修改部分代码和文档

Python/Segmentation/Unet.py

 import numpy as np
-from PIL import Image
 import cv2
 import migraphx
 
-def Preprocess(pil_img, newW, newH):
-    assert newW > 0 and newH > 0, 'Scale is too small'
-    pil_img = pil_img.resize((newW, newH))
-    img_nd = np.array(pil_img)
+def Preprocessing(pil_img, newW, newH):
+    assert newW > 0 and newH > 0, 'Scale is too small' 
+    img_nd = cv2.resize(pil_img, (newW, newH))          # 将图像尺寸修改为256x256
+    img_nd = cv2.cvtColor(img_nd, cv2.COLOR_BGR2RGB)    # BGR转换为RGB
+
     if len(img_nd.shape) == 2:
         img_nd = np.expand_dims(img_nd, axis=2)
 
-    # HWC to CHW
-    img_print = pil_img
-    img_trans = img_nd.transpose((2, 0, 1))
-    if img_trans.max() > 1:
-        img_trans = img_trans / 255
-    img_trans = np.expand_dims(img_trans, 0)
-
-    return img_trans, img_print
+    img_trans = img_nd.transpose((2, 0, 1))             # HWC转换为CHW
+    if img_trans.max() > 1:                             # 保证数据处于0-1之间的浮点数
+        img_trans = img_trans / 255.0  
+    img_trans = np.expand_dims(img_trans, 0)            # CHW扩展为NCHW
+    img = img_trans.astype(np.float32)                  # 转换成浮点型数据
+    return img
 
 def Sigmoid(x):
   return 1 / (1 + np.exp(-x))
@@ -25,7 +23,7 @@ def Sigmoid(x):
 if __name__ == '__main__':
     
     # 加载模型
-    model = migraphx.parse_onnx("./model/unet_13_256.onnx")
+    model = migraphx.parse_onnx("../../Resource/Models/Segmentation/unet_13_256.onnx")
     inputName = model.get_parameter_names()
     inputShape = model.get_parameter_shapes()
     print("inputName:{0} \ninputShape:{1}".format(inputName, inputShape))
@@ -34,10 +32,8 @@ if __name__ == '__main__':
     model.compile(migraphx.get_target("gpu"), device_id=0)   # device_id: 设置GPU设备，默认为0号设备
 
     # 图像预处理
-    img = Image.open("./car.jpeg")
-    img, imPrint = Preprocess(img, 256, 256)
-    input_img = np.zeros((1,3,256,256),dtype='float32') 
-    np.lib.stride_tricks.as_strided(input_img, shape=img.shape, strides=input_img.strides)[:] = img
+    img = cv2.imread("../../Resource/Images/car1.jpeg")
+    input_img = Preprocessing(img, 256, 256)
 
     # 模型推理
     mask = model.run({'inputs':input_img})      

Python/Segmentation/requirement.txt → Python/Segmentation/requirements.txt

 opencv-python
-numpy
-pillow
+numpy
\ No newline at end of file
\ No newline at end of file

README.md

@@ -86,7 +86,7 @@ python Unet.py
 
 输出结果为：
 
-<img src="C:/Users/柳聪/Desktop/ni/unet_migraphx/Doc/Images/Unet_03.jpg" style="zoom:100%;" align=middle>
+<img src="./Doc/Images/Unet_03.jpg" style="zoom:100%;" align=middle>
 
 ### C++版本推理
 
@@ -105,7 +105,7 @@ cd ./build/
 
 会在当前目录中生成分割结果图像Result.jpg
 
-<img src="C:/Users/柳聪/Desktop/ni/unet_migraphx/Doc/Images/Unet_02.jpg" style="zoom:100%;" align=middle>
+<img src="./Doc/Images/Unet_02.jpg" style="zoom:100%;" align=middle>
 
 ## 历史版本