![](https://private-user-images.githubusercontent.com/111307883/305182143-02fa2040-0de4-4072-96a0-a2572d874cbd.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MjUxMTc5NDgsIm5iZiI6MTcyNTExNzY0OCwicGF0aCI6Ii8xMTEzMDc4ODMvMzA1MTgyMTQzLTAyZmEyMDQwLTBkZTQtNDA3Mi05NmEwLWEyNTcyZDg3NGNiZC5wbmc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjQwODMxJTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI0MDgzMVQxNTIwNDhaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT03YTU2NTdiYTk0NDYyNzVlN2FjMjZhNGMzM2Y1ZWYwMmQ1ZmFmZjY5M2UyMmQwMzc5ODkwMjhiNWU5ZWJjZjU2JlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCZhY3Rvcl9pZD0wJmtleV9pZD0wJnJlcG9faWQ9MCJ9.jrt4kaw95khdHiR_-h1lYErCg-wHyHCtrS3sy3iNA18)
The fashion industry is undergoing a dramatic transformation by adopting new computer vision and ML and deep learning techniques. We're going to use the Fashion MNIST data that contains images like dress, bags and shoes We want to build a model (based on deep learning & machine learning model) that look at an image and tell us what type of clothes. We can do target marketing to specific customer
Objective : build a classifier, build a kind of a deep learning network that can look at these images and can tell us the category of clothes
You can download the dataset at this address : Fashion MNIST Dataset
Our Dataset for fashion consists of 70.000 images (28x28 grayscale) with :
-
60.000 training
-
10.000 testing
In addition, we have at our disposal 10 target class :
t-shirt/top - trouser - pullover - dress - coat - sandal - shirt - sneaker - bag - ankle - boot
A greyscale image is a system of 256 tones with values ranging from 0-255, 0 represents black and 255 represents white. Numbers in-between represents gerys between black and white. Binary sistem use digits '0' and '1' chere '00000000' for black and '11111111' for white (8-bit image).
Binary value of '11111111' is equal to decimal value of '255'
Fashion dataset contains 28x28 greyscale image with values ranging from 0-255
'0' represents black and '255' represents white
Each image is represented by a row with 784 (i.e 28x28) values
-
The neuron collects signals from input channels named dendrites, processes information in its nucleus, and then generates an output in a long thin branch called the axon.
-
Human learning occurs adaptively by varying the bond strength between these neurons.
-
Convolutions use a kernel matrix to scan a given image and apply a filter to obtain a certain effect.
-
An image Kernel is a matrix used to apply effects such as blurring and sharpening.
-
Kernels are used in machine learning for feature extraction to select most important pixels of an image.
-
Convolution preserves the spatial relationship between pixels.
-
RELU layers are used to add non-linearity in the feature map
-
It also enhances the sparsity or how scattered the feature map is
-
Pooling or down sampling layers are placed after convolutional layers to reduce feature map dimensionality
-
This improves the computational efficiency while preserving the features
-
Pooling helps the model to generalize by avoiding overfitting. If one of the pixel is shifted, the pooled feature map will still be the same
-
Max pooling works by retaining the maximum feature response within a given sample size in a feature map