Eddie (Xingyu) Jin's repositories
sequential_model_pytorch_rnn_1dcnn
Sequential data using RNN (LSTM, GRU, etc) CNN and RCNN. Adaptable to variable length input sequence.
Skeleton-based-cyclist-hand-signal-and-attention-recognition
Spatial Temporal Graph Convolutional Neural Networks: Recognise hand signals such as to turn left, to turn right and to stop; Identify whether the cyclist notices the vehicles behind or beside (OpenPose + Kinetics + NTU RGB+D )
DeepView3D
Viewpoint-based 3D reconstruction network (First Place of IBM Prize for Machine Learning @ University of Edinburgh)
Object-Detection-and-Action-Recognition-for-Driverless-Vehicles
Object Detection on traffic scenario and Action Recognition (for driverless vehicles) YOLOv3
Two-view-3D-construction
Two-view 3D construction via 2.5D sketches
anlp_assignment1
Assignment1 of Accelerated Natural Language Processing at the University of Edinburgh
anlp_assignment3
Assignment 3 of Accelerated Natural Language Precessing
Deep-Learning-Practical-Assignment-1
Implement CNN packages from scratch using python
mlpractical
Machine Learning Practical course repository
pytorch-image-models
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, DPN, CSPNet, and more
amazon-sagemaker-examples
Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker.
charades-algorithms
Activity Recognition Algorithms for the Charades Dataset
DeepLearningPractical_Assignment2
Implement CNN packages including Conv Layer (fprop, bprop, grads_wrt_params) with scipy.signal.convolve2d and Max Pooling using python; Exploring context in convolutional networks: Dilation, Striding, Pooling
examples
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
mmaction2
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
nmt-tips
A tutorial about neural machine translation including tips on building practical systems
nmt_toolkit
Materials for the second assignment of INFR 11157.
pix3d
Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling
super-events-cvpr18
Code for our CVPR 2018 paper "Learning Latent Super-Events to Detect Multiple Activities in Videos"
TensorFlow-and-DeepLearning-Tutorial
TensorFlow & Deep Learning Tutorial
Utilisation_Review_GPT4
GPT4 | LLM | Medical Report | Utilisation Review
vision
Datasets, Transforms and Models specific to Computer Vision