def classify_image():
image_data = request.form['image_data']
#base64 to cv2
encoded_data = image_data.split(',')[1]
nparr = np.frombuffer(base64.b64decode(encoded_data), np.uint8)
img = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
cv2.imwrite('image.jpg', img)
# enhancing image
im = Image.open('image.jpg')
enhancers = ImageEnhance.Sharpness(im)
enhanced_im = enhancers.enhance(2.75)
enhanced_im.save("sample.jpg")
im = Image.open('sample.jpg')
enhancercon = ImageEnhance.Contrast(im)
enhanced_im = enhancercon.enhance(1.2)
enhanced_im.save("sample.jpg")
im = Image.open('sample.jpg')
enhancerc = ImageEnhance.Color(im)
enhanced_im = enhancerc.enhance(1.1)
enhanced_im.save("sample.jpg")
# enhanced Image file
data = {}
with open('sample.jpg', mode='rb') as file:
imgw = file.read()
data['imgw'] = base64.b64encode(imgw)
response = jsonify(util.classify_image("b," + str(data['imgw'])[2:]))
response.headers.add('Access-Control-Allow-Origin', '*')
return response
def classify_image():
image_data = request.form['image_data']
response = jsonify(util.classify_image(image_data))
response.headers.add('Access-Control-Allow-Origin', '*')
return response
def classify_image():
image_data = request.form['image_data']
back_response = util.classify_image(image_data)
response = jsonify(back_response)
print(back_response)
response.headers.add('Access-control-Allow-Origin', '*')
return response
def classify_image():
image_data = request.form['image_data']
response = jsonify(util.classify_image(image_data))
response.headers.add('Access-Control-Allow-Origin', '*')
response.headers.add('Access-Control-Allow-Headers',
'Content-Type,Authorization')
response.headers.add('Access-Control-Allow-Methods', 'GET,PUT,POST,DELETE')
return response
def classify_image():
image_data = request.form['image_data']
data=[]
url = "https://api.unsplash.com/search/photos"
query={"page":"1", "client_id":"vrB0FKvJ2uIq780UySc3VE8LI8uxKhja3MyxU1MN9MI"}
q = util.classify_image(image_base64_data=image_data)
query["query"]=q
response = requests.get(url,params=query)
for i in range(0,10):
data.append(response.json()["results"][i]["urls"]["raw"])
response = jsonify(data)
response.headers.add('Access-Control-Allow-Origin', '*')
return response
model_name = 'mobilenet_v1_1.0_224_quant.tflite'
repeat = 10
model_dir = download_model_zoo(model_dir, model_name)
tflite_model_file = os.path.join(model_dir, model_name)
tflite_model_buf = open(tflite_model_file, "rb").read()
try:
import tflite
tflite_model = tflite.Model.GetRootAsModel(tflite_model_buf, 0)
except AttributeError:
import tflite.Model
tflite_model = tflite.Model.Model.GetRootAsModel(tflite_model_buf, 0)
interpreter = Interpreter(tflite_model_file, num_threads=get_cpu_count())
interpreter.allocate_tensors()
_, height, width, _ = interpreter.get_input_details()[0]['shape']
image = load_test_image('uint8', height, width)
numpy_time = np.zeros(repeat)
for i in range(0, repeat):
start_time = time.time()
results = classify_image(interpreter, image)
elapsed_ms = (time.time() - start_time) * 1000
numpy_time[i] = elapsed_ms
print("tflite %-20s %-19s (%s)" % (model_name, "%.2f ms" % np.mean(numpy_time),
"%.2f ms" % np.std(numpy_time)))
