python-3.x - Tensorflow 2.0 无效参数错误 : assertion failed: [Condition x == y did not hold element-wise:]

Question

我正在训练一个 mnist CNN。当我运行我的代码时，问题来了。我尝试了其他答案，但它们不起作用。我是 TensorFlow 的新手，所以有人可以向我解释这个错误。这是我的代码。我正在使用 Pycharm 2020.2。和 python 中的 Python 3.6。我找不到任何帮助。

import tensorflow as tf
from tensorflow.keras.models import Sequential

mnist = tf.keras.datasets.mnist

(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = tf.keras.utils.normalize(x_train, axis=1)
x_test = tf.keras.utils.normalize(x_train, axis=1)



model = Sequential()

model.add(tf.keras.layers.Dense(256))
model.add(tf.keras.layers.Conv1D(kernel_size=4, strides=1, filters=4, activation="relu"))
model.add(tf.keras.layers.Conv1D(kernel_size=3, strides=1, activation="relu", filters=3))
model.add(tf.keras.layers.Dense(128, activation="relu"))
model.add(tf.keras.layers.Conv1D(kernel_size=2, filters=2, strides=1, activation="relu"))
model.add(tf.keras.layers.Conv1D(kernel_size=1, filters=1, strides=1, activation="relu"))
model.add(tf.keras.layers.Dense(64, activation="relu"))
model.add(tf.keras.layers.MaxPool1D(pool_size=2, strides=1))
model.add(tf.keras.layers.Dense(256, activation="relu"))
model.add(tf.keras.layers.Conv1D(kernel_size=4, filters=4, strides=1, activation="relu"))
model.add(tf.keras.layers.Conv1D(kernel_size=3, filters=3, strides=1, activation="relu"))
model.add(tf.keras.layers.MaxPool1D(pool_size=2, strides=1))
model.add(tf.keras.layers.Dropout(0.2))
model.add(tf.keras.layers.Dense(128, activation="relu"))
model.add(tf.keras.layers.Conv1D(kernel_size=2, filters=2, strides=1, activation="relu"))
model.add(tf.keras.layers.Conv1D(kernel_size=1, filters=1, strides=1, activation="relu"))
model.add(tf.keras.layers.Dense(64, activation="relu"))
model.add(tf.keras.layers.Dense(16, activation="softmax"))
model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])


    
model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])
model.fit(x=x_train, y=y_train, batch_size=64, epochs=5, shuffle=True, validation_split=0.1)
model.summary()

报错:

