Tutorial Keras
Last updated
Was this helpful?
Last updated
Was this helpful?
Follow the tutorials in the following orders
Simple MNIST CNN
modified tutorial
,
original tutorial
,
Image classification from scratch
modified tutorial
original tutorial
,
Use AlexNet on MNIST
Use LeNet to train and recognize vehicles. Use Dataset of
Create your own convnet network for MNIST dataset. Compare the performance with tutorial output
88 MB
0.790
0.945
22,910,480
126
528 MB
0.713
0.901
138,357,544
23
549 MB
0.713
0.900
143,667,240
26
98 MB
0.749
0.921
25,636,712
-
171 MB
0.764
0.928
44,707,176
-
232 MB
0.766
0.931
60,419,944
-
98 MB
0.760
0.930
25,613,800
-
171 MB
0.772
0.938
44,675,560
-
232 MB
0.780
0.942
60,380,648
-
92 MB
0.779
0.937
23,851,784
159
215 MB
0.803
0.953
55,873,736
572
16 MB
0.704
0.895
4,253,864
88
14 MB
0.713
0.901
3,538,984
88
33 MB
0.750
0.923
8,062,504
121
57 MB
0.762
0.932
14,307,880
169
80 MB
0.773
0.936
20,242,984
201
23 MB
0.744
0.919
5,326,716
-
343 MB
0.825
0.960
88,949,818
-
29 MB
-
-
5,330,571
-
31 MB
-
-
7,856,239
-
36 MB
-
-
9,177,569
-
48 MB
-
-
12,320,535
-
75 MB
-
-
19,466,823
-
118 MB
-
-
30,562,527
-
166 MB
-
-
43,265,143
-
256 MB
-
-
66,658,687
-
The top-1 and top-5 accuracy refers to the model's performance on the ImageNet validation dataset.
Depth refers to the topological depth of the network. This includes activation layers, batch normalization layers etc.
Source code by
