Валентин Сичкар

Design, Train & Test deep CNN for Image Classification: https://www.udemy.com/course/convolutional-neural-networks-for-image-classification

Content of the CNN Course
Section 1: Quick Win - Convolution inside-out
Section 2: Assemble datasets
Section 3: Modify datasets
Section 4: Preprocess datasets
Section 5: Design deep CNNs
Section 6: Train & Test CNNs
Section 7: Practice Test
Section 8: Augment datasets

Example of Image Classification


Concept Map of the CNN Course


Join the Course now!
https://www.udemy.com/course/convolutional-neural-networks-for-image-classification

Model #1 is built on pure 'numpy' and reached 0.68 Validation Accuracy.
Description of implementation with pure 'numpy' is available on GitHub here
Code implementation is available on Kaggle here

Model #1 has following architecture:
Conv -> ReLU -> Pooling -> Affine -> ReLU -> Affine -> Softmax

Initial Parameters	Description
Weights Initialization	HE Normal
Weights Update Policy	Adam
Activation Function	ReLU
Regularization	L2
Pooling	Max
Loss Function	Cross-entropy, Softmax

Hyperparameters	Description
Filters for ConvNet Layer	32
Size of the Filters	height=width=7
Params for ConvNet Layer	stride=1, pad=3
Params for Pooling Layer	stride=2, height=width=2
Dimension of Hidden Affine Layer	500 neurons
Regularization	1e-3

Feeding of Model #1 with Training Images is shown on the figure below:



Training process of Model #1 with 50 000 iterations is shown on the figure below:



Initialized Filters and Trained Filters for ConvNet Layer is shown on the figure below:



Training process of Filters for ConvNet Layer is shown on the figure below: