Xinwei He

pointnet2.pytorch. Python

seq2seq-1. Sequence to Sequence Learning Model

HZAU_UnderGraduateThesis_Template. TeX

mvcnn.torch. Implementation of Multi-view CNN in torch

image_caption_with_semantic_attenion. image caption with semantic attention

cvpr_2018_TCL.pytorch. Python

visual-concepts-2. Jupyter Notebook

pytorch_projects_misc. Python

lidar_based_lane_detection_projects. Python

text2shape.pytorch. This is the implementation of text2shape in pytorch

BaiduImageCrawler2. Python

deep_residual_networks_cifar. HTML

bag2pcd_ros. extracting specific topic of point clouds from rosbag into pcd.

code_pool_for_for_my_own_use. Vim Script

train_minist_with_multi_GPU. Lua

VAND-APRIL-GAN-v3. Python

openNMT.pytorch. factored from https://github.com/OpenNMT/OpenNMT-py for details

IBM_seq2seq.py3. see https://github.com/IBM/pytorch-seq2seq for details

PCAT_open_source_v2. It supports displaying the front images (.jpg) in rviz in ROS, and one can modify rviz_cloud_annotation_plugin.h to support other image formats.

coco-caption-w-spice-py3. coco-caption-w-spice-py3 is for evaluating coco captioning results with spice metrics. support python3

utils_for_3d_research. MATLAB

features_analysis. Implementation of the approach described in "Understanding deep features with computer-generated imagery" , M. Aubry and B. Russell, ICCV, 2015

caffe. Caffe: a fast open framework for deep learning.