这个问题会让我发疯：我有一个使用tflearn的卷积网络代码。我想保存我的模型并加载它以对不同的图像进行预测。我是这样做的：
def predictValues(image_path):
...
model = tflearn.DNN(convnet)
if not os.path.exists("emotionPrediction.tfl.meta"):
X = images.reshape(-1, 1, 268, 1)
Y = lables.reshape(-1, 7)
model.fit({'input': X}, {'targets': Y}, n_epoch=2, snapshot_step=500, show_metric=True)
model.save("emotionPrediction.tfl")
model.load(".\\emotionPrediction.tfl", weights_only=True)
print("Emotion values for %s: ", file):
....
images = [path1, path2, path3]
for x in images:
predictValues(x)
不幸的是，无论我如何更改路径，代码都无法正常工作。我得到了第一张图片的预测，但之后对于其他图片我得到了这个错误：
2018-03-01 14:43:58.334231: W C:\tf_jenkins\workspace\rel-win\M\windows\PY\35\tensorflow\core\framework\op_kernel.cc:1198] Not found: Key Conv2D_11/W not found in checkpoint
2018-03-01 14:43:58.334617: W C:\tf_jenkins\workspace\rel-win\M\windows\PY\35\tensorflow\core\framework\op_kernel.cc:1198] Not found: Key FullyConnected_3/b not found in checkpoint
2018-03-01 14:43:58.337374: W C:\tf_jenkins\workspace\rel-win\M\windows\PY\35\tensorflow\core\framework\op_kernel.cc:1198] Not found: Key Conv2D_10/b not found in checkpoint
2018-03-01 14:43:58.337411: W C:\tf_jenkins\workspace\rel-win\M\windows\PY\35\tensorflow\core\framework\op_kernel.cc:1198] Not found: Key Conv2D_10/W not found in checkpoint
2018-03-01 14:43:58.342332: W C:\tf_jenkins\workspace\rel-win\M\windows\PY\35\tensorflow\core\framework\op_kernel.cc:1198] Not found: Key Conv2D_11/b not found in checkpoint
2018-03-01 14:43:58.350840: W C:\tf_jenkins\workspace\rel-win\M\windows\PY\35\tensorflow\core\framework\op_kernel.cc:1198] Not found: Key Conv2D_6/W not found in checkpoint
2018-03-01 14:43:58.354507: W C:\tf_jenkins\workspace\rel-win\M\windows\PY\35\tensorflow\core\framework\op_kernel.cc:1198] Not found: Key Conv2D_6/b not found in checkpoint
2018-03-01 14:43:58.355432: W C:\tf_jenkins\workspace\rel-win\M\windows\PY\35\tensorflow\core\framework\op_kernel.cc:1198] Not found: Key Conv2D_7/W not found in checkpoint
2018-03-01 14:43:58.535684: W C:\tf_jenkins\workspace\rel-win\M\windows\PY\35\tensorflow\core\framework\op_kernel.cc:1198] Not found: Key FullyConnected_3/W not found in checkpoint
2018-03-01 14:43:58.543666: W C:\tf_jenkins\workspace\rel-win\M\windows\PY\35\tensorflow\core\framework\op_kernel.cc:1198] Not found: Key Conv2D_7/b not found in checkpoint
2018-03-01 14:43:58.548686: W C:\tf_jenkins\workspace\rel-win\M\windows\PY\35\tensorflow\core\framework\op_kernel.cc:1198] Not found: Key Conv2D_8/W not found in checkpoint
2018-03-01 14:43:58.551316: W C:\tf_jenkins\workspace\rel-win\M\windows\PY\35\tensorflow\core\framework\op_kernel.cc:1198] Not found: Key Conv2D_8/b not found in checkpoint
2018-03-01 14:43:58.559867: W C:\tf_jenkins\workspace\rel-win\M\windows\PY\35\tensorflow\core\framework\op_kernel.cc:1198] Not found: Key Conv2D_9/W not found in checkpoint
2018-03-01 14:43:58.567227: W C:\tf_jenkins\workspace\rel-win\M\windows\PY\35\tensorflow\core\framework\op_kernel.cc:1198] Not found: Key Conv2D_9/b not found in checkpoint
2018-03-01 14:43:58.588178: W C:\tf_jenkins\workspace\rel-win\M\windows\PY\35\tensorflow\core\framework\op_kernel.cc:1198] Not found: Key FullyConnected_2/b not found in checkpoint
2018-03-01 14:43:58.588249: W C:\tf_jenkins\workspace\rel-win\M\windows\PY\35\tensorflow\core\framework\op_kernel.cc:1198] Not found: Key FullyConnected_2/W not found in checkpoint
Traceback (most recent call last):
File "C:\Users\xx\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1350, in _do_call
return fn(*args)
File "C:\Users\xx\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1329, in _run_fn
status, run_metadata)
File "C:\Users\xx\Python35\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 473, in __exit__
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.NotFoundError: Key Conv2D_11/W not found in checkpoint
