_all([
input_path
])
shutil.rmtree(os.path.join(img_output_dir, args.img_name))
if __name__ == '__main__':
global upload_directory, weight_file
global ALLOWED_EXTENSIONS
ALLOWED_EXTENSIONS = set(['png', 'jpg', 'jpeg'])
upload_directory = '/src/upload/'
create_directory(upload_directory)
weight_directory = '/src/'
weight_file = 'imagenet-vgg-verydeep-19.mat'
url_prefix = 'http://pretrained-models.auth-18b62333a540498882ff446ab602528b.storage.gra.cloud.ovh.net/image/neural-style-tf/'
get_model_bin(url_prefix + weight_file , weight_directory + weight_file)
port = 5000
host = '0.0.0.0'
app.run(host=host, port=port, threaded=True)
finally:
clean_all([
input_path,
output_path
])
if __name__ == '__main__':
global upload_directory
global results_video_directory
global video_colorizer
upload_directory = '/data/upload/'
create_directory(upload_directory)
results_video_directory = '/data/video/result/'
create_directory(results_video_directory)
model_directory = '/data/models/'
create_directory(model_directory)
video_model_url = 'https://www.dropbox.com/s/336vn9y4qwyg9yz/ColorizeVideo_gen.pth?dl=0'
get_model_bin(video_model_url, os.path.join(model_directory, 'ColorizeVideo_gen.pth'))
video_colorizer = get_video_colorizer()
port = 5000
host = '0.0.0.0'
app.run(host=host, port=port, threaded=False)
global deblur
global train_dir
global graph
global sess
global ALLOWED_EXTENSIONS
ALLOWED_EXTENSIONS = set(['png', 'jpg', 'jpeg'])
upload_directory = '/src/upload/'
create_directory(upload_directory)
checkpoint_dir = "/src/checkpoints/"
create_directory(checkpoint_dir)
url_prefix = 'http://pretrained-models.auth-18b62333a540498882ff446ab602528b.storage.gra.cloud.ovh.net/image/SRN-Deblur/'
model_zip = "srndeblur_models.zip"
get_model_bin(url_prefix + model_zip, checkpoint_dir + model_zip)
os.system("cd " + checkpoint_dir + " && unzip " + model_zip)
checkpoint_dir = os.path.join(checkpoint_dir, args.model)
deblur = model.DEBLUR(args)
port = 5000
host = '0.0.0.0'
app.run(host=host, port=port, threaded=True)
except:
traceback.print_exc()
return {'message': 'input error'}, 400
finally:
clean_all([
input_path,
output_path
])
if __name__ == '__main__':
global upload_directory
global model, net
upload_directory = 'upload'
create_directory(upload_directory)
model_name = "frozen_east_text_detection.pb"
model_url = "https://storage.gra5.cloud.ovh.net/v1/AUTH_18b62333a540498882ff446ab602528b/pretrained-models/" + model_name
get_model_bin(model_url , model_name)
net = cv2.dnn.readNet(model_name)
port = 5000
host = '0.0.0.0'
app.run(host=host, port=port, threaded=True)
upload_directory = '/src/upload/'
create_directory(upload_directory)
mobile_net_directory = '/src/models/mobile_net/'
xception_directory = '/src/models/xception/'
create_directory(mobile_net_directory)
create_directory(xception_directory)
url_prefix = 'http://pretrained-models.auth-18b62333a540498882ff446ab602528b.storage.gra.cloud.ovh.net/image/'
todo = []
for i in [
"frozen_inference_graph.pb",
"model.ckpt-30000.data-00000-of-00001", "model.ckpt-30000.index"
]:
get_model_bin(url_prefix + "mobile-net/" + i, mobile_net_directory + i)
for i in [
"frozen_inference_graph.pb", "model.ckpt.data-00000-of-00001 ",
"model.ckpt.index"
]:
get_model_bin(url_prefix + "xception/" + i, xception_directory + i)
#fast_graph_def = tf.GraphDef.FromString(open(mobile_net_directory + "frozen_inference_graph.pb", "rb").read())
slow_graph_def = tf.GraphDef.FromString(
open(xception_directory + "frozen_inference_graph.pb", "rb").read())
