Tensorflow目标检测API 1通道图像

在Tensorflow的对象检测API中，是否有任何方法可以使用针对RGB图像进行训练的预训练模型，用于单通道灰度图像（深度）？

我尝试了以下方法，使用Tensorflow中的预训练模型（更快的rcnn\u resnet101\u coco\u 11\u 06\u 2017）对灰度（1通道图像）执行对象检测。它确实对我有用

该模型是在RGB图像上训练的，所以我只需要在Tensorflow Repo中修改某些代码

第一次更改： 请注意，ipynb中的现有代码是为3通道映像编写的，因此请将load_image_更改为_numpy数组函数，如图所示

从

到

第二次更改：灰度图像只有一个通道中的数据。要执行目标检测，我们需要3个通道（推理代码是为3个通道编写的）

这可以通过两种方式实现。 a） 将单通道数据复制到另外两个通道中 b） 用零填充其他两个通道。 这两种方法都可以，我使用了第一种方法

在ipynb中，转到读取图像并将其转换为numpy数组（ipynb末尾的forloop）的部分

将代码更改为：

for image_path in TEST_IMAGE_PATHS:
  image = Image.open(image_path)
  # the array based representation of the image will be used later in order to prepare the
  # result image with boxes and labels on it.
  image_np = load_image_into_numpy_array(image)
  # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
  image_np_expanded = np.expand_dims(image_np, axis=0)

为此：

for image_path in TEST_IMAGE_PATHS:
  image = Image.open(image_path)
  # the array based representation of the image will be used later in order to prepare the
  # result image with boxes and labels on it.
  image_np = load_image_into_numpy_array(image)
  if image_np.shape[2] != 3:  
      image_np = np.broadcast_to(image_np, (image_np.shape[0], image_np.shape[1], 3)).copy() # Duplicating the Content
      ## adding Zeros to other Channels
      ## This adds Red Color stuff in background -- not recommended 
      # z = np.zeros(image_np.shape[:-1] + (2,), dtype=image_np.dtype)
      # image_np = np.concatenate((image_np, z), axis=-1)
  # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
  image_np_expanded = np.expand_dims(image_np, axis=0)

就是这样，运行该文件，您应该会看到结果。 这是我的结果

for image_path in TEST_IMAGE_PATHS:
  image = Image.open(image_path)
  # the array based representation of the image will be used later in order to prepare the
  # result image with boxes and labels on it.
  image_np = load_image_into_numpy_array(image)
  # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
  image_np_expanded = np.expand_dims(image_np, axis=0)

for image_path in TEST_IMAGE_PATHS:
  image = Image.open(image_path)
  # the array based representation of the image will be used later in order to prepare the
  # result image with boxes and labels on it.
  image_np = load_image_into_numpy_array(image)
  if image_np.shape[2] != 3:  
      image_np = np.broadcast_to(image_np, (image_np.shape[0], image_np.shape[1], 3)).copy() # Duplicating the Content
      ## adding Zeros to other Channels
      ## This adds Red Color stuff in background -- not recommended 
      # z = np.zeros(image_np.shape[:-1] + (2,), dtype=image_np.dtype)
      # image_np = np.concatenate((image_np, z), axis=-1)
  # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
  image_np_expanded = np.expand_dims(image_np, axis=0)