0

我为 deepspeech2 构建了一个模型，并使用 tpu 在 colab 上运行。我可以使用 gpu 在 colab 上运行它，但代码相同但 tpu。我得到了这样的磨损：

ValueError: in user code:

File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 878, in train_function  *
    return step_function(self, iterator)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 867, in step_function  **
    outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 860, in run_step  **
    outputs = model.train_step(data)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 808, in train_step
    y_pred = self(x, training=True)
File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 67, in error_handler
    raise e.with_traceback(filtered_tb) from None
File "/usr/local/lib/python3.7/dist-packages/keras/backend.py", line 4525, in rnn
    max_iterations = tf.reduce_max(input_length)

ValueError: Exception encountered when calling layer "forward_gru_1" (type GRU).

None values not supported.

Call arguments received:
  • inputs=tf.Tensor(shape=(None, None, 1568), dtype=float32)
  • mask=None
  • training=True
  • initial_state=None

我尝试修复差异 batch_size 但它不起作用。实际上，使用 gpu 在 colab 上运行时我没有同样的问题。这是我的模型构建的代码：

def build_model(input_dim, output_dim, rnn_layers=5, rnn_units=128):
    input_spectrogram = layers.Input((None, input_dim), name="input")
    x = layers.Reshape((-1, input_dim, 1), name="expand_dim")(input_spectrogram)
    # Convolution layer 1
    x = layers.Conv2D(
        filters=32,
        kernel_size=[11, 41],
        strides=[2, 2],
        padding="same",
        use_bias=False,
        name="conv_1",
    )(x)
    x = layers.BatchNormalization(name="conv_1_bn")(x)
    x = layers.ReLU(name="conv_1_relu")(x)
    # Convolution layer 2
    x = layers.Conv2D(
        filters=32,
        kernel_size=[11, 21],
        strides=[1, 2],
        padding="same",
        use_bias=False,
        name="conv_2",
    )(x)
    x = layers.BatchNormalization(name="conv_2_bn")(x)
    x = layers.ReLU(name="conv_2_relu")(x)
    # Reshape the resulted volume to feed the RNNs layers
    x = layers.Reshape((-1, x.shape[-2] * x.shape[-1]))(x)
    # RNN layers
    for i in range(1, rnn_layers + 1):
        recurrent = layers.GRU(
            units=rnn_units,
            activation="tanh",
            recurrent_activation="sigmoid",
            use_bias=True,
            return_sequences=True,
            reset_after=True,
            name=f"gru_{i}",
        )
        x = layers.Bidirectional(
            recurrent, name=f"bidirectional_{i}", merge_mode="concat"
        )(x)
        if i < rnn_layers:
            x = layers.Dropout(rate=0.5)(x)
    # Dense layer
    x = layers.Dense(units=rnn_units * 2, name="dense_1")(x)
    x = layers.ReLU(name="dense_1_relu")(x)
    x = layers.Dropout(rate=0.5)(x)
    # Classification layer
    output = layers.Dense(units=output_dim + 1, activation="softmax")(x)
4

0 回答 0