tf.import_graph_def(slow_graph_def, name='')
sess = tf.Session()
global rdn
global ALLOWED_EXTENSIONS
ALLOWED_EXTENSIONS = set(['png', 'jpg', 'jpeg'])
result_directory = '/src/results/'
create_directory(result_directory)
upload_directory = '/src/upload/'
create_directory(upload_directory)
model_directory = '/src/weights/'
create_directory(model_directory)
url_prefix = 'http://pretrained-models.auth-18b62333a540498882ff446ab602528b.storage.gra.cloud.ovh.net/image/'
model_file_rar = 'weights.rar'
get_model_bin(url_prefix + 'super-resolution/' + model_file_rar , os.path.join('/src', model_file_rar))
unrar(model_file_rar, '/src')
rdn = RDN(arch_params={'C':6, 'D':20, 'G':64, 'G0':64, 'x':2})
rdn.model.load_weights('weights/sample_weights/rdn-C6-D20-G64-G064-x2/ArtefactCancelling/rdn-C6-D20-G64-G064-x2_ArtefactCancelling_epoch219.hdf5')
port = 5000
host = '0.0.0.0'
app.run(host=host, port=port, threaded=False)
BOT_TOKEN = os.environ["BOT_TOKEN"]
# Set upload directory and create if not exists
upload_directory = '/data/upload'
create_directory(upload_directory)
# Set result images directory and create if not exists
results_img_directory = '/data/result_images'
create_directory(results_img_directory)
# Set data model directory and create if not exists
model_directory = '/data/models'
create_directory(model_directory)
# only get the model binay if it not present in /data/models
get_model_bin(artistic_model_url,
os.path.join(model_directory, "ColorizeArtistic_gen.pth"))
image_colorizer = get_image_colorizer(artistic=True)
get_model_bin(video_model_url,
os.path.join(model_directory, "ColorizeVideo_gen.pth"))
video_colorizer = get_video_colorizer()
video_colorizer.result_folder = Path(results_img_directory)
def color(file_path, chat_id):
# set input and outpu file path
input_path = file_path
output_path = os.path.join(results_img_directory,
os.path.basename(input_path))
try:
finally:
clean_all([
input_path,
output_path
])
if __name__ == '__main__':
global upload_directory
global config, res_sizes
upload_directory = '/src/upload/'
create_directory(upload_directory)
config = tf.ConfigProto(device_count={'GPU': 0})
# get all available image resolutions
res_sizes = utils.get_resolutions()
url_prefix = 'http://pretrained-models.auth-18b62333a540498882ff446ab602528b.storage.gra.cloud.ovh.net/image/deep-photo-enhancement/'
for i in ["blackberry_orig.data-00000-of-00001", "blackberry_orig.index", "iphone_orig.data-00000-of-00001", "iphone_orig.index", "sony_orig.data-00000-of-00001", "sony_orig.index"]:
get_model_bin(url_prefix + i , "models_orig/" + i)
get_model_bin(url_prefix + "imagenet-vgg-verydeep-19.mat" , "models/imagenet-vgg-verydeep-19.mat")
port = 5000
host = '0.0.0.0'
app.run(host=host, port=port, threaded=True)
upload_directory = '/src/upload/'
create_directory(upload_directory)
model_directory = '/src/model/'
create_directory(model_directory)
model_name = 'efficientnet-b5'
model = EfficientNet.from_pretrained(model_name)
model.eval()
model_url = "https://storage.gra.cloud.ovh.net/v1/AUTH_18b62333a540498882ff446ab602528b/pretrained-models/image/EfficientNet-PyTorch/"
labels_file = 'labels_map.txt'
get_model_bin(model_url + labels_file, model_directory + labels_file)
labels_map = json.load(open(model_directory + labels_file))
labels_map = [labels_map[str(i)] for i in range(1000)]
# Preprocess image
tfms = transforms.Compose([
transforms.Resize(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
])
port = 5000
