def predictResNet50():
if request.method == 'POST':
file_path = get_file_path_and_save(request)
img = image.load_img(file_path, target_size=(224, 224))
# Preprocessing the image
x = image.img_to_array(img)
# x = np.true_divide(x, 255)
x = np.expand_dims(x, axis=0)
# Be careful how your trained model deals with the input
# otherwise, it won't make correct prediction!
x = preprocess_input_resNet50(x, mode='caffe')
# Make prediction
preds = modelResNet50.predict(x)
# Process your result for human
# pred_class = preds.argmax(axis=-1) # Simple argmax
pred_class = decode_predictions_resNet50(preds,
top=3) # ImageNet Decode
result1 = pred_class[0][0]
f1 = "{0:.2f}".format(round(result1[2] * 100, 2))
a = result1[1] + " " + str(f1)
# print(a)
result2 = pred_class[0][1]
f2 = "{0:.2f}".format(round(result2[2] * 100, 2))
b = result2[1] + " " + str(f2)
# print(b)
result3 = pred_class[0][2]
f3 = "{0:.2f}".format(round(result3[2] * 100, 2))
c = result3[1] + " " + str(f3)
# print(c)
result = a + "\n" + b + "\n" + c
#print(result)
return result
return None
def predictResNet50():
if request.method == 'POST':
file_path = get_file_path_and_save(request)
img = image.load_img(file_path, target_size=(224, 224))
# Preprocessing the image
x = image.img_to_array(img)
# x = np.true_divide(x, 255)
x = np.expand_dims(x, axis=0)
# Be careful how your trained model deals with the input
# otherwise, it won't make correct prediction!
x = preprocess_input_resNet50(x, mode='caffe')
# Make prediction
preds = modelResNet50.predict(x)
# Process your result for human
# pred_class = preds.argmax(axis=-1) # Simple argmax
pred_class = decode_predictions_resNet50(preds,
top=1) # ImageNet Decode
result = str(pred_class[0][0][1]) # Convert to string
return result
return None
from __future__ import division, print_function