【发布时间】：2023-03-18 03:21:02
【问题描述】：
当我想重新训练inception模块时，出现如下错误（我使用https://codelabs.developers.google.com/codelabs/tensorflow-for-poets/#0中的方法）
root@00aa0e1cd75b:/tf_files# python retrain.py \
--bottleneck_dir=bottlenecks
--how_many_training_steps=500
--model_dir=inception
--summaries_dir=training_summaries/basic
--output_graph=retrained_graph.pb
--output_labels=retrained_labels.txt
--image_dir=MRII
2017-06-20 15:04:15.616625: W
tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library
wasn't compiled to use SSE4.1 instructions, but these are available on your
machine and could speed up CPU computations.
Looking for images in 'Bold'
Looking for images in 'ASL'
Creating bottleneck at bottlenecks/Bold/1011_221_MR.MR.CCIR-00600_CCIR-
00675_Benzinger_AV45.13.49.20150915.142526.1kyq4ky.dcm.jpeg.txt
2017-06-20 15:04:22.501680: W tensorflow/core/framework/op_def_util.cc:332]
Op BatchNormWithGlobalNormalization is deprecated. It will cease to work in
GraphDef version 9. Use tf.nn.batch_normalization().
Not a JPEG file: starts with 0x50 0x35
Traceback (most recent call last):
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 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"]]
请告诉我如何处理此错误。谢谢！
【问题讨论】：
-
如果你能找到导致问题的文件，那么你可以去检查它。如果文件损坏，则脚本将引发错误。看起来你有一个错误，说你甚至没有加载 JPEG 文件，但这可能是其他一些错误。仔细检查您的数据并查看您的数据！
标签： python tensorflow