I am making an input pipeline in tensorflow for a task I want to do. I have set up a TFRecord dataset which has been saved out to a file on disk.
I am trying to load in the dataset (to be batched and sent to the actual ML algorithm) using the following code:
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()
However, I get an error on the dataset.map() line. The error I get looks like this: TypeError: Expected int64, got <tensorflow.python.framework.sparse_tensor.SparseTensor object at 0x00000000085F74A8> of type 'SparseTensor' instead.
The read_single_record()
function looks like this:
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
I'm not sure where the issue lies. I got the idea for this code from the tensorflow API documentation, slightly modified for my purposes. I really have no idea where to start trying to fix this.
For reference, here is the code I have for generating the TFRecord file:
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())
Note that I've removed some code that isn't to do with the actual serialisation/creation of the TFRecords file.