使用 Tensorflow 数据集解码 RLE(运行 长度编码)掩码

Decoding RLE (run-length encoding) mask with Tensorflow Datasets

我一直在试验 数据集,但我不知道如何有效地创建 RLE-masks。 仅供参考,我正在使用 Kaggle 中空中客车船舶检测挑战赛的数据:https://www.kaggle.com/c/airbus-ship-detection/data

我知道我的 RLE 解码功能可以(借用)一个内核:

def rle_decode(mask_rle, shape=(768, 768)):
'''
mask_rle: run-length as string formated (start length)
shape: (height,width) of array to return
Returns numpy array, 1 - mask, 0 - background
'''
if not isinstance(mask_rle, str):
    img = np.zeros(shape[0]*shape[1], dtype=np.uint8)
    return img.reshape(shape).T

s = mask_rle.split()
starts, lengths = [np.asarray(x, dtype=int) for x in (s[0:][::2], s[1:][::2])]
starts -= 1
ends = starts + lengths
img = np.zeros(shape[0]*shape[1], dtype=np.uint8)
for lo, hi in zip(starts, ends):
    img[lo:hi] = 1
return img.reshape(shape).T

.. 但它似乎不能很好地处理管道:

list_ds = tf.data.Dataset.list_files(train_paths_abs)
ds = list_ds.map(parse_img)

使用以下解析函数,一切正常:

def parse_img(file_path,new_size=[128,128]):    
    img_content = tf.io.read_file(file_path)
    img = tf.image.decode_jpeg(img_content)
    img = tf.image.convert_image_dtype(img, tf.float32)    
    img = tf.image.resize(img,new_size)
    return img

但是如果我加上面具,事情就会变得很糟糕:

def parse_img(file_path,new_size=[128,128]):
    
    # Image
    img_content = tf.io.read_file(file_path)
    img = tf.image.decode_jpeg(img_content)
    img = tf.image.convert_image_dtype(img, tf.float32)    
    img = tf.image.resize(img,new_size)
    
    # Mask
    file_id = tf.strings.split(file_path,'/')[-1]
    objects = [rle_decode(m) for m in df2[df.ImageId==file_id]]
    mask = np.sum(objects,axis=0)
    mask = np.expand_dims(mask,3)   # Force mask to have 3 channels, necessary for resize step
    mask = tf.image.convert_image_dtype(mask, tf.int8)
    mask = tf.clip_by_value(mask,0,1)
    mask = tf.image.resize(mask,new_size)
    mask = tf.squeeze(mask)     # squeeze back
    mask = tf.image.convert_image_dtype(mask, tf.int8)
    
    return img, mask

虽然我的 parse_img 函数工作正常(我已经在样本上检查过它,每个 运行 需要 271 µs ± 67.9 µs); list_ds.map 这一步在挂起之前需要很长时间(> 5 分钟)。 我不知道出了什么问题,这让我发疯! 有什么想法吗?

你可以像这样用重写函数rle_decode(这里我不做最后的转置以使其更通用,但你可以稍后再做):

import tensorflow as tf

def rle_decode_tf(mask_rle, shape):
    shape = tf.convert_to_tensor(shape, tf.int64)
    size = tf.math.reduce_prod(shape)
    # Split string
    s = tf.strings.split(mask_rle)
    s = tf.strings.to_number(s, tf.int64)
    # Get starts and lengths
    starts = s[::2] - 1
    lens = s[1::2]
    # Make ones to be scattered
    total_ones = tf.reduce_sum(lens)
    ones = tf.ones([total_ones], tf.uint8)
    # Make scattering indices
    r = tf.range(total_ones)
    lens_cum = tf.math.cumsum(lens)
    s = tf.searchsorted(lens_cum, r, 'right')
    idx = r + tf.gather(starts - tf.pad(lens_cum[:-1], [(1, 0)]), s)
    # Scatter ones into flattened mask
    mask_flat = tf.scatter_nd(tf.expand_dims(idx, 1), ones, [size])
    # Reshape into mask
    return tf.reshape(mask_flat, shape)

一个小测试(TensorFlow 2.0):

mask_rle = '1 2 4 3 9 4 15 5'
shape = [4, 6]
# Original NumPy function
print(rle_decode(mask_rle, shape))
# [[1 0 0 1]
#  [1 0 0 0]
#  [0 1 1 0]
#  [1 1 1 0]
#  [1 1 1 0]
#  [1 1 1 0]]
# TensorFlow function (transposing is done out of the function)
tf.print(tf.transpose(rle_decode_tf(mask_rle, shape)))
# [[1 0 0 1]
#  [1 0 0 0]
#  [0 1 1 0]
#  [1 1 1 0]
#  [1 1 1 0]
#  [1 1 1 0]]