CUDA_ERROR_LAUNCH_FAILED: unspecified launch failure

来源：7-10 LSTM文本分类与文本生成实战

jandy_chen

2020-02-07

## 双向双层的LSTM
bi_lstm_model = keras.models.Sequential([
    # 1. define matrix: [vocab_size, embedding_dim]
    # 2. [1,2,3,4..], max_length * embedding_dim
    # 3. batch_size * max_length * embedding_dim
    keras.layers.Embedding(vocab_size, embedding_dim,
                           input_length = max_length),
    keras.layers.Bidirectional(
        keras.layers.LSTM(
            units = 64, return_sequences = True)),
    keras.layers.Bidirectional(
        keras.layers.LSTM(
            units=64, return_sequences=False)),
    keras.layers.Dense(64, activation = 'relu'),
    keras.layers.Dense(1, activation='sigmoid'),
])

这个LSTM双层的，训练几个epoch，notebook报服务中断，后台显示出错如下图：（改为单层的时候正常运行通过）
图片描述