Tensorflow 无法从 `dataset.map(mapFn)` 中的方法获取 `image.shape`

mic*_*ael 11 python tensorflow2.0

我正在尝试做tensorflow等效的torch.transforms.Resize(TRAIN_IMAGE_SIZE),它将最小的图像尺寸调整为TRAIN_IMAGE_SIZE. 像这样的东西

def transforms(filename):
  parts = tf.strings.split(filename, '/')
  label = parts[-2]

  image = tf.io.read_file(filename)
  image = tf.image.decode_jpeg(image)
  image = tf.image.convert_image_dtype(image, tf.float32)

  # this doesn't work with Dataset.map() because image.shape=(None,None,3) from Dataset.map()
  image = largest_sq_crop(image) 

  image = tf.image.resize(image, (256,256))
  return image, label

list_ds = tf.data.Dataset.list_files('{}/*/*'.format(DATASET_PATH))
images_ds = list_ds.map(transforms).batch(4)
Run Code Online (Sandbox Code Playgroud)

简单的答案在这里:Tensorflow:裁剪图像的最大中心正方形区域

但是当我使用 with 的方法时tf.data.Dataset.map(transforms),我shape=(None,None,3)从内部获取largest_sq_crop(image)。当我正常调用它时,该方法工作正常。

mic*_*ael 7

我找到了答案。这与我的调整大小方法在急切执行中工作良好的事实有关,例如,tf.executing_eagerly()==True但在dataset.map(). 显然,在那个执行环境中,tf.executing_eagerly()==False.

我的错误在于我解压图像的形状以获得缩放尺寸的方式。Tensorflow 图执行似乎不支持访问元tensor.shape组。

  # wrong
  b,h,w,c = img.shape
  print("ERR> ", h,w,c)
  # ERR>  None None 3

  # also wrong
  b = img.shape[0]
  h = img.shape[1]
  w = img.shape[2]
  c = img.shape[3]
  print("ERR> ", h,w,c)
  # ERR>  None None 3

  # but this works!!!
  shape = tf.shape(img)
  b = shape[0]
  h = shape[1]
  w = shape[2]
  c = shape[3]
  img = tf.reshape( img, (-1,h,w,c))
  print("OK> ", h,w,c)
  # OK>  Tensor("strided_slice_2:0", shape=(), dtype=int32) Tensor("strided_slice_3:0", shape=(), dtype=int32) Tensor("strided_slice_4:0", shape=(), dtype=int32)

Run Code Online (Sandbox Code Playgroud)

我在函数下游使用形状尺寸dataset.map(),它引发了以下异常,因为它获取的是None而不是值。

TypeError: Failed to convert object of type <class 'tuple'> to Tensor. Contents: (-1, None, None, 3). Consider casting elements to a supported type.
Run Code Online (Sandbox Code Playgroud)

当我切换到手动解压形状时tf.shape(),一切正常。