Computer vision tasks with keras and Tensorflow
This repo contains diverse computer vision tasks with Keras and Tensorflow.
-
Where the goal is to assign one or more labels to an image. It may be either single-label classification (an image can only be in one category, excluding the others), or multi-label classification (tagging all categories that an image belongs to).
-
Where the goal is to “segment” or “partition” an image into different areas, with each area usually representing a category.
-
Where the goal is to draw rectangles (called bounding boxes) around objects of interest in an image, and associate each rectangle with a class. A self-driving car could use an object-detection model to monitor cars, pedestri- ans, and signs in view of its cameras, for instance.
-
Transfer Learning on the cats_vs_dogs dataset with VGG16 architechture from keras
An exploratory walktrought of Computer Vision with pretrained models on the Ctas vs Dog Dataset
-
Image segmentation on the Oxford Pets Dataset
An exploratory walktrought of Image Segmentation with complex Convolutional models on the oxford pets dataset
Original Image and Segmented result
-
Image classification on the oxford_flowers102 dataset
Image classification on the oxford_flowers102 dataset with mobinetV2 model
References :