【出现如下形式的报错】借用github上的错误代码
File "retrain.py", line 808, in main
jpeg_data_tensor, bottleneck_tensor)
File "retrain.py", line 440, in cache_bottlenecks
jpeg_data_tensor, bottleneck_tensor)
File "retrain.py", line 392, in get_or_create_bottleneck
create_bottleneck_file(bottleneck_path, image_lists, label_name, index, image_dir, category, sess, jpeg_data_tensor, bottleneck_tensor)
File "retrain.py", line 356, in create_bottleneck_file
bottleneck_values = run_bottleneck_on_image(sess, image_data, jpeg_data_tensor, bottleneck_tensor)
File "retrain.py", line 275, in run_bottleneck_on_image
{image_data_tensor: image_data})
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 778, in run
run_metadata_ptr)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 982, in _run
feed_dict_string, options, run_metadata)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1032, in _do_run
target_list, options, run_metadata)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1052, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Invalid JPEG data, size 147471
[[Node: DecodeJpeg = DecodeJpegacceptable_fraction=1, channels=3, dct_method="", fancy_upscaling=true, ratio=1, try_recover_truncated=false, _device="/job:localhost/replica:0/task:0/cpu:0"]]
Caused by op u'DecodeJpeg', defined at:
File "retrain.py", line 1062, in
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "retrain.py", line 779, in main
create_inception_graph())
File "retrain.py", line 256, in create_inception_graph
RESIZED_INPUT_TENSOR_NAME]))
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/importer.py", line 308, in import_graph_def
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2336, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1228, in init
self._traceback = _extract_stack()
InvalidArgumentError (see above for traceback): Invalid JPEG data, size 147471
[[Node: DecodeJpeg = DecodeJpegacceptable_fraction=1, channels=3, dct_method="", fancy_upscaling=true, ratio=1, try_recover_truncated=false, _device="/job:localhost/replica:0/task:0/cpu:0"]]
【原因】有jpg文件损坏，并不是因为数据中有png等其他格式的图片，这些格式的图片可能没有进入处理流程
【解决】关键是找出哪些jpg文件引起了报错，仔细检查源码，找出读取照片文件的代码，加入print代码把文件名打印出来，然后重新运行程序，找出报错文件，删除掉或单独进行修复。一般出错的文件较少，我的做法是直接删除
【示例】
def create_bottleneck_file(bottleneck_path, image_lists, label_name, index,image_dir, category, sess, jpeg_data_tensor,decoded_image_tensor, resized_input_tensor,bottleneck_tensor):"""Create a single bottleneck file."""tf.logging.debug('Creating bottleneck at ' + bottleneck_path)image_path = get_image_path(image_lists, label_name, index,image_dir, category)if not tf.gfile.Exists(image_path):tf.logging.fatal('File does not exist %s', image_path)image_data = tf.gfile.GFile(image_path, 'rb').read()# 加入这行代码，成功找到有问题的图片，然后把它拿出来，程序就可以继续运行了print('image#############', image_path) # 定位有问题的图片try:bottleneck_values = run_bottleneck_on_image(sess, image_data, jpeg_data_tensor, decoded_image_tensor,resized_input_tensor, bottleneck_tensor)except Exception as e:raise RuntimeError('Error during processing file %s (%s)' % (image_path,str(e)))bottleneck_string = ','.join(str(x) for x in bottleneck_values)with tf.gfile.GFile(bottleneck_path, 'w') as bottleneck_file:bottleneck_file.write(bottleneck_string)