def post_process(infer_output, origin_img, image_file):
"""post process"""
print("post process")
print(infer_output[1])
# box_num indicates the number of targets detected in the picture
box_num = infer_output[1][0, 0]
print("box num ", box_num)
box_info = infer_output[0].flatten()
print("\n")
print(box_info[0:6 * box_num].reshape(6, box_num))
scalex = utils.align_up128(origin_img.width) / MODEL_WIDTH
scaley = utils.align_up16(origin_img.height) / MODEL_HEIGHT
output_path = os.path.join("./outputs", os.path.basename(image_file))
origin_image = Image.open(image_file)
draw = ImageDraw.Draw(origin_image)
font = ImageFont.truetype("SourceHanSansCN-Normal.ttf", size=30)
print("images:{}".format(image_file))
# Create a list to save Json results
obj_res = []
# Inference result output
print("======== inference results: =============")
for n in range(int(box_num)):
ind = int(box_info[5 * int(box_num) + n])
label = labels[ind]
score = box_info[4 * int(box_num) + n]
top_left_x = box_info[0 * int(box_num) + n] * scalex
top_left_y = box_info[1 * int(box_num) + n] * scaley
bottom_right_x = box_info[2 * int(box_num) + n] * scalex
bottom_right_y = box_info[3 * int(box_num) + n] * scaley
# Output the target name, category number, coordinate position, and detection rate in turn
print("%s: class %d, box %d %d %d %d, score %f" %
(label, ind, top_left_x, top_left_y, bottom_right_x,
bottom_right_y, score))
# Mark the test results on the picture
draw.line([(top_left_x, top_left_y), (bottom_right_x, top_left_y),
(bottom_right_x, bottom_right_y),
(top_left_x, bottom_right_y), (top_left_x, top_left_y)],
fill=(0, 200, 100),
width=2)
draw.text((top_left_x, top_left_y), label, font=font, fill=255)
# json data
obj = {}
obj['label'] = label
obj['score'] = score
points = {}
points['lx'] = top_left_x
points['ly'] = top_left_y
points['rx'] = bottom_right_x
points['ry'] = bottom_right_y
obj['points'] = points
obj_res.append(obj)
#Save the final test result picture
origin_image.save(output_path)
return obj_res
def jpegd(self, image):
"""
jepg image to yuv image
"""
# Create conversion output image desc
output_desc, out_buffer = self._gen_jpegd_out_pic_desc(image)
ret = acl.media.dvpp_jpeg_decode_async(self._dvpp_channel_desc,
image.data(),
image.size,
output_desc,
self._stream)
if ret != constants.ACL_ERROR_NONE:
log_error("dvpp_jpeg_decode_async failed ret={}".format(ret))
return None
ret = acl.rt.synchronize_stream(self._stream)
if ret != constants.ACL_ERROR_NONE:
log_error("dvpp_jpeg_decode_async failed ret={}".format(ret))
return None
# Return the decoded AclImage instance
stride_width = utils.align_up128(image.width)
stride_height = utils.align_up16(image.height)
stride_size = utils.yuv420sp_size(stride_width, stride_height)
return AclImage(out_buffer, stride_width,
stride_height, stride_size, constants.MEMORY_DVPP)
def post_process_big(infer_output, origin_img, image_file, out_target):
"""post process big"""
print("post process")
print(infer_output[1])
box_num = infer_output[1][0, 0]
print("box num ", box_num)
box_info = infer_output[0].flatten()
print("\n")
print(box_info[0:6 * box_num].reshape(6, box_num))
scalex = utils.align_up128(origin_img.width) / MODEL_WIDTH
scaley = utils.align_up16(origin_img.height) / MODEL_HEIGHT
output_path = os.path.join(out_target, os.path.basename(image_file))
origin_image = Image.open(image_file)
draw = ImageDraw.Draw(origin_image)
font = ImageFont.truetype("../SourceHanSansCN-Normal.ttf", size=30)
print("images:{}".format(image_file))
print("======== inference results: =============")
imagename = get_file_name(image_file)
# Get the number in the name of the cropped picture
x = imagename.split("_")
row_num = (int)(x[0])
y = x[1].split(".")
col_num = (int)(y[0])
obj_res = []
for n in range(int(box_num)):
ind = int(box_info[5 * int(box_num) + n])
label = labels[ind]
score = box_info[4 * int(box_num) + n]
top_left_x = box_info[0 * int(box_num) + n] * scalex
top_left_y = box_info[1 * int(box_num) + n] * scaley
bottom_right_x = box_info[2 * int(box_num) + n] * scalex
bottom_right_y = box_info[3 * int(box_num) + n] * scaley
print("%s: class %d, box %d %d %d %d, score %f" %
(label, ind, top_left_x, top_left_y, bottom_right_x,
bottom_right_y, score))
draw.line([(top_left_x, top_left_y), (bottom_right_x, top_left_y),
(bottom_right_x, bottom_right_y),
(top_left_x, bottom_right_y), (top_left_x, top_left_y)],
fill=(0, 200, 100),
width=2)
draw.text((top_left_x, top_left_y), label, font=font, fill=255)
# Big picture mapping coordinates
big_lx = top_left_x + (col_num - 1) * 832
big_ly = top_left_y + (row_num - 1) * 832
big_rx = bottom_right_x + (col_num - 1) * 832
big_ry = bottom_right_y + (row_num - 1) * 832
#json data
obj = {}
obj['label'] = label
obj['score'] = score
points = {}
points['lx'] = big_lx
points['ly'] = big_ly
points['rx'] = big_rx
points['ry'] = big_ry
obj['points'] = points
obj_res.append(obj)
origin_image.save(output_path)
return obj_res