def pre_process(image):
height, width = image.shape[0:2]
inp_height, inp_width = 512, 512
c = np.array([height / 2., width / 2.], dtype=np.float32)
s = max(height, width) * 1.0
trans_input = get_affine_transform(c, s, 0, [inp_width, inp_height])
inp_image = cv2.warpAffine(image,
trans_input, (inp_width, inp_height),
flags=cv2.INTER_LINEAR)
mean = np.array(
[0.5194416012442385, 0.5378052387430711, 0.533462090585746],
dtype=np.float32).reshape(1, 1, 3)
std = np.array(
[0.3001546018824507, 0.28620901391179554, 0.3014112676161966],
dtype=np.float32).reshape(1, 1, 3)
inp_image = ((inp_image / 255. - mean) / std).astype(np.float32)
images = inp_image.transpose(2, 0, 1).reshape(
1, 3, inp_height, inp_width) # 三维reshape到4维，（1，3，512，512）
images = torch.from_numpy(images)
meta = {
'c': c,
's': s,
'out_height': inp_height // 4,
'out_width': inp_width // 4
}
return images, meta
def pre_process(image, image_size=224):
height, width = image.shape[0:2]
inp_height, inp_width = image_size, image_size
c = np.array([width / 2.0, height / 2.0], dtype=np.float32)
s = max(height, width) * 1.0
trans_input = get_affine_transform(c, s, 0, [inp_width, inp_height])
inp_image = cv2.warpAffine(image,
trans_input, (inp_width, inp_height),
flags=cv2.INTER_LINEAR)
# mean = np.array(
# [0.5194416012442385, 0.5378052387430711, 0.533462090585746], dtype=np.float32
# ).reshape(1, 1, 3)
# std = np.array(
# [0.3001546018824507, 0.28620901391179554, 0.3014112676161966], dtype=np.float32
# ).reshape(1, 1, 3)
mean = np.array([0.4803, 0.4641, 0.4476],
dtype=np.float32).reshape(1, 1, 3)
std = np.array([0.1878, 0.1881, 0.1959], dtype=np.float32).reshape(1, 1, 3)
inp_image = ((inp_image / 255.0 - mean) / std).astype(np.float32)
# inp_image = (inp_image / 255.0).astype(np.float32)
images = inp_image.transpose(2, 0, 1).reshape(
1, 3, inp_height, inp_width) # 三维reshape到4维，（1，3，512，512）
# print(inp_image)
images = torch.from_numpy(images)
meta = {
"c": c,
"s": s,
"out_height": inp_height // 4,
"out_width": inp_width // 4
}
return images, meta
def transform_preds(coords, center, scale, output_size):
target_coords = np.zeros(coords.shape)
trans = get_affine_transform(center, scale, 0, output_size, inv=1)
for p in range(coords.shape[0]):
target_coords[p, 0:2] = affine_transform(coords[p, 0:2], trans)
return target_coords