def predict(self, frame):
#frame = cv2.resize(frame, (224, 224))
frame = image_utils.img_to_array(frame)
frame = np.expand_dims(frame, axis=0)
frame = preprocess_input(frame)
preds = self.model.predict(frame)
return decode_predictions_custom(preds)[0][0]
def predict(self, frame):
image = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB).astype(np.float32)
#image = image.transpose((2, 0, 1))
image = image.reshape((1, ) + image.shape)
image = preprocess_input(image)
preds = self.model.predict(image)
return decode_predictions_custom(preds)[0][0]
def predict(self, frame):
imag = image.img_to_array(frame)
imag = cv2.resize(imag,(224,224))
imag = np.expand_dims(imag,axis=0)
imag = preprocess_input(imag)
imag = imag/255
preds = self.model.predict(imag)
return decode_predictions_custom(preds)[0]
def model_prediction(test_image_path):
test_image = image_preprocess(test_image_path)
y_prob = rbc_model.predict(test_image)
predictions = decode_predictions_custom(y_prob)
return predictions
while frame_number < video_length:
cap.set(1, frame_number)
ret, frame = cap.read()
cv2.resize(frame, (224, 224))
# Load the image using Keras helper ultility
print("[INFO] loading and preprocessing image...")
image = cv2.resize(frame, (224, 224))
image = image_utils.img_to_array(image)
# Convert (3, 224, 224) to (1, 3, 224, 224)
# Here "1" is the number of images passed to network
# We need it for passing batch containing serveral images in real project
image = np.expand_dims(image, axis=0)
image = preprocess_input(image)
# Classify the image
print("[INFO] classifying image...")
preds = model.predict(image)
(inID, label, prob) = decode_predictions_custom(preds)[0][0]
# Display the predictions
print("RBC ID: {}, Label: {}, Prob: {}".format(inID, label, prob))
cv2.putText(frame, "Label: {}, Prob: {}".format(label, prob), (10, 30),
cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 255, 0), 2)
cv2.imshow("Classification", frame)
cv2.waitKey(0)
frame_number += 1
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cv2.destroyAllWindows()
sys.exit()
