I will build computer vision models for segmentation and generation
I am a Machine Learning and Computer Vision enthusiast with expertise in image classification, segmentation, object detection, depth estimation, and image generation. My gig offers three packages: the Basic package covers quick image classification using pretrained models, the Standard package handles object detection using YOLO and image segmentation on custom datasets, and the Premium package is for advanced tasks like GAN-based image generation, depth estimation, and image captioning. I've worked on projects like grayscale to color image conversion using DCGANs (Pix2Pix), semantic and binary segmentation on the IDD dataset using DeepLab, low-light image enhancement with Zero-DCE, visual question answering using Q-Former, and fine-tuning BLIP-2 for remote sensing image captioning. I work with frameworks like PyTorch, TensorFlow, Keras, NumPy, and scikit-learn to deliver high-quality, custom computer vision solutions tailored to your needs.
Visit Gig