如何在Tensorflow中加載預訓練的LSTM模型權重

Question

我想在Tensorflow中實施具有預訓練權重的LSTM模型。這些重量可能來自Caffee或火炬。
我發現文件rnn_cell.py中有LSTM單元，例如rnn_cell.BasicLSTMCell和rnn_cell.MultiRNNCell。但是我怎樣才能加載這些LSTM單元的預訓練權重。

Answer 1

以下是加載預先訓練的Caffe模型的解決方案。請參閱this thread中討論中引用的full code here。

net_caffe = caffe.Net(prototxt, caffemodel, caffe.TEST) 
caffe_layers = {} 

for i, layer in enumerate(net_caffe.layers): 
    layer_name = net_caffe._layer_names[i] 
    caffe_layers[layer_name] = layer 

def caffe_weights(layer_name): 
    layer = caffe_layers[layer_name] 
    return layer.blobs[0].data 

def caffe_bias(layer_name): 
    layer = caffe_layers[layer_name] 
    return layer.blobs[1].data 

#tensorflow uses [filter_height, filter_width, in_channels, out_channels] 2-3-1-0 
#caffe uses [out_channels, in_channels, filter_height, filter_width] 0-1-2-3 
def caffe2tf_filter(name): 
    f = caffe_weights(name) 
    return f.transpose((2, 3, 1, 0)) 

class ModelFromCaffe(): 
    def get_conv_filter(self, name): 
     w = caffe2tf_filter(name) 
     return tf.constant(w, dtype=tf.float32, name="filter") 

    def get_bias(self, name): 
     b = caffe_bias(name) 
     return tf.constant(b, dtype=tf.float32, name="bias") 

    def get_fc_weight(self, name): 
     cw = caffe_weights(name) 
     if name == "fc6": 
      assert cw.shape == (4096, 25088) 
      cw = cw.reshape((4096, 512, 7, 7)) 
      cw = cw.transpose((2, 3, 1, 0)) 
      cw = cw.reshape(25088, 4096) 
     else: 
      cw = cw.transpose((1, 0)) 

     return tf.constant(cw, dtype=tf.float32, name="weight") 

images = tf.placeholder("float", [None, 224, 224, 3], name="images") 
m = ModelFromCaffe() 

with tf.Session() as sess: 
    sess.run(tf.initialize_all_variables()) 
    batch = cat.reshape((1, 224, 224, 3)) 
    out = sess.run([m.prob, m.relu1_1, m.pool5, m.fc6], feed_dict={ images: batch }) 
...