=======
print("height:", height)
print("widht:", width)
cv2.imshow("before", image)
cv2.waitKey(0)
>>>>>>> 536f2b4cf039aaa66c898f02c27d7212ec378360
if height > width:
r = 64 / height
small = cv2.resize(image, (int(width * r) , 64))
else:
r = 64 / width
small = cv2.resize(image, (64, int(height * r)))
if image is None:
print("image is null")
cv2.imshow("after", small)
cv2.waitKey(0)
#image = skimage.io.imread(os.path.join(TEST_PIC_DIR, "gray.jpg"))
#memoryUse = py.get_memory_info()[0]/2.**30
#print("Memory use:", memoryUse)
# Run detection
start = datetime.now()
result = model.detect([small], verbose=1)
print("Time taken for detection: {}".format(datetime.now() - start))
r = result[0]
visualize.display_instances(small, r['rois'], r['masks'], r['class_ids'],
class_names, r['scores'])
# Test on a random image
image_id = random.choice(dataset_val.image_ids)
original_image, image_meta, gt_class_id, gt_bbox, gt_mask =\
modellib.load_image_gt(dataset_val, config,
image_id, use_mini_mask=False)
log("original_image", original_image)
log("image_meta", image_meta)
log("gt_class_id", gt_class_id)
log("gt_bbox", gt_bbox)
log("gt_mask", gt_mask)
visualize.display_instances(original_image,
gt_bbox,
gt_mask,
gt_class_id,
dataset_train.class_names,
figsize=(8, 8))
results = model.detect([original_image], verbose=1)
r = results[0]
visualize.display_instances(original_image,
r['rois'],
r['masks'],
r['class_ids'],
dataset_val.class_names,
r['scores'],
ax=get_ax())
# Compute VOC-Style mAP @ IoU=0.5
def detect_and_color_splash(model, image_path=None, video_path=None):
assert image_path or video_path
class_names = ['BG', 'Pothole']
_uid = str(uuid.uuid4())[:8]
# Image or video?
if image_path:
# Run model detection and generate the color splash effect
print("Running on {}".format(args.image))
# Read image
image = skimage.io.imread(args.image)
# Detect objects
r = model.detect([image], verbose=1)[0]
# Mask and Box image, return as byte stream
file_path = visualize.display_instances(image,
r['rois'],
r['masks'],
r['class_ids'],
class_names,
r['scores'],
colors=generate_color(
r['class_ids']),
uid=_uid)
# Save output
shutil.copy2(file_path, ROOT_DIR)
temp_folder_cleanup(_uid)
# file_name = "splash_{:%Y%m%dT%H%M%S}.jpg".format(datetime.datetime.now())
# plt.imsave(file_name, plt.imread(img_buff))
elif video_path:
import cv2
# Video capture
vcapture = cv2.VideoCapture(video_path)
width = int(vcapture.get(cv2.CAP_PROP_FRAME_WIDTH))
height = int(vcapture.get(cv2.CAP_PROP_FRAME_HEIGHT))
fps = vcapture.get(cv2.CAP_PROP_FPS)
# Define codec and create video writer
uid = uuid.uuid4()
file_path = "{}_{:%Y%m%dT%H%M%S}.avi".format(_uid,
datetime.datetime.now())
vwriter = cv2.VideoWriter(file_path, cv2.VideoWriter_fourcc(*'MJPG'),
fps, (width, height))
count = 0
success = True
while success:
print("frame: ", count)
# Read next image
success, image = vcapture.read()
if success:
# OpenCV returns images as BGR, convert to RGB
image = image[..., ::-1]
# Detect objects
r = model.detect([image], verbose=0)[0]
# Color splash
splash = visualize.display_instances(image,
r['rois'],
r['masks'],
r['class_ids'],
class_names,
r['scores'],
colors=generate_color(
r['class_ids']),
is_video=True,
uid=_uid)
splash = cv2.imread(splash)
splash = cv2.resize(splash, (width, height))
vwriter.write(splash)
count += 1
vwriter.release()
temp_folder_cleanup(_uid)
print("Saved to ", file_path)
