diff --git a/official/cv/deeplabv3/infer/Dockerfile b/official/cv/deeplabv3/infer/Dockerfile
index 487c5864ffbdc30aa951e5226a32114056e1fe11..b0f31f18f55f18e79e93a9bbafdc18e29ad9553b 100644
--- a/official/cv/deeplabv3/infer/Dockerfile
+++ b/official/cv/deeplabv3/infer/Dockerfile
@@ -1,5 +1,6 @@
ARG FROM_IMAGE_NAME
FROM ${FROM_IMAGE_NAME}
+USER root
COPY requirements.txt .
RUN pip3 install -r requirements.txt
diff --git a/official/cv/deeplabv3/infer/convert/convert_om.sh b/official/cv/deeplabv3/infer/convert/convert_om.sh
index 39cd519422de53f0d5174f7dc49eab9d834c333a..0ec6c789ca077b518e9fd7cded606ca24b28f14c 100644
--- a/official/cv/deeplabv3/infer/convert/convert_om.sh
+++ b/official/cv/deeplabv3/infer/convert/convert_om.sh
@@ -34,5 +34,6 @@ atc --framework=1 \
--model=$model_path \
--output=$output_model_name \
--fusion_switch_file=fusion_switch.cfg \
+ --precision_mode=allow_fp32_to_fp16 \
--op_select_implmode=high_precision \
--soc_version=Ascend310
diff --git a/official/cv/deeplabv3/infer/data/config/deeplabv3.pipeline b/official/cv/deeplabv3/infer/data/config/deeplabv3.pipeline
index af4c94d6808ecc4a81b9e2b033f28a7caf18a2f5..84685018e855a90333eaeaaf89adb7cb572ecb18 100644
--- a/official/cv/deeplabv3/infer/data/config/deeplabv3.pipeline
+++ b/official/cv/deeplabv3/infer/data/config/deeplabv3.pipeline
@@ -3,52 +3,12 @@
"stream_config": {
"deviceId": "0"
},
- "mxpi_imagedecoder0": {
- "props": {
- "handleMethod": "opencv"
- },
- "factory": "mxpi_imagedecoder",
- "next": "mxpi_imageresize0"
- },
- "mxpi_imageresize0": {
- "props": {
- "handleMethod": "opencv",
- "resizeType": "Resizer_KeepAspectRatio_Long",
- "scaleValue": "513"
- },
- "factory": "mxpi_imageresize",
- "next": "opencv_normalize0"
- },
- "opencv_normalize0": {
- "props": {
- "alpha": "123.675, 116.28, 103.53",
- "beta": "58.395, 57.120, 57.375",
- "dataType": "FLOAT32"
- },
- "factory": "mxpi_imagenormalize",
- "next": "mxpi_imageresize1"
- },
- "mxpi_imageresize1": {
- "props": {
- "handleMethod": "opencv",
- "resizeType": "Resizer_OnlyPadding",
- "scaleValue": "513",
- "paddingType": "Padding_RightDown",
- "paddingHeight": "513",
- "paddingWidth": "513",
- "paddingColorB": "0",
- "paddingColorG": "0",
- "paddingColorR": "0"
- },
- "factory": "mxpi_imageresize",
- "next": "mxpi_tensorinfer0"
- },
"mxpi_tensorinfer0": {
"props": {
- "dataSource": "mxpi_imageresize1",
+ "dataSource": "appsrc0",
"modelPath": "../data/model/deeplabv3.om"
},
- "factory": "mxpi_modelinfer",
+ "factory": "mxpi_tensorinfer",
"next": "mxpi_semanticsegpostprocessor0"
},
"mxpi_semanticsegpostprocessor0": {
@@ -73,7 +33,7 @@
"blocksize": "409600"
},
"factory": "appsrc",
- "next": "mxpi_imagedecoder0"
+ "next": "mxpi_tensorinfer0"
},
"appsink0": {
"props": {
diff --git a/official/cv/deeplabv3/infer/sdk/main.py b/official/cv/deeplabv3/infer/sdk/main.py
index 31c434af2291000e453504003d5fb2dfd86d00f2..b55446f0a8c2e432bbd9865dbed0d8333d7f6135 100644
--- a/official/cv/deeplabv3/infer/sdk/main.py
+++ b/official/cv/deeplabv3/infer/sdk/main.py
@@ -20,8 +20,9 @@ import json
import os
import cv2
import numpy as np
-from StreamManagerApi import MxDataInput
from StreamManagerApi import StreamManagerApi
+from StreamManagerApi import InProtobufVector, MxProtobufIn, MxDataInput
