對(duì)張量切片的方式和numpy 一樣，如下

out1=outs[:,:100] out2=outs[:,100:]

下面是代碼demo

import keras.backend as K from tensorflow.keras.layers import concatenate from tensorflow.keras import Sequential,Model from tensorflow.keras.layers import Dense ,Concatenate,Input,BatchNormalizationdense_inputs1 = Input(shape=(1024, )) dense_inputs2 = Input(shape=(512, ))d1 = Dense(256, activation='relu')(dense_inputs1) d2 = Dense(256, activation='relu')(dense_inputs2)merge_inputs = concatenate([d1,d2],axis=1)flow_dense = Dense(256, activation='relu')(merge_inputs) flow_dense = BatchNormalization()( flow_dense)outs = Dense(100+1, activation='softmax')(flow_dense) print(outs)

原來(lái)的張量這是101維度的張量

Tensor("dense_11/Softmax:0", shape=(?, 101), dtype=float32)

101維度的張量已經(jīng)切割成100維和１維

out1=outs[:,:100] out2=outs[:,100:] print(out1) print(out2) Tensor("strided_slice_10:0", shape=(?, 100), dtype=float32) Tensor("strided_slice_11:0", shape=(?, 1), dtype=float32)

總結(jié)

以上是生活随笔為你收集整理的keras 张量切片的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問(wèn)題。

如果覺(jué)得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。