python – 如何在Tensorflow中加载预训练的LSTM模型权重

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,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,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((2,0))
            cw = cw.reshape(25088,4096)
        else:
            cw = cw.transpose((1,0))

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

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

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