Trying to reuse LSTM weights in Keras from a model built in DyNet

Hi :wave:

I am currently trying to use weights from a model in dynet:

dynet model:
```
dy_model = dy.BiRNNBuilder(layers, dim_input, dim_hidden, model, dy.LSTMBuilder)
```

Keras model:
```
def multi_layer_birnn(input, layer_count, dim_hidden, params):
out = input
dim_hidden = int(dim_hidden / 2)
for li in range(layer_count):
layer_params = params[li]
fwparams = layer_params['fw']
bwparams = layer_params['bw']
forward_cell = layers.LSTM(
dim_hidden,
return_sequences=True,
unit_forget_bias=False,
kernel_initializer =keras.initializers.Constant(fwparams['W']),
recurrent_initializer=keras.initializers.Constant(fwparams['U']),
bias_initializer=keras.initializers.Constant(fwparams['b']),
)
forward_cell.trainable = False

backward_cell = layers.LSTM(
dim_hidden,
return_sequences=True,
unit_forget_bias=False,
kernel_initializer =keras.initializers.Constant(bwparams['W']),
recurrent_initializer=keras.initializers.Constant(bwparams['U']),
bias_initializer=keras.initializers.Constant(bwparams['b']),
go_backwards=True,
)
backward_cell.trainable = False
birnn = layers.Bidirectional(forward_cell, backward_layer=backward_cell)
birnn.trainable = False
out = birnn(out)
return out

ws_rnn = multi_layer_birnn(ws_input, LAYERS, DIM_HIDDEN, params['birnn'])
```

to get params from Dynet I do the following
```
rnn_layers = []
for layer in dy_model.builder_layers:
fworbw = []
for fwbw in layer:
(W, U, b) = fwbw.param_collection().parameters_list()
b = b.as_array()
W = W.as_array()
U = U.as_array()
fworbw.append({
'U': U,
'W': W,
'b': b,
})
rnn_layers.append({
'fw': fworbw[0],
'bw': fworbw[1],
})
params = { 'birnn: rnn_layers }
```

I've tested and made sure that the inputs to the lstm are completely identical, however I get different output between the two frameworks :(

Start from the shown Dynet parameter extraction and Keras Bidirectional LSTM construction, then compare gate ordering, tensor shapes, bias layout, and backward-sequence handling. Reproduce the mismatch with identical inputs and verify that the converted weights produce matching outputs, or document the remaining framework convention difference.

Written by the indexing model from the issue text.