host = '0.0.0.0'
app.run(host=host, port=port, threaded=True)
ALLOWED_EXTENSIONS = set(['png', 'jpg', 'jpeg'])
upload_directory = '/src/upload/'
create_directory(upload_directory)
model_path = "/src/models/"
model_file = "resnet152_weights_tf.h5"
weights_file = "model.96-0.89.hdf5"
url_prefix = "https://storage.gra.cloud.ovh.net/v1/AUTH_18b62333a540498882ff446ab602528b/pretrained-models/image/"
for i in [model_file, weights_file]:
get_model_bin(url_prefix + "car-classifier/v0/" + i , model_path + i)
model, graph = load_my_model(model_path + model_file, model_path + weights_file)
img_width, img_height = 224, 224
cars_meta = scipy.io.loadmat('devkit/cars_meta')
class_names = cars_meta['class_names'] # shape=(1, 196)
class_names = np.transpose(class_names)
port = 5000
host = '0.0.0.0'
app.run(host=host, port=port, threaded=True)
if __name__ == '__main__':
global upload_directory, model_directory
global encode, decoder, start_text, hidden
upload_directory = 'upload/'
create_directory(upload_directory)
model_directory = 'model_weights/'
create_directory(model_directory)
encoder_file = 'encoder_resnet34_0.061650436371564865.pt'
decoder_file = 'decoder_resnet34_0.061650436371564865.pt'
model_url = "https://storage.gra.cloud.ovh.net/v1/AUTH_18b62333a540498882ff446ab602528b/pretrained-models/image/sketch2code/"
get_model_bin(model_url + encoder_file,
os.path.join(model_directory, encoder_file))
get_model_bin(model_url + decoder_file,
os.path.join(model_directory, decoder_file))
encoder = torch.load(os.path.join(model_directory, encoder_file))
decoder = torch.load(os.path.join(model_directory, decoder_file))
star_text = '<START>'
hidden = decoder.init_hidden()
port = 5000
host = '0.0.0.0'
app.run(host=host, port=port, threaded=True)
result_directory = '/src/results/'
create_directory(result_directory)
upload_directory = '/src/upload/'
create_directory(upload_directory)
prewarm = True if os.getenv('PREWARM', 'TRUE') == 'TRUE' else False
if prewarm:
model_scene_parsing = pretrained.pspnet_50_ADE_20K(
) # load the pretrained model trained on ADE20k dataset
model_cityscapes = pretrained.pspnet_101_cityscapes(
) # load the pretrained model trained on Cityscapes dataset
model_visual_object = pretrained.pspnet_101_voc12(
) # load the pretrained model trained on Pascal VOC 2012 dataset
else:
get_model_bin(
"https://www.dropbox.com/s/0uxn14y26jcui4v/pspnet50_ade20k.h5?dl=1",
"/root/.keras/dataset/pspnet50_ade20k.h5")
get_model_bin(
"https://www.dropbox.com/s/c17g94n946tpalb/pspnet101_cityscapes.h5?dl=1",
"/root/.keras/dataset/pspnet101_cityscapes.h5")
get_model_bin(
"https://www.dropbox.com/s/uvqj2cjo4b9c5wg/pspnet101_voc2012.h5?dl=1",
"/root/.keras/dataset/pspnet101_voc2012.h5")
port = 5000
host = '0.0.0.0'
app.run(host=host, port=port, threaded=False)
return json.dumps(results), 200
except:
traceback.print_exc()
return {'message': 'input error'}, 400
finally:
clean_all([input_path])
if __name__ == '__main__':
global model, graph
upload_directory = '/src/upload/'
create_directory(upload_directory)
model_directory = '/src/models/'
create_directory(model_directory)
moodel_url_prefix = "http://pretrained-models.auth-18b62333a540498882ff446ab602528b.storage.gra.cloud.ovh.net/text/programming-language/"
get_model_bin(moodel_url_prefix + "save_tmp.h5",
model_directory + "save_tmp.h5")
model = keras.models.load_model(model_directory + "save_tmp.h5")
graph = tf.get_default_graph()
port = 5000
host = '0.0.0.0'
app.run(host=host, port=port, threaded=True)
