在GPU上运行的TensorFlow Word2Vec模型

在里面 this TensorFlow example tf.device('/cpu:0') :

batch_size = 128
embedding_size = 128  # Dimension of the embedding vector.
skip_window = 1  # How many words to consider left and right.
num_skips = 2  # How many times to reuse an input to generate a label.

# We pick a random validation set to sample nearest neighbors. Here we limit the
# validation samples to the words that have a low numeric ID, which by
# construction are also the most frequent. 
valid_size = 16  # Random set of words to evaluate similarity on.
valid_window = 100  # Only pick dev samples in the head of the distribution.
valid_examples = np.array(random.sample(range(valid_window), valid_size))
num_sampled = 64  # Number of negative examples to sample.

graph = tf.Graph()

with graph.as_default(), tf.device('/cpu:0'):
    # Input data.
    train_dataset = tf.placeholder(tf.int32, shape=[batch_size])
    train_labels = tf.placeholder(tf.int32, shape=[batch_size, 1])
    valid_dataset = tf.constant(valid_examples, dtype=tf.int32)

    # Variables.
    embeddings = tf.Variable(
        tf.random_uniform([vocabulary_size, embedding_size], -1.0, 1.0))
    softmax_weights = tf.Variable(
        tf.truncated_normal([vocabulary_size, embedding_size],
                            stddev=1.0 / math.sqrt(embedding_size)))
    softmax_biases = tf.Variable(tf.zeros([vocabulary_size]))

    # Model.
    # Look up embeddings for inputs.
    embed = tf.nn.embedding_lookup(embeddings, train_dataset)

    # Compute the softmax loss, using a sample of the negative labels each time.
    loss = tf.reduce_mean(
        tf.nn.sampled_softmax_loss(weights=softmax_weights,
                                   biases=softmax_biases, inputs=embed,
                                   labels=train_labels, num_sampled=num_sampled,
                                   num_classes=vocabulary_size))

    # Optimizer.
    # Note: The optimizer will optimize the softmax_weights AND the embeddings.
    # This is because the embeddings are defined as a variable quantity and the
    # optimizer's `minimize` method will by default modify all variable quantities 
    # that contribute to the tensor it is passed.
    # See docs on `tf.train.Optimizer.minimize()` for more details.
    optimizer = tf.train.AdagradOptimizer(1.0).minimize(loss)

    # Compute the similarity between minibatch examples and all embeddings.
    # We use the cosine distance:
    norm = tf.sqrt(tf.reduce_sum(tf.square(embeddings), 1, keep_dims=True))
    normalized_embeddings = embeddings / norm
    valid_embeddings = tf.nn.embedding_lookup(normalized_embeddings, valid_dataset)
    similarity = tf.matmul(valid_embeddings, tf.transpose(normalized_embeddings))

尝试切换到GPU时,会引发以下异常:

无效argumenterror

我想知道为什么提供的图形不能在GPU上计算?这是因为 tf.int32 类型或者我应该切换到另一个优化器?换句话说,有什么方法可以在GPU上处理Word2Vec模型吗?(无类型铸造)。

根据Akshay Agrawal的建议,以下是原始代码的更新片段,以实现所需的结果:

with graph.as_default(), tf.device('/gpu:0'):
    # Input data.
    train_dataset = tf.placeholder(tf.int32, shape=[batch_size])
    train_labels = tf.placeholder(tf.int32, shape=[batch_size, 1])
    valid_dataset = tf.constant(valid_examples, dtype=tf.int32)

    embeddings = tf.Variable(
        tf.random_uniform([vocabulary_size, embedding_size], -1.0, 1.0))
    softmax_weights = tf.Variable(
        tf.truncated_normal([vocabulary_size, embedding_size],
                            stddev=1.0 / math.sqrt(embedding_size)))
    softmax_biases = tf.Variable(tf.zeros([vocabulary_size]))    
    embed = tf.nn.embedding_lookup(embeddings, train_dataset)

    with tf.device('/cpu:0'):
        loss = tf.reduce_mean(
            tf.nn.sampled_softmax_loss(weights=softmax_weights,
                                       biases=softmax_biases,
                                       inputs=embed,
                                       labels=train_labels,
                                       num_sampled=num_sampled,
                                       num_classes=vocabulary_size))

    optimizer = tf.train.AdamOptimizer(0.001).minimize(loss)

    norm = tf.sqrt(tf.reduce_sum(tf.square(embeddings), 1, keep_dims=True))
    normalized_embeddings = embeddings / norm
    valid_embeddings = tf.nn.embedding_lookup(normalized_embeddings, valid_dataset)
    similarity = tf.matmul(valid_embeddings, tf.transpose(normalized_embeddings))