I can code for your computer vision problems using state of the art deep learning techniques in following frameworks Tensorflow, Keras, Pytorch and OpenCV using Python. I can address variety of problems including Object Detection, Recognition, Counting and Tracking, Image Segmentation (Semantic and Instance), Image/Video Captioning, Image Generation ,Machine reading comprehension, Human Pose estimation, Depth estimation and Activity recognition. Deep Learning models that I use are YOLOv3, SSD, Faster R-CNN, GANs, Mask R-CNN, SegNet, UNet, LSTM, Transformer, GPT3, and Custom models.