Sn0wl3r0ker
commented
4 years ago add this to the utils/visualization_utils.py
def return_coordinates( image, boxes, classes, scores, category_index, instance_masks=None, instance_boundaries=None, keypoints=None, use_normalized_coordinates=False, max_boxes_to_draw=20, min_score_thresh=.5, agnostic_mode=False, line_thickness=4, groundtruth_box_visualization_color='black', skip_scores=False, skip_labels=False): # Create a display string (and color) for every box location, group any boxes # that correspond to the same location. box_to_display_str_map = collections.defaultdict(list) box_to_color_map = collections.defaultdict(str) box_to_instance_masks_map = {} box_to_instance_boundaries_map = {} box_to_score_map = {} box_to_keypoints_map = collections.defaultdict(list) if not max_boxes_to_draw: max_boxes_to_draw = boxes.shape[0] for i in range(min(max_boxes_to_draw, boxes.shape[0])): if scores is None or scores[i] > min_score_thresh: box = tuple(boxes[i].tolist()) if instance_masks is not None: box_to_instance_masks_map[box] = instance_masks[i] if instance_boundaries is not None: box_to_instance_boundaries_map[box] = instance_boundaries[i] if keypoints is not None: box_to_keypoints_map[box].extend(keypoints[i]) if scores is None: box_to_color_map[box] = groundtruth_box_visualization_color else: display_str = '' if not skip_labels: if not agnostic_mode: if classes[i] in category_index.keys(): class_name = category_index[classes[i]]['name'] else: class_name = 'N/A' display_str = str(class_name) if not skip_scores: if not display_str: display_str = '{}%'.format(int(100*scores[i])) else: display_str = '{}: {}%'.format(display_str, int(100*scores[i])) box_to_display_str_map[box].append(display_str) box_to_score_map[box] = scores[i] if agnostic_mode: box_to_color_map[box] = 'DarkOrange' else: box_to_color_map[box] = STANDARD_COLORS[ classes[i] % len(STANDARD_COLORS)] # Draw all boxes onto image. coordinates_list = [] counter_for = 0 for box, color in box_to_color_map.items(): ymin, xmin, ymax, xmax = box height, width, channels = image.shape ymin = int(ymin*height) ymax = int(ymax*height) xmin = int(xmin*width) xmax = int(xmax*width) coordinates_list.append([ymin, ymax, xmin, xmax, (box_to_score_map[box]*100)]) counter_for = counter_for + 1 return coordinates_listadd this to Object_detection_dir.py
coordinates = vis_util.return_coordinates( image, np.squeeze(boxes), np.squeeze(classes).astype(np.int32), np.squeeze(scores), category_index, use_normalized_coordinates=True, line_thickness=8, min_score_thresh=0.80)as well as this:
textfile = open("json/"+filename_string+".json", "a") textfile.write(json.dumps(coordinates)) textfile.write("\n")I think this should be all. Hi! This is not a issue.I add this simple loop to make the code detect all .JPG file the the testimg folder and export the .json file, img with boxes in json, json/testimg folder. Hope this can help someone who wants it.... P.S. i'm still a noob, so hope u can give me some advise
1.import some models:
import glob
import re2.markdown default IMAGE PATH: "# IMAGE_NAME =" "# PATH_TO_IMAGE = os.path.join(CWD_PATH,IMAGE_NAME)"
3.And heres the change:
for filename in sorted(glob.glob("testimg/"+ "*.JPG")):
print("\n")
print("Start parsing "+filename+"...")
image = cv2.imread(filename)
image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
image_expanded = np.expand_dims(image_rgb, axis=0) filenameJ = re.sub(r".*?\/", "", filename)
open("json/"+filenameJ+".json", "a").write(json.dumps(coordinates)+"\n"
for coordinate in coordinates:
(y1, y2, x1, x2, acc, classification) = coordinate
height = y2-y1
width = x2-x1
crop = image[y1:y1+height, x1:x1+width]
cv2.imwrite("json/"+filename, image)
print(coordinate)
jix1710
psi43
Raman1121
Aakanksha3010
vinilreddy36
unrivalle
ghost
wael-mahdi
EDIT: Nevermind, got it to work!
Hey, first off, great tutorial, thank you so much.
I got it to run on ubuntu 16.04 as well with ease but I have a problem. I'm running on a CLI Ubuntu server, so instead of using an image as output, I'd just like to have the coordinates of the boxes.
I looked into the Object_detection_image.py and found where the boxes are being drawn, but it uses a function named visualize_boxes_and_labels_on_image_array to draw them. If I try to ouput the np.squeeze(boxes), it returns this:
Is there a way to just get the coordinates from that?
Thank you for your time!
EDIT: Okay, I added a new function to the visualization_utils.py that returns the "ymin, ymax, xmin, xmax" variables, used in other functions of that file to draw the boxes. The problem is, they look like this:
[[0.5897822976112366, 0.8703674674034119, 0.35585764050483704, 0.5124077796936035], [0.6508234739303589, 0.8575793504714966, 0.13419045507907867, 0.2114586979150772]]I was expecting coordinates. These seem like percentages.EDIT: Okay, I got it to work.