def post(self):
"""Brand and model classifcation
Image can be loaded either by using an internet URL in the url field or
by using a local stored image in the image field
"""
images = request.files.getlist('image')
url = request.form.get('url', None)
res = list()
if url:
try:
resp = urlopen(url)
img = np.asarray(bytearray(resp.read()), dtype="uint8")
img = cv2.imdecode(img, cv2.IMREAD_COLOR)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
res.append(predict_class(img))
except Exception as e:
print(url)
print(e)
if images:
for i in range(len(images)):
nparr = np.frombuffer(images[i].read(), np.uint8)
img = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
res.append(predict_class(img))
else:
abort(403)
return res
def test_class(img_clio4, img_clio_peugeot):
print('Testing image', img_clio_peugeot.shape)
res = predict_class(img_clio_peugeot)
for modele in ['CLIO', '208', 'A1', 'MINI']:
assert any([modele in vehicule['brand_model_classif']['label'] for vehicule in res]), 'There is no clio in first predictions'
print('Testing image', img_clio4.shape)
res = predict_class(img_clio4)
assert type(res) == list
assert any(['CLIO' in vehicule['brand_model_classif']['label'] for vehicule in res]), 'There is no clio in first predictions'
def lambda_handler_classification(event, context):
print("ENV", getenv('BACKEND'))
print("ENV", getenv('DETECTION_THRESHOLD'))
print("LISTDIR", listdir('/tmp'))
res = list()
body_str = event.get('image', None)
#c_type, c_data = parse_header(event['headers']['Content-Type'])
#assert c_type == 'multipart/form-data'
#decoded_string = base64.b64decode(event['body'])
#form_data = parse_multipart(BytesIO(decoded_string), c_data)
if body_str:
print(type(body_str))
print(body_str[:100])
# read encoded image
imageString = base64.b64decode(body_str)
# convert binary data to numpy array
nparr = np.frombuffer(imageString, np.uint8)
# let opencv decode image to correct format
img = cv2.imdecode(nparr, cv2.IMREAD_ANYCOLOR)
res.append(predict_class(img))
return {'statusCode': 200, 'body': json.dumps(res)}
def test_class(img_clio4):
print('Testing image', img_clio4.shape)
res = predict_class(img_clio4)
assert type(res) == list
assert any(['CLIO' in vehicule['label']
for vehicule in res]), 'There is no clio in first predictions'
def test_class_prio(img_clio4):
"""Test if 'CLASSIFICATION_MODEL_PRIO' in os.environ
"""
if 'CLASSIFICATION_MODEL_PRIO' in os.environ:
print('Testing image', img_clio4.shape)
res = predict_class(img_clio4)
#import pdb; pdb.set_trace()
assert type(res) == list
assert any(['CLIO' in vehicule['brand_model_classif']['label'] for vehicule in res]), 'There is no clio in first predictions'
assert any(['AUTRES' in vehicule['prio_classif']['label'] for vehicule in res]), 'There is no clio in first predictions'
else:
print('!!!! Test not executed, add CLASSIFICATION_MODEL_PRIO path !!!!!')
def long_task(self, video_name, rotation90, prob_detection,
prob_classification, selected_fps):
logger.debug(video_name)
res = dict()
cap = cv2.VideoCapture("/tmp/video", )
media_info = MediaInfo.parse('/tmp/video')
myjson = json.loads(media_info.to_json())
rotation = myjson['tracks'][1]['rotation']
total_rotation = int(float(rotation) / 90) + int(rotation90 / 90)
logger.debug('Rotation total {}'.format(rotation))
while not cap.isOpened():
cap = cv2.VideoCapture("/tmp/video", )
cv2.waitKey(1000)
logger.debug("Wait for the header")
pos_frame = cap.get(cv2.cv2.CAP_PROP_POS_FRAMES)
total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
fps = int(cap.get(cv2.CAP_PROP_FPS))
skip_images = int(fps / selected_fps)
logger.debug(
"Real fps {}, selected fps: {}, taking 1 image between {}".format(
fps, selected_fps, skip_images))
while True:
flag, frame = cap.read()
if flag:
# The frame is ready and already captured
pos_frame = int(cap.get(cv2.cv2.CAP_PROP_POS_FRAMES))
# Every 10 frames
if pos_frame % skip_images == 0:
h, w, _ = frame.shape
# frame = frame[0:h,int(2*w/3):w]
frame = frame[0:h, 0:w]
frame = rotate_frame90(frame, total_rotation)
self.update_state(state='PROGRESS',
meta={
'current':
pos_frame,
'total':
total_frames,
'partial_result': [{
'frame':
res[key]['frame'],
'seconds':
res[key]['seconds'],
'model':
key,
'img':
res[key]['img']
} for key in res]
})
output = predict_class(frame)
if len(output) > 0:
for box in output:
logger.debug('Frame {}'.format(pos_frame))
logger.debug(box)
if float(box['confidence']) > (
prob_detection / 100) and float(
box['prob'][0]) > (prob_classification /
100):
logger.debug(box['pred'][0])
# Print detected boxes
cv2.rectangle(frame, (box['x1'], box['y1']),
(box['x2'], box['y2']), (255, 0, 0),
6)
cv2.putText(frame, box['label'],
(box['x1'], box['y1'] - 5),
cv2.FONT_HERSHEY_SIMPLEX, 0.5,
(0, 255, 0), 2)
# Convert captured image to JPG
retval, buffer = cv2.imencode('.jpg', frame)
# Convert to base64 encoding and show start of data
jpg_as_text = base64.b64encode(buffer)
base64_string = jpg_as_text.decode('utf-8')
modele = box['pred'][0]
res[modele] = {
'frame': pos_frame,
'seconds': pos_frame / fps,
'model': box['pred'][0],
'img': base64_string
}
else:
break
return {
'current':
total_frames,
'total':
total_frames,
'status':
'Task completed!',
'partial_result': [{
'frame': res[key]['frame'],
'seconds': res[key]['seconds'],
'model': key,
'img': res[key]['img']
} for key in res],
'result':
list(res.keys())
}