将tensorflow的ckpt模型存储为npy的实例

时间:2021-05-22

实例如下所示:

#coding=gbkimport numpy as npimport tensorflow as tffrom tensorflow.python import pywrap_tensorflowcheckpoint_path='model.ckpt-5000'#your ckpt pathreader=pywrap_tensorflow.NewCheckpointReader(checkpoint_path)var_to_shape_map=reader.get_variable_to_shape_map()alexnet={}alexnet_layer = ['conv1','conv2','conv3','conv4','conv5','fc6','fc7','fc8']add_info = ['weights','biases']alexnet={'conv1':[[],[]],'conv2':[[],[]],'conv3':[[],[]],'conv4':[[],[]],'conv5':[[],[]],'fc6':[[],[]],'fc7':[[],[]],'fc8':[[],[]]}for key in var_to_shape_map: #print ("tensor_name",key) str_name = key # 因为模型使用Adam算法优化的,在生成的ckpt中,有Adam后缀的tensor if str_name.find('Adam') > -1: continue print('tensor_name:' , str_name) if str_name.find('/') > -1: names = str_name.split('/') # first layer name and weight, bias layer_name = names[0] layer_add_info = names[1] else: layer_name = str_name layer_add_info = None if layer_add_info == 'weights': alexnet[layer_name][0]=reader.get_tensor(key) elif layer_add_info == 'biases': alexnet[layer_name][1] = reader.get_tensor(key) else: alexnet[layer_name] = reader.get_tensor(key)# save npynp.save('alexnet_pointing04.npy',alexnet)print('save npy over...')#print(alexnet['conv1'][0].shape)#print(alexnet['conv1'][1].shape)

以上这篇将tensorflow的ckpt模型存储为npy的实例就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持。

声明:本页内容来源网络,仅供用户参考;我单位不保证亦不表示资料全面及准确无误,也不保证亦不表示这些资料为最新信息,如因任何原因,本网内容或者用户因倚赖本网内容造成任何损失或损害,我单位将不会负任何法律责任。如涉及版权问题,请提交至online#300.cn邮箱联系删除。

相关文章