def rnet_boxes(img,
rnet,
bounding_boxes,
thresholds=THRESHOLDS,
nms_thresholds=NMS_THRESHOLDS,
show_boxes=True):
rnet.eval()
img_boxes = get_image_boxes(bounding_boxes, img, size=24)
img_boxes = torch.FloatTensor(img_boxes)
img_boxes = img_boxes.to(
torch.device('cuda' if torch.cuda.is_available() else 'cpu'))
output = rnet(img_boxes)
probs = output[0].data.cpu().numpy() # shape [n_boxes, 1]
offsets = output[1].data.cpu().numpy() # shape [n_boxes, 4]
keep = np.where(probs[:, 0] > thresholds[1])[0]
bounding_boxes = bounding_boxes[keep]
bounding_boxes[:, 4] = probs[keep, 0].reshape((-1, ))
offsets = offsets[keep]
keep = nms(bounding_boxes, nms_thresholds[1])
bounding_boxes = bounding_boxes[keep]
bounding_boxes = calibrate_box(bounding_boxes, offsets[keep])
bounding_boxes = convert_to_square(bounding_boxes)
bounding_boxes[:, 0:4] = np.round(bounding_boxes[:, 0:4])
if show_boxes: show_bboxes(img, bounding_boxes, []).show()
return bounding_boxes
def onet_boxes(img,
onet,
bounding_boxes,
thresholds=THRESHOLDS,
nms_thresholds=NMS_THRESHOLDS,
show_boxes=True):
onet.eval()
img_boxes = get_image_boxes(bounding_boxes, img, size=48)
if len(img_boxes) == 0:
return [], []
img_boxes = torch.FloatTensor(img_boxes)
img_boxes = img_boxes.to(
torch.device('cuda' if torch.cuda.is_available() else 'cpu'))
output = onet(img_boxes)
probs = output[0].data.cpu().numpy() # shape [n_boxes, 1]
offsets = output[1].data.cpu().numpy() # shape [n_boxes, 4]
landmarks = output[2].data.cpu().numpy() # shape [n_boxes, 10]
keep = np.where(probs[:, 0] > thresholds[2])[0]
bounding_boxes = bounding_boxes[keep]
# 用更大模型的置信度对原置信度进行更新
bounding_boxes[:, 4] = probs[keep, 0].reshape((-1, ))
offsets = offsets[keep]
landmarks = landmarks[keep]
# compute landmark points
width = bounding_boxes[:, 2] - bounding_boxes[:, 0] + 1.0
height = bounding_boxes[:, 3] - bounding_boxes[:, 1] + 1.0
xmin, ymin = bounding_boxes[:, 0], bounding_boxes[:, 1]
# print('width:{},\nheight:{},\nxmin:{},\nymin:{}\n'.format(width, height, xmin, ymin))
# landmark[,前5个为x，后5个为y]
# 在左上角坐标的基础上，通过 w，h 确定脸各关键点的坐标。
landmarks_pixel = np.zeros(landmarks.shape)
landmarks_pixel[:, 0:5] = (
np.expand_dims(xmin, 1) +
np.expand_dims(width, 1) * landmarks[:, 0::2]).copy()
landmarks_pixel[:, 5:10] = (
np.expand_dims(ymin, 1) +
np.expand_dims(height, 1) * landmarks[:, 1::2]).copy()
# for i in landmarks:print(i)
bounding_boxes = calibrate_box(bounding_boxes, offsets)
keep = nms(bounding_boxes, nms_thresholds[2], mode='min')
bounding_boxes = bounding_boxes[keep]
landmarks_pixel = landmarks_pixel[keep]
if show_boxes: show_bboxes(img, bounding_boxes, landmarks_pixel).show()
return bounding_boxes, landmarks_pixel
os.path.join('..', 'open_images_', 'validation-images-with-rotation.csv'))
meta.set_index('ImageID', inplace=True)
print('data loaded')
for index, row in meta.iterrows():
if index not in id2url:
continue
#if not np.isnan(row.Rotation):
if row.Rotation != 270:
continue
'''
image_url = id2url[index]
try:
image = get_image(image_url, rotate=id2rot[index])
except:
print('error downloading: ' + image_url)
continue
'''
image = get_image_from_s3(index)
result = get_image_boxes(objects, index)
print(row.Rotation)
print(result)
image_with_boxes = draw_boxes(image, result["detection_boxes"],
result["detection_class_names"])
display_image(image_with_boxes)