我正在为我想做的任务在 tensorflow 中制作一个输入管道。我已经设置了一个 TFRecord 数据集，该数据集已保存到磁盘上的文件中。
我正在尝试使用以下代码加载数据集(进行批处理并发送到实际的 ML 算法):
dataset = tf.data.TFRecordDataset(filename)
print("Starting mapping...")
dataset = dataset.map(map_func = read_single_record)
print("Mapping complete")
buffer = 500 # How large of a buffer will we sample from?
batch_size = 125
capacity = buffer + 2 * batch_size
print("Shuffling dataset...")
dataset = dataset.shuffle(buffer_size = buffer)
print("Batching dataset...")
dataset = dataset.batch(batch_size)
dataset = dataset.repeat()
print("Creating iterator...")
iterator = dataset.make_one_shot_iterator()
examples_batch, labels_batch = iterator.get_next()
但是，我在 dataset.map() 行上收到错误。我收到的错误如下所示:TypeError: Expected int64, got <tensorflow.python.framework.sparse_tensor.SparseTensor object at 0x00000000085F74A8> of type 'SparseTensor' instead.
read_single_record()函数看起来像这样:
keys_to_features = {
"image/pixels": tf.FixedLenFeature([], tf.string, default_value = ""),
"image/label/class": tf.FixedLenFeature([], tf.int64, default_value = 0),
"image/label/numbb": tf.FixedLenFeature([], tf.int64, default_value = 0),
"image/label/by": tf.VarLenFeature(tf.float32),
"image/label/bx": tf.VarLenFeature(tf.float32),
"image/label/bh": tf.VarLenFeature(tf.float32),
"image/label/bw": tf.VarLenFeature(tf.float32)
}
features = tf.parse_single_example(record, keys_to_features)
image_pixels = tf.image.decode_image(features["image/pixels"])
print("Features: {0}".format(features))
example = image_pixels # May want to do some processing on this at some point
label = [features["image/label/class"],
features["image/label/numbb"],
features["image/label/by"],
features["image/label/bx"],
features["image/label/bh"],
features["image/label/bw"]]
return example, label
我不确定问题出在哪里。我从 tensorflow API 文档中得到了这段代码的想法，为了我的目的稍微修改了一下。我真的不知道从哪里开始尝试解决这个问题。
作为引用，这里是我生成 TFRecord 文件的代码:
def parse_annotations(in_file, img_filename, cell_width, cell_height):
""" Parses the annotations file to obtain the bounding boxes for a single image
"""
y_mins = []
x_mins = []
heights = []
widths = []
grids_x = []
grids_y = []
classes = [0]
num_faces = int(in_file.readline().rstrip())
img_width, img_height = get_image_dims(img_filename)
for i in range(num_faces):
clss, x, y, width, height = in_file.readline().rstrip().split(',')
x = float(x)
y = float(y)
width = float(width)
height = float(height)
x = x - (width / 2.0)
y = y - (height / 2.0)
y_mins.append(y)
x_mins.append(x)
heights.append(height)
widths.append(width)
grid_x, grid_y = get_grid_loc(x, y, width, height, img_width, img_height, cell_width, cell_height)
pixels = get_image_pixels(img_filename)
example = tf.train.Example(features = tf.train.Features(feature = {
"image/pixels": bytes_feature(pixels),
"image/label/class": int_list_feature(classes),
"image/label/numbb": int_list_feature([num_faces]),
"image/label/by": float_list_feature(y_mins),
"image/label/bx": float_list_feature(x_mins),
"image/label/bh": float_list_feature(heights),
"image/label/bw": float_list_feature(widths)
}))
return example, num_faces
if len(sys.argv) < 4:
print("Usage: python convert_to_tfrecord.py [path to processed annotations file] [path to training output file] [path to validation output file] [training fraction]")
else:
processed_fn = sys.argv[1]
train_fn = sys.argv[2]
valid_fn = sys.argv[3]
train_frac = float(sys.argv[4])
if(train_frac > 1.0 or train_frac < 0.0):
print("Training fraction (f) must be 0 <= f <= 1")
else:
with tf.python_io.TFRecordWriter(train_fn) as writer:
with tf.python_io.TFRecordWriter(valid_fn) as valid_writer:
with open(processed_fn) as f:
for line in f:
ex, n_faces = parse_annotations(f, line.rstrip(), 30, 30)
randVal = rand.random()
if(randVal < train_frac):
writer.write(ex.SerializeToString())
else:
valid_writer.write(ex.SerializeToString())
请注意，我删除了一些与 TFRecords 文件的实际序列化/创建无关的代码。
请您参考如下方法:
未测试，但映射函数似乎无法返回 SparseTensor 和 Tensor 的列表。
tf.VarLenFeature(tf.float32) 返回一个 SparseTensor 但 tf.FixedLenFeature([], tf.int64) 返回一个 张量。
为了更好地进行批处理，我建议您只使用 Tensor。
关于如何派生 label 的建议:
label = {
"image/label/class" : features["image/label/class"],
"image/label/numbb" : features["image/label/numbb"],
"image/label/by" : tf.sparse_tensor_to_dense(features["image/label/by"], default_value=-1),
"image/label/bx" : tf.sparse_tensor_to_dense(features["image/label/bx"], default_value=-1)
"image/label/bh" : tf.sparse_tensor_to_dense(features["image/label/bh"], default_value=-1)
"image/label/bw" : tf.sparse_tensor_to_dense(features["image/label/bw"], default_value=-1)
}
有关如何处理此映射输出的灵感，我建议使用 thread .
