def draw_all_detection(im_array, detections, class_names, scale):
"""
visualize all detections in one image
:param im_array: [b=1 c h w] in rgb
:param detections: [ numpy.ndarray([[x1 y1 x2 y2 score]]) for j in classes ]
:param class_names: list of names in imdb
:param scale: visualize the scaled image
:return:
"""
import cv2
import random
color_white = (255, 255, 255)
im = image.transform_inverse(im_array, config.PIXEL_MEANS)
# change to bgr
im = cv2.cvtColor(im, cv2.cv.CV_RGB2BGR)
for j, name in enumerate(class_names):
if name == '__background__':
continue
color = (random.randint(0, 256), random.randint(0, 256),
random.randint(0, 256)) # generate a random color
dets = detections[j]
for det in dets:
bbox = det[:4] * scale
score = det[-1]
bbox = map(int, bbox)
cv2.rectangle(im, (bbox[0], bbox[1]), (bbox[2], bbox[3]),
color=color,
thickness=2)
cv2.putText(im,
'%s %.3f' % (class_names[j], score),
(bbox[0], bbox[1] + 10),
color=color_white,
fontFace=cv2.FONT_HERSHEY_COMPLEX,
fontScale=0.5)
return im
def vis_all_detection(im_array, detections, class_names, scale):
"""
visualize all detections in one image
:param im_array: [b=1 c h w] in rgb
:param detections: [ numpy.ndarray([[x1 y1 x2 y2 score]]) for j in classes ]
:param class_names: list of names in imdb
:param scale: visualize the scaled image
:return:
"""
import matplotlib.pyplot as plt
import random
im = image.transform_inverse(im_array, config.PIXEL_MEANS)
plt.imshow(im)
for j, name in enumerate(class_names):
if name == '__background__':
continue
color = (random.random(), random.random(), random.random()) # generate a random color
dets = detections[j]
for det in dets:
bbox = det[:4] * scale
score = det[-1]
rect = plt.Rectangle((bbox[0], bbox[1]),
bbox[2] - bbox[0],
bbox[3] - bbox[1], fill=False,
edgecolor=color, linewidth=3.5)
plt.gca().add_patch(rect)
plt.gca().text(bbox[0], bbox[1] - 2,
'{:s} {:.3f}'.format(name, score),
bbox=dict(facecolor=color, alpha=0.5), fontsize=12, color='white')
plt.show()
def draw_all_detection(im_array, detections, class_names, scale):
"""
visualize all detections in one image
:param im_array: [b=1 c h w] in rgb
:param detections: [ numpy.ndarray([[x1 y1 x2 y2 score]]) for j in classes ]
:param class_names: list of names in imdb
:param scale: visualize the scaled image
:return:
"""
import cv2
import random
color_white = (255, 255, 255)
im = image.transform_inverse(im_array, config.PIXEL_MEANS)
# change to bgr
im = cv2.cvtColor(im, cv2.cv.CV_RGB2BGR)
for j, name in enumerate(class_names):
if name == '__background__':
continue
color = (random.randint(0, 256), random.randint(0, 256), random.randint(0, 256)) # generate a random color
dets = detections[j]
for det in dets:
bbox = det[:4] * scale
score = det[-1]
bbox = map(int, bbox)
cv2.rectangle(im, (bbox[0], bbox[1]), (bbox[2], bbox[3]), color=color, thickness=2)
cv2.putText(im, '%s %.3f' % (class_names[j], score), (bbox[0], bbox[1] + 10),
color=color_white, fontFace=cv2.FONT_HERSHEY_COMPLEX, fontScale=0.5)
return im
def draw_detection_mask(im_array, boxes_this_image, masks_this_image, scale, filename):
import cv2
import random
class_names = ('__background__', 'person', 'rider', 'car', 'truck', 'bus', 'train', 'mcycle', 'bicycle')
