python读取.caffemodel文件

最新推荐文章于 2020-10-16 22:03:48 发布

黄鑫huangxin

最新推荐文章于 2020-10-16 22:03:48 发布

阅读量3k

点赞数

分类专栏： caffe

本文链接：https://blog.csdn.net/qq_33373858/article/details/83188768

版权

本文介绍如何使用Python读取并解析Caffe框架的.caffemodel文件，以获取预训练模型的参数和结构信息。

摘要由CSDN通过智能技术生成

想读取预训练好的.caffemodel文件的信息，了解模型参数和结构

import caffe.proto.caffe_pb2 as caffe_pb2
caffemodel_filename = 'resnet101_faster_rcnn_final.caffemodel'
model = caffe_pb2.NetParameter()
 
f=open(caffemodel_filename, 'rb')
model.ParseFromString(f.read())
f.close()
 
layers = model.layer
print 'name: "%s"'%model.name
layer_id=-1
for layer in layers:
    layer_id = layer_id + 1
    print 'layer {'
    print '  name: "%s"'%layer.name
    print '  type: "%s"'%layer.type
 
    
    tops = layer.top
    for top in tops:
        print '  top: "%s"'%top
    
    bottoms = layer.bottom
    for bottom in bottoms:
        print '  bottom: "%s"'%bottom
    
    if len(layer.include)>0:
        print '  include {'
        includes = layer.include
        phase_mapper={
            '0': &