使用图像作为双向 LSTM 网络的输入

Question

我想知道在将图像作为双向 LSTM 的输入之前如何处理图像。每当我运行我的代码：

时，我总是会收到此错误

AttributeError: 'list' object has no attribute 'get_shape'

来自这一行：

outputs, _, _ = tf.nn.bidirectional_dynamic_rnn(lstm_fw_cell, lstm_bw_cell, x, dtype=tf.float32)

这是与问题相关的部分代码：

def bi_rnn(features, labels, mode):
    x = tf.unstack(features, num_inputs, 1)
    ... # cell initialization
    # Get lstm cell output
    try:
        outputs, _, _ = tf.nn.bidirectional_dynamic_rnn(lstm_fw_cell, lstm_bw_cell, x, dtype=tf.float32)

... 

def serving_input_fn():
    feature_placeholders = {
        'features': tf.placeholder(tf.float32, [None, num_inputs])
    }
    features = {
        key: tf.expand_dims(tensor, -1) for key, tensor in feature_placeholders.items()
    }
    features = tf.squeeze(features, axis=[2])
    return InputFnOps(features, None, feature_placeholders)

def read_dataset(img_paths, labels):
    def _input_fn():
        ... # reading image paths omitted
        image_files = tf.image.decode_png(image_files)
        image_files = tf.image.resize_images(image_files, [1024, 128])
        image_files = evaluate_images(image_files)
        ... # labels part omitted
        return tf.convert_to_tensor(np.array(image_files)), labels2
    return _input_fn

Answer 1

我几乎已经放弃了这个并且做了 something else work. It doesn't use the TFLearn features unlike this one. The recent one I'm working on has a problem which you can view 。

使用图像作为双向 LSTM 网络的输入

Using Images as Input to a Bidirectional LSTM Network

lstm

tensorflow