color_white = (255, 255, 255)
im = image.transform_inverse(im_array.asnumpy(), config.PIXEL_MEANS)
# change to bgr
im = cv2.cvtColor(im, cv2.cv.CV_RGB2BGR)
for j, name in enumerate(class_names):
if name == '__background__':
continue
color = (random.randint(0, 256), random.randint(0, 256), random.randint(0, 256)) # generate a random color
dets = boxes_this_image[j]
masks = masks_this_image[j]
for i in range(len(dets)):
bbox = dets[i, :4] * scale
score = dets[i, -1]
bbox = map(int, bbox)
cv2.rectangle(im, (bbox[0], bbox[1]), (bbox[2], bbox[3]), color=color, thickness=2)
cv2.putText(im, '%s %.3f' % (class_names[j], score), (bbox[0], bbox[1] + 10),
color=color_white, fontFace=cv2.FONT_HERSHEY_COMPLEX, fontScale=0.5)
mask = masks[i, :, :]
mask = cv2.resize(mask, (bbox[2] - bbox[0], (bbox[3] - bbox[1])), interpolation=cv2.INTER_LINEAR)
mask[mask > 0.5] = 1
mask[mask <= 0.5] = 0
mask_color = random.randint(0, 255)
c = random.randint(0, 2)
target = im[bbox[1]: bbox[3], bbox[0]: bbox[2], c] + mask_color * mask
target[target >= 255] = 255
im[bbox[1]: bbox[3], bbox[0]: bbox[2], c] = target
print filename
cv2.imwrite(filename, im)
def vis_all_detection(im_array, detections, class_names, scale):
"""
visualize all detections in one image
:param im_array: [b=1 c h w] in rgb
:param detections: [ numpy.ndarray([[x1 y1 x2 y2 score]]) for j in classes ]
:param class_names: list of names in imdb
:param scale: visualize the scaled image
:return:
"""
import matplotlib.pyplot as plt
import random
im = image.transform_inverse(im_array, config.PIXEL_MEANS)
plt.imshow(im)
# for j, name in enumerate(class_names):
# if name == '__background__':
# continue
color = (random.random(), random.random(), random.random()
) # generate a random color
# dets = detections[j]
print(len(detections))
for det in detections:
bbox = det[:4] * scale
#score = det[-1]
rect = plt.Rectangle((bbox[0], bbox[1]),
bbox[2] - bbox[0],
bbox[3] - bbox[1],
fill=False,
edgecolor=color,
linewidth=3.5)
plt.gca().add_patch(rect)
# plt.gca().text(bbox[0], bbox[1] - 2,
# '{:s} {:.3f}'.format(name, score),
# bbox=dict(facecolor=color, alpha=0.5), fontsize=12, color='white')
plt.show()
def draw_detection_mask(im_array, boxes_this_image, masks_this_image, scale, filename):
import cv2
import random
class_names = ('__background__', 'person', 'rider', 'car', 'truck', 'bus', 'train', 'mcycle', 'bicycle')
color_white = (255, 255, 255)
im = image.transform_inverse(im_array.asnumpy(), config.PIXEL_MEANS)
# change to bgr
# im = cv2.cvtColor(im, cv2.cv.CV_RGB2BGR)
im = cv2.cvtColor(im, cv2.COLOR_RGB2BGR)
for j, name in enumerate(class_names):
if name == '__background__':
continue
color = (random.randint(0, 256), random.randint(0, 256), random.randint(0, 256)) # generate a random color
dets = boxes_this_image[j]
masks = masks_this_image[j]
for i in range(len(dets)):
bbox = dets[i, :4] * scale
score = dets[i, -1]
bbox = list(map(int, bbox))
cv2.rectangle(im, (bbox[0], bbox[1]), (bbox[2], bbox[3]), color=color, thickness=2)
cv2.putText(im, '%s %.3f' % (class_names[j], score), (bbox[0], bbox[1] + 10),
color=color_white, fontFace=cv2.FONT_HERSHEY_COMPLEX, fontScale=0.5)
