PyTorch与Tensorflow中LSTM的不同输出

我正在尝试将Tensorflow（1.15）模型转换为PyTorch模型。因为我得到了非常不同的损耗值，所以我尝试比较相同输入的前向传递中LSTM的输出。LSTM的声明和初始化如下所示：

Tensorflow代码

rnn_cell_video_fw = tf.contrib.rnn.LSTMCell(
            num_units=self.options['rnn_size'],
            state_is_tuple=True, 
            initializer=tf.orthogonal_initializer()
        )

rnn_cell_video_fw = tf.contrib.rnn.DropoutWrapper(
            rnn_cell_video_fw,
            input_keep_prob=1.0 - rnn_drop,
            output_keep_prob=1.0 - rnn_drop 
        )

sequence_length = tf.expand_dims(tf.shape(video_feat_fw)[1], axis=0)
initial_state = rnn_cell_video_fw.zero_state(batch_size=batch_size, dtype=tf.float32)

rnn_outputs_fw, _ = tf.nn.dynamic_rnn(
                    cell=rnn_cell_video_fw, 
                    inputs=video_feat_fw, 
                    sequence_length=sequence_length, 
                    initial_state=initial_state,
                    dtype=tf.float32
                )

self.rnn_video_fw = nn.LSTM(self.options['video_feat_dim'], self.options['rnn_size'], dropout = self.options['rnn_drop'])

rnn_outputs_fw, _ = self.rnn_video_fw(video_feat_fw)

PyTorch代码

rnn_cell_video_fw = tf.contrib.rnn.LSTMCell(
            num_units=self.options['rnn_size'],
            state_is_tuple=True, 
            initializer=tf.orthogonal_initializer()
        )

rnn_cell_video_fw = tf.contrib.rnn.DropoutWrapper(
            rnn_cell_video_fw,
            input_keep_prob=1.0 - rnn_drop,
            output_keep_prob=1.0 - rnn_drop 
        )

sequence_length = tf.expand_dims(tf.shape(video_feat_fw)[1], axis=0)
initial_state = rnn_cell_video_fw.zero_state(batch_size=batch_size, dtype=tf.float32)

rnn_outputs_fw, _ = tf.nn.dynamic_rnn(
                    cell=rnn_cell_video_fw, 
                    inputs=video_feat_fw, 
                    sequence_length=sequence_length, 
                    initial_state=initial_state,
                    dtype=tf.float32
                )

self.rnn_video_fw = nn.LSTM(self.options['video_feat_dim'], self.options['rnn_size'], dropout = self.options['rnn_drop'])

rnn_outputs_fw, _ = self.rnn_video_fw(video_feat_fw)

在train.py中初始化LSTM

def init_weight(m):
        if type(m) in [nn.LSTM]:
            for param in m.parameters():
                    nn.init.orthogonal_(m.weight_hh_l0)
                    nn.init.orthogonal_(m.weight_ih_l0)

每个数据项的情况都差不多，我的PyTorch模型没有收敛。我对输出LSTM差异的怀疑是正确的吗？如果是的话，我错在哪里

---

如果还需要其他功能，请告诉我。

Pytorch在RNN模块上使用

time，batch，others

，而不是使用

batch，somthing，others

，这可能是原因。是的，我也考虑了这一点，并相应地更改了形状，但这也没有帮助：(