Archer阿茶

1、关于卷积网络的降维，挺多视频教程讲的不明不白，实战也是把一些隐藏点忽略带过，找到吴恩达老师的视频教程一看，很多细节的点都有详细提到，建议大家学完一门课程可以回看吴恩达老师的深度学习课程。在一个[nxn]7x7的图像数据，使用[fxf]3x3的filter或者kernel来扫描图像，假设conv2d的padding为p, 卷积步长stride s为2，那么其转换后的换算为[（n+2p-f）/...

官方链接：https://github.com/tensorflow/tensorflow/releasesMajor Features and Improvementstensorflow-2.2主要更新内容，如下：Replaced the scalar type for string tensors fromstd::stringtotensorflow::tstringw...

再进行RNN循环神经网络学习过程中发现一个奇怪的bug，错误日志如下： File "C:\Users\Jame_Peng\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\eager\execute.py", line 61, in quick_execute num_out...

Loading Keras modelsKeras models are trackable, so they can be saved to SavedModel. The object returned by tf.saved_model.load is not a Keras object (i.e. doesn't have .fit, .predict, etc. methods). A few attributes and functions are still available: .va