Train on 54000 samples, validate on 6000 samples
Epoch 1/5
2020-09-09 15:16:16.953428: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_10.dll
2020-09-09 15:16:17.146701: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll
2020-09-09 15:16:17.741916: W tensorflow/stream_executor/gpu/redzone_allocator.cc:312] Internal: Invoking GPU asm compilation is supported on Cuda non-Windows platforms only
Relying on driver to perform ptx compilation. This message will be only logged once.
2020-09-09 15:16:18.085250: W tensorflow/core/common_runtime/base_collective_executor.cc:217] BaseCollectiveExecutor::StartAbort Invalid argument: assertion failed: [Condition x == y did not hold element-wise:] [x (loss/output_1_loss/SparseSoftmaxCrossEntropyWithLogits/Shape_1:0) = ] [64 1] [y (loss/output_1_loss/SparseSoftmaxCrossEntropyWithLogits/strided_slice:0) = ] [64 14]
     [[{{node loss/output_1_loss/SparseSoftmaxCrossEntropyWithLogits/assert_equal_1/Assert/Assert}}]]
   64/54000 [..............................] - ETA: 39:34Traceback (most recent call last):
  File "F:\anaconda\envs\tensorflow1\lib\site-packages\IPython\core\interactiveshell.py", line 3331, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-2-d2317d03e1c1>", line 1, in <module>
    runfile('F:/Pycharm_projects/my_fun_project/Fake or real news/fake-or-real-news/bitcoin.py', wdir='F:/Pycharm_projects/my_fun_project/Fake or real news/fake-or-real-news')
  File "C:\Program Files\JetBrains\PyCharm Community Edition 2019.3.3\plugins\python-ce\helpers\pydev\_pydev_bundle\pydev_umd.py", line 197, in runfile
    pydev_imports.execfile(filename, global_vars, local_vars)  # execute the script
  File "C:\Program Files\JetBrains\PyCharm Community Edition 2019.3.3\plugins\python-ce\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile
    exec(compile(contents+"\n", file, 'exec'), glob, loc)
  File "F:/Pycharm_projects/my_fun_project/Fake or real news/fake-or-real-news/bitcoin.py", line 41, in <module>
    model.fit(x=x_train, y=y_train, batch_size=64, epochs=5, shuffle=True, validation_split=0.1)
  File "F:\anaconda\envs\tensorflow1\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 819, in fit
    use_multiprocessing=use_multiprocessing)
  File "F:\anaconda\envs\tensorflow1\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py", line 342, in fit
    total_epochs=epochs)
  File "F:\anaconda\envs\tensorflow1\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py", line 128, in run_one_epoch
    batch_outs = execution_function(iterator)
  File "F:\anaconda\envs\tensorflow1\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py", line 98, in execution_function
    distributed_function(input_fn))
  File "F:\anaconda\envs\tensorflow1\lib\site-packages\tensorflow_core\python\eager\def_function.py", line 568, in __call__
    result = self._call(*args, **kwds)
  File "F:\anaconda\envs\tensorflow1\lib\site-packages\tensorflow_core\python\eager\def_function.py", line 632, in _call
    return self._stateless_fn(*args, **kwds)
  File "F:\anaconda\envs\tensorflow1\lib\site-packages\tensorflow_core\python\eager\function.py", line 2363, in __call__
    return graph_function._filtered_call(args, kwargs)  # pylint: disable=protected-access
  File "F:\anaconda\envs\tensorflow1\lib\site-packages\tensorflow_core\python\eager\function.py", line 1611, in _filtered_call
    self.captured_inputs)
  File "F:\anaconda\envs\tensorflow1\lib\site-packages\tensorflow_core\python\eager\function.py", line 1692, in _call_flat
    ctx, args, cancellation_manager=cancellation_manager))
  File "F:\anaconda\envs\tensorflow1\lib\site-packages\tensorflow_core\python\eager\function.py", line 545, in call
    ctx=ctx)
  File "F:\anaconda\envs\tensorflow1\lib\site-packages\tensorflow_core\python\eager\execute.py", line 67, in quick_execute
    six.raise_from(core._status_to_exception(e.code, message), None)
  File "<string>", line 3, in raise_from
tensorflow.python.framework.errors_impl.InvalidArgumentError:  assertion failed: [Condition x == y did not hold element-wise:] [x (loss/output_1_loss/SparseSoftmaxCrossEntropyWithLogits/Shape_1:0) = ] [64 1] [y (loss/output_1_loss/SparseSoftmaxCrossEntropyWithLogits/strided_slice:0) = ] [64 14]
     [[node loss/output_1_loss/SparseSoftmaxCrossEntropyWithLogits/assert_equal_1/Assert/Assert (defined at F:/Pycharm_projects/my_fun_project/Fake or real news/fake-or-real-news/bitcoin.py:41) ]] [Op:__inference_distributed_function_2970]
Function call stack:
distributed_function

Answer 1

错误是因为你的output_shape和 label_shape不匹配。这是您创建的模型的架构:

.

如您所见，您的模型输出 (batch_size, 14, 16)但您提供的标签的形状为 (batch_size, 16) .

为了解决这个问题，请尝试添加 Flatten最后一层 Dense层。

代码:

model = Sequential()
model.add(tf.keras.layers.Dense(256, input_shape = (28,28)))
model.add(tf.keras.layers.Conv1D(kernel_size=4, strides=1, filters=4, activation="relu"))
model.add(tf.keras.layers.Conv1D(kernel_size=3, strides=1, activation="relu", filters=3))
model.add(tf.keras.layers.Dense(128, activation="relu"))
model.add(tf.keras.layers.Conv1D(kernel_size=2, filters=2, strides=1, activation="relu"))
model.add(tf.keras.layers.Conv1D(kernel_size=1, filters=1, strides=1, activation="relu"))
model.add(tf.keras.layers.Dense(64, activation="relu"))
model.add(tf.keras.layers.MaxPool1D(pool_size=2, strides=1))
model.add(tf.keras.layers.Dense(256, activation="relu"))
model.add(tf.keras.layers.Conv1D(kernel_size=4, filters=4, strides=1, activation="relu"))
model.add(tf.keras.layers.Conv1D(kernel_size=3, filters=3, strides=1, activation="relu"))
model.add(tf.keras.layers.MaxPool1D(pool_size=2, strides=1))
model.add(tf.keras.layers.Dropout(0.2))
model.add(tf.keras.layers.Dense(128, activation="relu"))
model.add(tf.keras.layers.Conv1D(kernel_size=2, filters=2, strides=1, activation="relu"))
model.add(tf.keras.layers.Conv1D(kernel_size=1, filters=1, strides=1, activation="relu"))
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(64, activation="relu"))
model.add(tf.keras.layers.Dense(16, activation="softmax"))

现在您的模型架构如下所示:

现在，您的模型具有匹配的形状并且可以毫无问题地进行训练。