def crop_and_paste_get_roi(self, image, width, height,
crop_and_paste_width, crop_and_paste_height):
"""
:image: input image
:width: input image width
:height: input image height
:crop_and_paste_width: crop_and_paste_width
:crop_and_paste_height: crop_and_paste_height
:return: return AclImage
"""
print('[Dvpp] vpc crop and paste stage:')
input_desc = self._gen_input_pic_desc(image)
stride_width = utils.align_up16(crop_and_paste_width)
stride_height = utils.align_up2(crop_and_paste_height)
out_buffer_size = utils.yuv420sp_size(stride_width, stride_height)
out_buffer, ret = acl.media.dvpp_malloc(out_buffer_size)
output_desc = \
self._gen_output_pic_desc(crop_and_paste_width, crop_and_paste_height, out_buffer, out_buffer_size)
self._crop_config = acl.media.dvpp_create_roi_config(
0, (width >> 1 << 1) - 1, 0, (height >> 1 << 1) - 1)
self._paste_config = acl.media.dvpp_create_roi_config(
0, crop_and_paste_width - 1, 0, crop_and_paste_height - 1)
ret = acl.media.dvpp_vpc_crop_and_paste_async(self._dvpp_channel_desc,
input_desc, output_desc,
self._crop_config,
self._paste_config,
self._stream)
utils.check_ret("acl.media.dvpp_vpc_crop_and_paste_async", ret)
ret = acl.rt.synchronize_stream(self._stream)
utils.check_ret("acl.rt.synchronize_stream", ret)
print('[Dvpp] vpc crop and paste stage success')
stride_width = utils.align_up16(crop_and_paste_width)
stride_height = utils.align_up2(crop_and_paste_height)
return AclImage(out_buffer, stride_width, stride_height,
out_buffer_size, constants.MEMORY_DVPP)
def crop_and_paste(self, image, width, height, crop_and_paste_width,
crop_and_paste_height):
"""
crop_and_paste
"""
print('[Dvpp] vpc crop and paste stage:')
input_desc = self._gen_input_pic_desc(image)
stride_width = utils.align_up16(crop_and_paste_width)
stride_height = utils.align_up2(crop_and_paste_height)
out_buffer_size = utils.yuv420sp_size(stride_width, stride_height)
out_buffer, ret = acl.media.dvpp_malloc(out_buffer_size)
output_desc = self._gen_output_pic_desc(crop_and_paste_width,
crop_and_paste_height,
out_buffer, out_buffer_size)
self._crop_config = acl.media.dvpp_create_roi_config(
0, (width >> 1 << 1) - 1, 0, (height >> 1 << 1) - 1)
# set crop area:
rx = float(width) / float(crop_and_paste_width)
ry = float(height) / float(crop_and_paste_height)
if rx > ry:
dx = 0
r = rx
dy = int((crop_and_paste_height - height / r) / 2)
else:
dy = 0
r = ry
dx = int((crop_and_paste_width - width / r) / 2)
pasteRightOffset = int(crop_and_paste_width - 2 * dx)
pasteBottomOffset = int(crop_and_paste_height - 2 * dy)
if (pasteRightOffset % 2) == 0:
pasteRightOffset = pasteRightOffset - 1
if (pasteBottomOffset % 2) == 0:
pasteBottomOffset = pasteBottomOffset - 1
self._paste_config = acl.media.dvpp_create_roi_config(
0, pasteRightOffset, 0, pasteBottomOffset)
ret = acl.media.dvpp_vpc_crop_and_paste_async(self._dvpp_channel_desc,
input_desc, output_desc,
self._crop_config,
self._paste_config,
self._stream)
utils.check_ret("acl.media.dvpp_vpc_crop_and_paste_async", ret)
ret = acl.rt.synchronize_stream(self._stream)
utils.check_ret("acl.rt.synchronize_stream", ret)
print('[Dvpp] vpc crop and paste stage success')
stride_width = utils.align_up16(crop_and_paste_width)
stride_height = utils.align_up2(crop_and_paste_height)
return AclImage(out_buffer, stride_width, stride_height,
out_buffer_size, constants.MEMORY_DVPP)
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 resize(self, image, resize_width, resize_height):
"""
Scale yuvsp420 picture to specified size
"""
# Generate input picture desc
input_desc = self._gen_input_pic_desc(image)
# Calculate the image size after scaling
stride_width = utils.align_up16(resize_width)
stride_height = utils.align_up2(resize_height)
output_size = utils.yuv420sp_size(stride_width, stride_height)
# Request memory for the zoomed picture
out_buffer, ret = acl.media.dvpp_malloc(output_size)
if ret != constants.ACL_ERROR_NONE:
log_error("Dvpp malloc failed, error: ", ret)
return None
# Create output image
output_desc = self._gen_output_pic_desc(resize_width, resize_height,
out_buffer, output_size)
if output_desc is None:
log_error("Gen resize output desc failed")
return None
# Call dvpp asynchronous zoom interface to zoom pictures
ret = acl.media.dvpp_vpc_resize_async(self._dvpp_channel_desc,
input_desc,
output_desc,
self._resize_config,
self._stream)
if ret != constants.ACL_ERROR_NONE:
log_error("Vpc resize async failed, error: ", ret)
return None
# Wait for the zoom operation to complete
ret = acl.rt.synchronize_stream(self._stream)
if ret != constants.ACL_ERROR_NONE:
log_error("Resize synchronize stream failed, error: ", ret)
return None
# Release the resources requested for scaling
acl.media.dvpp_destroy_pic_desc(input_desc)
acl.media.dvpp_destroy_pic_desc(output_desc)
return AclImage(out_buffer, stride_width,
stride_height, output_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