TensorFlow2 学习笔记

import numpy as np

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

model = Sequential()

model.add(Dense(64,activation= 'relu',input_shape = (784,)))
model.add(Dense(10,activation='softmax'))

from tensorflow.keras.layers import Dense,Flatten,Softmax

model = Sequential()

model.add(Flatten(input_shape=(28,28)))
model.add(Dense(16,activation='relu',name='layer_1'))
model.add(Dense(16,activation='relu'))
model.add(Dense(10))
model.add(Softmax())

model.weights

[<tf.Variable 'layer_1/kernel:0' shape=(784, 16) dtype=float32, numpy=
 array([[ 0.01290578,  0.07445015,  0.01681935, ...,  0.04626302,
          0.01588257, -0.01308318],
        [-0.0527299 , -0.07710216,  0.07464638, ...,  0.0087358 ,
         -0.02961487, -0.05955961],
        [ 0.03564721, -0.08287186, -0.03924981, ..., -0.0771492 ,
         -0.01618949, -0.05667122],
        ...,
        [ 0.05695684, -0.03964275, -0.0828326 , ...,  0.04255903,
          0.07647406, -0.07485285],
        [-0.0596628 , -0.06039616,  0.01491483, ..., -0.06700376,
         -0.04544031,  0.02588803],
        [-0.0542443 ,  0.04723233, -0.0512512 , ...,  0.05871357,
          0.00494871,  0.00856258]], dtype=float32)>,
 <tf.Variable 'layer_1/bias:0' shape=(16,) dtype=float32, numpy=
 array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.],
       dtype=float32)>,
 <tf.Variable 'dense_2/kernel:0' shape=(16, 16) dtype=float32, numpy=
 array([[ 3.40442985e-01, -4.17145699e-01, -3.55908453e-01,
          5.62509298e-02,  4.30662185e-01, -2.74808615e-01,
          3.66872460e-01, -3.51692528e-01, -1.94020331e-01,
         -2.64424592e-01, -3.09619218e-01, -3.71832252e-02,
         -2.10865408e-01,  5.35627902e-02,  3.65656346e-01,
         -2.95218408e-01],
        [ 9.27143395e-02, -3.74022126e-01,  1.87536269e-01,
          1.70864791e-01,  2.35066026e-01,  6.93340003e-02,
         -2.57344306e-01, -2.92516887e-01,  3.15936655e-01,
         -1.14047825e-01,  8.96017253e-02, -2.54236758e-02,
          3.05450171e-01,  2.01215446e-02, -1.91974759e-01,
         -1.95948616e-01],
        [-1.88459083e-01,  1.10159487e-01, -4.29021925e-01,
          7.55192339e-02, -3.92421991e-01,  4.13672775e-01,
          8.35732520e-02, -1.30163729e-02, -2.17564017e-01,
         -2.04560027e-01, -2.11227536e-02, -1.98445335e-01,
         -1.75059170e-01, -3.59995067e-02, -1.48799598e-01,
         -3.02458525e-01],
        [-2.93337405e-01,  4.23404187e-01,  9.23266113e-02,
         -4.59597111e-02, -7.17966557e-02,  2.40310818e-01,
          2.35053897e-03,  6.20829463e-02,  1.63255244e-01,
          2.99993902e-01,  2.19102770e-01,  3.32830042e-01,
          2.87256986e-01,  2.86558360e-01, -3.94982815e-01,
         -1.73235893e-01],