Using Convolutional neural network to classify fashion images This model starts from reading images as pixels, process the images in order to prepare it to be injected to the CNN model. The CNN model contains convolutional layer as kernel or features detectors. At the begining we use 32 kernels with dimentions 3*3, then to imporve the model we use 64 kernels Moreover, we then use max pooling to preserve the most importance features. Then Flatten the features to be injected into the dense layers
-
Notifications
You must be signed in to change notification settings - Fork 0
petersamoaa/Fashion-image-labeling-
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Using Convolutional neural network to classify fashion images
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published