+import MxpiDataType_pb2 as MxpiDataType
from get_dataset_colormap import label_to_color_image
PIPELINE_PATH = "../data/config/deeplabv3.pipeline"
@@ -58,16 +59,35 @@ def _init_stream(pipeline_path):
return stream_manager_api
-def _do_infer(stream_manager_api, data_input):
+def _do_infer(stream_manager_api, data_input, origin_img):
stream_name = b'segmentation'
- unique_id = stream_manager_api.SendDataWithUniqueId(
- stream_name, 0, data_input)
+ vision_list = MxpiDataType.MxpiVisionList()
+ vision_vec = vision_list.visionVec.add()
+ vision_vec.visionInfo.format = 0
+ vision_vec.visionInfo.width = origin_img.shape[1]
+ vision_vec.visionInfo.height = origin_img.shape[0]
+ vision_vec.visionInfo.widthAligned = origin_img.shape[1]
+ vision_vec.visionInfo.heightAligned = origin_img.shape[0]
+
+ vision_vec.visionData.memType = 0
+
+ vision_vec.visionData.dataStr = data_input.tobytes()
+ vision_vec.visionData.dataSize = len(data_input)
+
+ protobuf = MxProtobufIn()
+ protobuf.key = b"appsrc0"
+ protobuf.type = b'MxTools.MxpiVisionList'
+ protobuf.protobuf = vision_list.SerializeToString()
+ protobuf_vec = InProtobufVector()
+
+ protobuf_vec.push_back(protobuf)
+ unique_id = stream_manager_api.SendProtobuf(stream_name, 0, protobuf_vec)
+
if unique_id < 0:
raise RuntimeError("Failed to send data to stream.")
- timeout = 3000
- infer_result = stream_manager_api.GetResultWithUniqueId(
- stream_name, unique_id, timeout)
+ infer_result = stream_manager_api.GetResult(stream_name, unique_id)
+
if infer_result.errorCode != 0:
raise RuntimeError(
"GetResultWithUniqueId error, errorCode=%d, errorMsg=%s" % (
@@ -80,6 +100,37 @@ def _do_infer(stream_manager_api, data_input):
return np.frombuffer(data_str, dtype=np.uint8).reshape(shape)
+def resize_long(img, long_size=513):
+ h, w, _ = img.shape
+ if h > w:
+ new_h = long_size
+ new_w = int(1.0 * long_size * w / h)
+ else:
+ new_w = long_size
+ new_h = int(1.0 * long_size * h / w)
+ imo = cv2.resize(img, (new_w, new_h))
+ return imo
+
+
+def pre_process(img_, crop_size=513):
+ image_mean = [103.53, 116.28, 123.675]
+ image_std = [57.375, 57.120, 58.395]
+ # resize
+ img_ = resize_long(img_, crop_size)
+
+ # mean, std
+ image_mean = np.array(image_mean)
+ image_std = np.array(image_std)
+ img_ = (img_ - image_mean) / image_std
+
+ # pad to crop_size
+ pad_h = crop_size - img_.shape[0]
+ pad_w = crop_size - img_.shape[1]
+ if pad_h > 0 or pad_w > 0:
+ img_ = cv2.copyMakeBorder(img_, 0, pad_h, 0, pad_w, cv2.BORDER_CONSTANT, value=0)
+
+ return img_
+
def main():
args = _parse_args()
# init stream manager
@@ -97,9 +148,15 @@ def main():
img_path = os.path.join(args.data_root, img_path)
msk_path = os.path.join(args.data_root, msk_path)
msk_ = cv2.imread(msk_path, cv2.IMREAD_GRAYSCALE)
- with open(img_path, 'rb') as f:
- data_input.data = f.read()
- each_array = _do_infer(stream_manager_api, data_input)
+ img_ = cv2.imread(img_path)
+ re_img = img_
+
+ crop_size = 513
+ img_ = pre_process(img_, crop_size)
+
+ data_input = img_.astype("float32")
+
+ each_array = _do_infer(stream_manager_api, data_input, re_img)
hist += _cal_hist(
msk_.flatten(), each_array.flatten(), args.num_classes)
@@ -116,6 +173,5 @@ def main():
stream_manager_api.DestroyAllStreams()
-
if __name__ == '__main__':
main()