我将阅读“图像”(2000)和“地标”(388)。
这是代码的一部分。
filename_queue = tf.train.string_input_producer([savepath])
reader = tf.TFRecordReader()
_, serialized_example = reader.read(filename_queue)
features = tf.parse_single_example(serialized_example, features={'label': tf.FixedLenFeature([], tf.string), 'img_raw':tf.FixedLenFeature([], tf.string), })
image = tf.decode_raw(features['img_raw'], tf.uint8)
image = tf.reshape(image, [224, 224, 3])
image = tf.cast(image, tf.float32)
label = tf.decode_raw(features['label'], tf.float64) # problem is here
label = tf.cast(label, tf.float32)
label = tf.reshape(label, [388])错误是
InvalidArgumentError (see above for traceback): Input to reshape is a tensor with 291 values, but the requested shape has 388.当我将'float64‘改为’float64 32‘时:
label = tf.decode_raw(features['label'], tf.float32) # problem is here
#Error: InvalidArgumentError (see above for traceback): Input to reshape is a tensor with 582 values, but the requested shape has 388或者是“浮动16”:
label = tf.decode_raw(features['label'], tf.float16) # problem is here
#Error: InvalidArgumentError (see above for traceback): Input to reshape is a tensor with 1164 values, but the requested shape has 388下面是我制作tfrecords的方法:(为了简单起见,我简化了一些代码)
writer = tf.python_io.TFRecordWriter(savepath)
for i in range(number_of_images):
img = Image.open(ImagePath[i]) # load one image from path
landmark = landmark_read_from_csv[i] # shape of landmark_read_from_csv is (number_of_images, 388)
example = tf.train.Example(features=tf.train.Features(feature={
"label": tf.train.Feature(bytes_list=tf.train.BytesList(value=[landmark.tobytes()])),
'img_raw': tf.train.Feature(bytes_list=tf.train.BytesList(value=[img.tobytes()]))}))
writer.write(example.SerializeToString())
writer.close()我有三个问题:
发布于 2017-12-22 23:22:37
我最近遇到了一个非常类似的问题,根据我个人的经验,我很有信心我能够推断出你的问题的答案,尽管我不能百分之百肯定。
byte列表时具有不同的长度,并且由于float16的长度是float32的一半,所以相同的字节列表可以被读取为n个float32值的序列,或者是float16值的两倍。换句话说,当您更改数据类型时,您试图解码的byte列表不会改变,但是更改的是您对这个数组列表的分区。tfrecord文件的数据的数据类型,并在读取byte_list时使用相同的数据类型来解码它(可以使用.dtype属性检查numpy数组的数据类型)。https://stackoverflow.com/questions/47120509
复制相似问题