mask = masks[i, :, :]
mask = cv2.resize(mask, (bbox[2] - bbox[0], (bbox[3] - bbox[1])), interpolation=cv2.INTER_LINEAR)
mask[mask > 0.5] = 1
mask[mask <= 0.5] = 0
mask_color = random.randint(0, 255)
c = random.randint(0, 2)
target = im[bbox[1]: bbox[3], bbox[0]: bbox[2], c] + mask_color * mask
target[target >= 255] = 255
im[bbox[1]: bbox[3], bbox[0]: bbox[2], c] = target
print(filename)
cv2.imwrite(filename, im)
def draw_detection(im_array, boxes_this_image, scale, filename):
"""
visualize all detections in one image
:param im_array: [b=1 c h w] in rgb
:param detections: [ numpy.ndarray([[x1 y1 x2 y2 score]]) for j in classes ]
:param class_names: list of names in imdb
:param scale: visualize the scaled image
:return:
"""
import cv2
import random
class_names = ('__background__', 'person', 'rider', 'car', 'truck', 'bus',
'train', 'mcycle', 'bicycle')
color_white = (255, 255, 255)
im = image.transform_inverse(im_array.asnumpy(), config.PIXEL_MEANS)
# change to bgr
im = cv2.cvtColor(im, cv2.COLOR_RGB2BGR)
for j, name in enumerate(class_names):
if name == '__background__':
continue
color = (random.randint(0, 256), random.randint(0, 256),
random.randint(0, 256)) # generate a random color
dets = boxes_this_image[j]
for det in dets:
bbox = det[:4] * scale
score = det[-1]
bbox = map(int, bbox)
cv2.rectangle(im, (bbox[0], bbox[1]), (bbox[2], bbox[3]),
color=color,
thickness=2)
cv2.putText(im,
'%s %.3f' % (class_names[j], score),
(bbox[0], bbox[1] + 10),
color=color_white,
fontFace=cv2.FONT_HERSHEY_COMPLEX,
fontScale=0.5)
print(filename)
cv2.imwrite(filename, im)
def vis_all_detection(im_array,
detections,
class_names,
scale,
head_boxes=None,
joints=None):
"""
visualize all detections in one image
:param im_array: [b=1 c h w] in rgb
:param detections: [ numpy.ndarray([[x1 y1 x2 y2 score]]) for j in classes ]
:param class_names: list of names in imdb
:param scale: visualize the scaled image
:return:
"""
import matplotlib.pyplot as plt
import random
im = image.transform_inverse(im_array, config.PIXEL_MEANS)
plt.imshow(im)
for j, name in enumerate(class_names):
if name == '__background__':
continue
color = (random.random(), random.random(), random.random()
) # generate a random color
dets = detections[j]
for det in dets:
bbox = det[:4] * scale
score = det[-1]
rect = plt.Rectangle((bbox[0], bbox[1]),
bbox[2] - bbox[0],
bbox[3] - bbox[1],
fill=False,
edgecolor=color,
linewidth=3.5)
plt.gca().add_patch(rect)
plt.gca().text(bbox[0],
bbox[1] - 2,
'{:s} {:.3f}'.format(name, score),
bbox=dict(facecolor=color, alpha=0.5),
fontsize=12,
color='white')
if head_boxes is not None:
color = (random.random(), random.random(), random.random()
) # generate a random color
for det in head_boxes:
bbox = det[:4] * scale
rect = plt.Rectangle((bbox[0], bbox[1]),
bbox[2] - bbox[0],
bbox[3] - bbox[1],
fill=False,
edgecolor=color,
linewidth=3.5)
plt.gca().add_patch(rect)
if joints is not None:
color = (random.random(), random.random(), random.random()
) # generate a random color
for joint in joints:
joint *= scale
for (cx, cy) in zip(joint[0::2], joint[1::2]):
ptr = plt.Circle((cx, cy), 5.0, color=color)
plt.gca().add_artist(ptr)
plt.show()
