tensorflow.python.framework.errors_impl.InvalidArgumentError: Expected image (JPEG, PNG, or GIF), got unknown format starting with '!(5#*8)->+-?*,>*'
[[Node: DecodeJpeg = DecodeJpeg[acceptable_fraction=1, channels=0, dct_method="", fancy_upscaling=true, ratio=1, try_recover_truncated=false](ParseSingleExample/Squeeze_image_raw)]]
[[Node: IteratorGetNext = IteratorGetNext[output_shapes=[[?,128,128,3], [?]], output_types=[DT_FLOAT, DT_INT64], _device="/job:localhost/replica:0/task:0/device:CPU:0"](Iterator)]]
读取tfrecord时 用tf.FixedLenFeature([], tf.string)处理features
最后使用tf.image.decode_jpeg(features['image_raw'])处理得到的tf.string
报如上错误。在tensorflow1.4下decode_jpeg无法处理字符转图片的情况?
使用tf.decode_raw(features['image_raw'],tf.uint8)后运行正常.......