hi各位大佬好，我是菜鳥小明哥，在寫代碼中tf1的代碼很多都不能直接轉為tf2，需要替換為同樣功能的函式，因此本篇暫且統計遇到的幾個及使用方法，以備后用，
For Recommendation in Deep learning QQ Group 277356808
For deep learning QQ Second Group 629530787
I'm here waiting for you
不接受這個網頁的私聊/私信！！！
歡迎關注微信視頻號、快手：小明哥直播間
1-dropout這個已經提及不再贅述，
2-全連接dense/MLP也已論述，
3-卷積conv如下：1d示例，
提起卷積肯定要說起輸入資料的格式，有NCW和NWC兩種格式（舊的4個字母的已經廢棄），其實就是tf和torch的區別，分別為：就是首字母唄，
NWC：[batch, in_width, in_channels]
NCW：[batch, in_channels, in_width]tf1中tf.nn.conv1d
conv1d(value=None, filters=None, stride=None, padding=None, use_cudnn_on_gpu=None, data_fo
rmat=None, name=None, input=None, dilations=None)
Computes a 1-D convolution given 3-D input and filter tensors. (deprecated argument va
lues) (deprecated argument values)
tf1中tf.layers.conv1d
conv1d(inputs, filters, kernel_size, strides=1, padding='valid', data_format='channels_last', dilation_rate=1, activation=None, use_bias=True, kernel_initializer=None, bias_initializer=<tensorflow.python.ops.init_ops.Zeros object at 0x7fd5cbcc3650>, kernel_regularizer=None, bias_regularizer=None, activity_regularizer=None, kernel_constraint=None, bias_constraint=None, trainable=True, name=None, reuse=None)
tf2
class Conv1D(Conv)
| Conv1D(filters, kernel_size, strides=1, padding='valid', data_format='channels_last', dilation_rate=1, activation=None, use_bias=True, kernel_initializer='glorot_uniform', bias_initializer='zeros', kernel_regularizer=None, bias_regularizer=None, activity_regularizer=None, kernel_constraint=None, bias_constraint=None, **kwargs)
從上面的對比中發現tf1中第一個的缺少kernel_size，下面嘗試計算下：舉例如下
發現第一個需要指定padding的模式，否則出錯，
后兩個的out shape 是一樣的，但在tf1環境下報錯，真是夠了，tf2下無錯，
inputs=tf.random.normal((4,30,18))
>>> filter=16
>>> kernel_size=1
tf1中
out1=tf.layers.conv1d(inputs,filter,kernel_size)
/tensor_shape.py", line 193, in __init__
self._value = int(value)
TypeError: int() argument must be a string, a bytes-like object or a number, not 'type'
>>> conv=tf.compat.v2.keras.layers.Conv1D(filter,kernel_size)
>>> out2=conv(inputs)
self._value = int(value)
TypeError: int() argument must be a string, a bytes-like object or a number, not 'type'
tf2中
>>> out1=tf.compat.v1.layers.conv1d(inputs,filter,kernel_size)
>>> conv=tf.compat.v2.keras.layers.Conv1D(filter,kernel_size)
>>> out2=conv(inputs)
>>> out1.shape
TensorShape([4, 30, 16])
>>> out2.shape
TensorShape([4, 30, 16])
愿我們終有重逢之時，而你還記得我們曾經討論的話題，
4-數學計算,這種加上math即可
>>> tf.log
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
AttributeError: module 'tensorflow' has no attribute 'log'
>>> tf.math.log(2.78)
<tf.Tensor: shape=(), dtype=float32, numpy=1.0224509>轉載請註明出處，本文鏈接：https://www.uj5u.com/qita/379229.html
標籤：AI
上一篇：IMDB電影資料分析實踐
下一篇：將一個模式的值推入另一個模式