[[Node: save_7/RestoreV2_6 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save_7/Const_0_0, save_7/RestoreV2_6/tensor_names, save_7/RestoreV2_6/shape_and_slices)]]
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\Users\xx\Desktop\Prediction.py", line 128, in <module>
predictEmotions(x)
File "C:\Users\xx\Desktop\Prediction.py", line 113, in predictEmotions
model.load(".\\emotionPrediction.tfl", weights_only=True)
File "C:\Users\xx\Python35\lib\site-packages\tflearn\models\dnn.py", line 308, in load
self.trainer.restore(model_file, weights_only, **optargs)
File "C:\Users\xx\Python35\lib\site-packages\tflearn\helpers\trainer.py", line 492, in restore
self.restorer_trainvars.restore(self.session, model_file)
File "C:\Users\xx\Python35\lib\site-packages\tensorflow\python\training\saver.py", line 1686, in restore
{self.saver_def.filename_tensor_name: save_path})
File "C:\Users\xx\Python35\lib\site-packages\tensorflow\python\client\session.py", line 895, in run
run_metadata_ptr)
File "C:\Users\xx\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1128, in _run
feed_dict_tensor, options, run_metadata)
File "C:\Users\xx\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1344, in _do_run
options, run_metadata)
File "C:\Users\xx\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1363, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.NotFoundError: Key Conv2D_11/W not found in checkpoint
[[Node: save_7/RestoreV2_6 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save_7/Const_0_0, save_7/RestoreV2_6/tensor_names, save_7/RestoreV2_6/shape_and_slices)]]
Caused by op 'save_7/RestoreV2_6', defined at:
File "C:\Users\xx\Desktop\Prediction.py", line 128, in <module>
predictEmotions(x)
File "C:\Users\xx\Desktop\Prediction.py", line 105, in predictEmotions
model = tflearn.DNN(convnet)
File "C:\Users\xx\Python35\lib\site-packages\tflearn\models\dnn.py", line 65, in __init__
best_val_accuracy=best_val_accuracy)
File "C:\Users\xx\Python35\lib\site-packages\tflearn\helpers\trainer.py", line 155, in __init__
allow_empty=True)
File "C:\Users\xx\Python35\lib\site-packages\tensorflow\python\training\saver.py", line 1239, in __init__
self.build()
File "C:\Users\xx\Python35\lib\site-packages\tensorflow\python\training\saver.py", line 1248, in build
self._build(self._filename, build_save=True, build_restore=True)
File "C:\Users\xx\Python35\lib\site-packages\tensorflow\python\training\saver.py", line 1284, in _build
build_save=build_save, build_restore=build_restore)
File "C:\Users\xx\Python35\lib\site-packages\tensorflow\python\training\saver.py", line 765, in _build_internal
restore_sequentially, reshape)
File "C:\Users\xx\Python35\lib\site-packages\tensorflow\python\training\saver.py", line 428, in _AddRestoreOps
tensors = self.restore_op(filename_tensor, saveable, preferred_shard)
File "C:\Users\xx\Python35\lib\site-packages\tensorflow\python\training\saver.py", line 268, in restore_op
[spec.tensor.dtype])[0])
File "C:\Users\xx\Python35\lib\site-packages\tensorflow\python\ops\gen_io_ops.py", line 1113, in restore_v2
shape_and_slices=shape_and_slices, dtypes=dtypes, name=name)
File "C:\Users\xx\Python35\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "C:\Users\xx\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 3160, in create_op
op_def=op_def)
File "C:\Users\xx\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 1625, in __init__
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
NotFoundError (see above for traceback): Key Conv2D_11/W not found in checkpoint
[[Node: save_7/RestoreV2_6 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save_7/Const_0_0, save_7/RestoreV2_6/tensor_names, save_7/RestoreV2_6/shape_and_slices)]]
有人可以帮忙吗？我已经谷歌搜索了几个小时来解决这个问题但是徒劳无功..
答案 0 :(得分：0)
你必须使用
model.predict(input)
model.load()只会加载预先保存的模型文件。它不会马上给你预测。