Pranit Puri's repositories
VQ-GAN
VQGAN and CLIP are actually two separate machine learning algorithms that can be used together to generate images based on a text prompt. VQGAN is a generative adversarial neural network that is good at generating images that look similar to others (but not from a prompt), and CLIP is another neural network that is able to determine how well a caption (or prompt) matches an image.
3D-Models-Clothes
3D Models of Shirts-Tshirts
Collage-Builder
It creates collage of the Dataset you provide.
Fingerprint-Recognition
Fingerprint Recognition
Full-Body-Detection
Full body Detection using MediaPipe and openCv
PlytoObject
This Program converts the .PLY files to .OBJ files.
Top-Interview-Questions-LeetCode
LeetCode
Background-Remover-Cv
Tool that can be used to remove background from a image.
Background-Scrap-File
Used for an entire dataset.
Color-Feature-Extraction
Color Feature Extraction using K-Mean. Depicting the Pie-Chart of the Color Composition.
Fast-Style-Transfer-Tf
Fast Style Transfer using Tensorflow and Pytorch
Style-Transfer-Vgg19
Style Transfer using Vgg19 and Pytorch
Facial-Expression-Recognition-VGG19
This model will help you to detect the facial expression from a Image and show the result in a form of Emoji