TensorFlow 调用预训练好的模型—— Python 实现
2021-05-23 01:29
标签:过程 which pat http 路径 变量 sso success https 获取更多精彩,请关注「seniusen」! TensorFlow 调用预训练好的模型—— Python 实现 标签:过程 which pat http 路径 变量 sso success https 原文地址:https://www.cnblogs.com/seniusen/p/9736851.html1. 准备预训练好的模型
model_checkpoint_path: "/home/senius/python/c_python/test/model-40"
all_model_checkpoint_paths: "/home/senius/python/c_python/test/model-40"
2. 导入模型图、参数值和相关变量
import tensorflow as tf
import numpy as np
sess = tf.Session()
X = None # input
yhat = None # output
def load_model():
"""
Loading the pre-trained model and parameters.
"""
global X, yhat
modelpath = r‘/home/senius/python/c_python/test/‘
saver = tf.train.import_meta_graph(modelpath + ‘model-40.meta‘)
saver.restore(sess, tf.train.latest_checkpoint(modelpath))
graph = tf.get_default_graph()
X = graph.get_tensor_by_name("X:0")
yhat = graph.get_tensor_by_name("tanh:0")
print(‘Successfully load the pre-trained model!‘)
3. 运行前向传播过程得到预测值
def predict(txtdata):
"""
Convert data to Numpy array which has a shape of (-1, 41, 41, 41 3).
Test a single example.
Arg:
txtdata: Array in C.
Returns:
Three coordinates of a face normal.
"""
global X, yhat
data = np.array(txtdata)
data = data.reshape(-1, 41, 41, 41, 3)
output = sess.run(yhat, feed_dict={X: data}) # (-1, 3)
output = output.reshape(-1, 1)
ret = output.tolist()
return ret
4. 测试
load_model()
testdata = np.fromfile(‘/home/senius/python/c_python/test/04t30t00.npy‘, dtype=np.float32)
testdata = testdata.reshape(-1, 41, 41, 41, 3) # (150, 41, 41, 41, 3)
testdata = testdata[0:2, ...] # the first two examples
txtdata = testdata.tolist()
output = predict(txtdata)
print(output)
# [[-0.13345889747142792], [0.5858198404312134], [-0.7211828231811523],
# [-0.03778800368309021], [0.9978875517845154], [0.06522832065820694]]
下一篇:使用Java绘制验证码
文章标题:TensorFlow 调用预训练好的模型—— Python 实现
文章链接:http://soscw.com/essay/88067.html