Tutorial Keras

Follow the tutorials in the following orders

Keras.io Tutorial

Computer Vision Tutorials: https://keras.io/examples/vision/

1. Simple MNIST CNN

   • modified tutorial

     • source from github , run on colab

   • original tutorial

     • source from github , run on colab

2. Image classification from scratch

   • modified tutorial

     • source from github

   • original tutorial

     • source from github , run on colab

Pyimagesearch.com Tutorial

Get Started Tutorial

1. How to train and test your own dataset

Keras Model Zoo:

Collection of pretrained models: click here

• YOLOv3 in Keras

• SSD in Keras

YOLOv3 in Keras

Blog post

Source code by experiencor Huynh Ngoc Anh

Other Tutorials

A Start-to-Finish Guide to Building Deep Neural Networks in KerasMedium

Exercise

Image Recognition

1. Use AlexNet on MNIST

2. Use LeNet to train and recognize vehicles. Use Dataset of

3. Create your own convnet network for MNIST dataset. Compare the performance with tutorial output

Popular network architecture in Keras

Available models

Model	Size	Top-1 Accuracy	Top-5 Accuracy	Parameters	Depth
Xception	88 MB	0.790	0.945	22,910,480	126
VGG16	528 MB	0.713	0.901	138,357,544	23
VGG19	549 MB	0.713	0.900	143,667,240	26
ResNet50	98 MB	0.749	0.921	25,636,712	-
ResNet101	171 MB	0.764	0.928	44,707,176	-
ResNet152	232 MB	0.766	0.931	60,419,944	-
ResNet50V2	98 MB	0.760	0.930	25,613,800	-
ResNet101V2	171 MB	0.772	0.938	44,675,560	-
ResNet152V2	232 MB	0.780	0.942	60,380,648	-
InceptionV3	92 MB	0.779	0.937	23,851,784	159
InceptionResNetV2	215 MB	0.803	0.953	55,873,736	572
MobileNet	16 MB	0.704	0.895	4,253,864	88
MobileNetV2	14 MB	0.713	0.901	3,538,984	88
DenseNet121	33 MB	0.750	0.923	8,062,504	121
DenseNet169	57 MB	0.762	0.932	14,307,880	169
DenseNet201	80 MB	0.773	0.936	20,242,984	201
NASNetMobile	23 MB	0.744	0.919	5,326,716	-
NASNetLarge	343 MB	0.825	0.960	88,949,818	-
EfficientNetB0	29 MB	-	-	5,330,571	-
EfficientNetB1	31 MB	-	-	7,856,239	-
EfficientNetB2	36 MB	-	-	9,177,569	-
EfficientNetB3	48 MB	-	-	12,320,535	-
EfficientNetB4	75 MB	-	-	19,466,823	-
EfficientNetB5	118 MB	-	-	30,562,527	-
EfficientNetB6	166 MB	-	-	43,265,143	-
EfficientNetB7	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.