TensorFlow入门学习教程

[博观风向标]

课程名称	适应人群
TensorFlow入门学习教程	所有人

深度学习框架TensorFlow视频培训课程概况：涉及TensorFlow的安装、基本语法、TensorFlow的使用、训练、回归模型、使用TensorFlow构建神经网络，线性回归、Mnist数据集、逻辑回归、卷积神经网络、循环神经网络、项目实战等。

[丑八袁]

给的课件下载内容和讲的代码不一致。这是怎么回事啊？？？能否认真点。

[丑八袁]

给的课件下载内容和讲的代码不一致。这是怎么回事啊？？？能否认真点。

[强子rojon]

我怀疑老师的课程是否是发布在csdn,这里是不是只是复制了一份，从来不见回复

[强子rojon]

我怀疑老师的课程是否是发布在csdn,这里是不是只是复制了一份，从来不见回复

[yurikudy]

课件里的cnn_train这个文件呢，最重要的东西没有

[yurikudy]

课件里的cnn_train这个文件呢，最重要的东西没有

[念旧人丶]

还成吧 有些小细节可以在细致一点，倒是能百度的到，所以无伤大雅，整体不错

[不会]

老师，请问testData怎么写？

[博观风向标]

@不会 我更新下testData内容，上传到课程附件内

[不会]

老师，请问testData怎么写？

[博观风向标]

@llllllln 我更新下testData内容，上传到课程附件内

[llllllln]

testData可以提供一下包吗？ 代码跑不了啊

[博观风向标]

@llllllln 谢谢

[llllllln]

看到最后一章了，代码在课件里有链接，自己也手动实现了，对于新手小白非常友好，推荐。

[博观风向标]

@forzhutong 在最后一章。

[forzhutong]

代码在哪里下载呢，找不到代码呀

[博观风向标]

各位同学们，课件在最后一章节上。

[博观风向标]

@forzhutong 【验证码识别的代码实现】目录的最右边有个【课件下载】。如果您没找到，可以联系下学院客服，看看是不是显示除出了问题。

[forzhutong]

最后一章只有两个视频啊，没有代码下载呀

[博观风向标]

@虽然发了这么多c++作业但是考试只有61 已私信回复您

[虽然发了这么多c++作业但是考试只有61]

老师，我用jupyter跑线性回归代码时出现如下错误，要怎么解决呀 AttributeError Traceback (most recent call last) in () 42 # define the number of training iteration 43 optimizer = tf.train.GradientDescentOptimizer(0.5) ---> 44 train = optimizer.minimize(loss) 45 46 #epoch = ... C:\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\training\optimizer.py in minimize(self, loss, global_step, var_list, gate_gradients, aggregation_method, colocate_gra

[虽然发了这么多c++作业但是考试只有61]

AttributeError Traceback (most recent call last) in () 42 # define the number of training iteration 43 optimizer = tf.train.GradientDescentOptimizer(0.5) ---> 44 train = optimizer.minimize(loss) 45 46 #epoch = ... C:\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\training\optimizer.py in minimize(self, loss, global_step, var_list, gate_gradients, aggregation_method, colocate_gradients_with_ops, name, grad_loss)

[Sean（半沢直樹）]

在跑RNN的代码的时候报错。报错信息为：Attempt to have a second RNNCell use the weights of a variable scope that already has weights: 'rnn/basic_lstm_cell'; and the cell was not constructed as BasicLSTMCell(..., reuse=True). To share the weights of an RNNCell, simply reuse it in your second calculation, or create a new one with the argument reuse=True. 在讲代码修改添加scope以后，问题可以解决，但scope每次只能又一次就要换值，如：outputs,states = rnn.static_rnn(lstm_cell,x,dtype=tf.float32,scope='b')

[Sean（半沢直樹）]

在跑RNN的代码的时候报错。报错信息为：Attempt to have a second RNNCell use the weights of a variable scope that already has weights: 'rnn/basic_lstm_cell'; and the cell was not constructed as BasicLSTMCell(..., reuse=True). To share the weights of an RNNCell, simply reuse it in your second calculation, or create a new one with the argument reuse=True. 在讲代码修改添加scope以后，问题可以解决，但scope每次只能又一次就要换值，如：outputs,states = rnn.static_rnn(lstm_cell,x,dtype=tf.float32,scope='b')

[Sean（半沢直樹）]

报错信息为：Attempt to have a second RNNCell use the weights of a variable scope that already has weights: 'rnn/basic_lstm_cell'; and the cell was not constructed as BasicLSTMCell(..., reuse=True). To share the weights of an RNNCell, simply reuse it in your second calculation, or create a new one with the argument reuse=True. 在讲代码修改添加scope以后，问题可以解决，但scope每次只能又一次就要换值，如：outputs,states = rnn.static_rnn(lstm_cell,x,dtype=tf.float32,scope='b')

[昨日星辰。]

AttributeError: module 'tensorflow' has no attribute 'Session'