def apply_gradcam(img_path):
original_img = cv2.imread(img_path)
original_img = cv2.resize(original_img, (320, 240))
image = preprocess_img(img_path)
preds = model_predict(image)
i = np.argmax(preds[0])
# initialize our gradient class activation map and build the heatmap
cam = GradCAM(TRAINED_MODEL, i)
heatmap = cam.compute_heatmap(image)
# resize the resulting heatmap to the original input image dimensions
# and then overlay heatmap on top of the image
heatmap = cv2.resize(heatmap,
(original_img.shape[1], original_img.shape[0]))
heatmap_legend, heatmap, output = cam.overlay_heatmap(heatmap,
original_img,
alpha=0.2)
white_strip = 255 * np.ones((255, 1, 3), np.uint8)
white_strip = cv2.resize(white_strip, (original_img.shape[1], 20))
output = np.vstack([heatmap_legend, white_strip, heatmap, output])
return output
# use the network to make predictions on the input imag and find
# the class label index with the largest corresponding probability
preds = model.predict(image)
i = np.argmax(preds[0])
# decode the ImageNet predictions to obtain the human-readable label
decoded = imagenet_utils.decode_predictions(preds)
(imagenetID, label, prob) = decoded[0][0]
label = "{}: {:.2f}%".format(label, prob * 100)
print("[INFO] {}".format(label))
# initialize our gradient class activation map and build the heatmap
cam = GradCAM(model, i)
heatmap = cam.compute_heatmap(image)
# resize the resulting heatmap to the original input image dimensions
# and then overlay heatmap on top of the image
heatmap = cv2.resize(heatmap, (orig.shape[1], orig.shape[0]))
(heatmap, output) = cam.overlay_heatmap(heatmap, orig, alpha=0.5)
# draw the predicted label on the output image
cv2.rectangle(output, (0, 0), (340, 40), (0, 0, 0), -1)
cv2.putText(output, label, (10, 25), cv2.FONT_HERSHEY_SIMPLEX, 0.8,
(255, 255, 255), 2)
# display the original image and resulting heatmap and output image
# to our screen
output = np.vstack([orig, heatmap, output])
output = imutils.resize(output, height=700)
cv2.imshow("Output", output)
cv2.waitKey(0)
def heatmap(self):
labels = {'0': 0, '1': 1}
class_labels = ["0 - No Hemmorhage", "1 - Hemmorhage"]
filename = QFileDialog.getOpenFileName()
name = filename[0]
from tensorflow.keras.preprocessing import image
new_model = load_model("trainn_5.h5")
keyboard = np.zeros((600, 1000, 3), np.uint8)
image_path = name
path = name
test_img_load = load_img(image_path, target_size=(128, 128, 3))
test_img = image.img_to_array(test_img_load)
test_img = np.expand_dims(test_img, axis=0)
test_img /= 255
label_map_inv = {v: k for k, v in labels.items()}
result = new_model.predict(test_img)
prediction = result.argmax(axis=1)
i = label_map_inv[int(prediction)]
label = class_labels[(int(i))]
image = load_img(path, target_size=(128, 128))
image = img_to_array(image)
image = np.expand_dims(image, axis=0)
image = imagenet_utils.preprocess_input(image)
orig = cv2.imread(path)
resized = cv2.resize(orig, (128, 128))
cam = GradCAM(new_model, int(i))
heatmap = cam.compute_heatmap(test_img)
heatmap = cv2.resize(heatmap, (orig.shape[1], orig.shape[0]))
(heatmap, output) = cam.overlay_heatmap(heatmap, orig, alpha=0.3)
#cv2.rectangle(output, (0, 0), (340, 40), (0, 0, 0), -1)
#cv2.putText(output, "re", (10, 25), cv2.FONT_HERSHEY_SIMPLEX,
#0.8, (255, 255, 255), 2)
output = np.hstack([orig, output])
keyboard = cv2.resize(keyboard, (output.shape[1], 100))
key = np.vstack([keyboard, output])
key = imutils.resize(key, height=500)
if label == "0 - No Hemmorhage":
color = (0, 255, 0)
else:
color = (0, 0, 255)
cv2.putText(key, label, ((int(((key.shape[1]) / 2)) - 180), 40), 1, 2,
color, 2)
cv2.imshow("Output", key)
cv2.waitKey(0)