Pinned Repositories
amsword.github.io
caffe-parallel
parallel the training of caffe in deep learning
CMC
pytorch implementation of "Contrastive Multiview Coding", "Momentum Contrast for Unsupervised Visual Representation Learning", and "Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination"
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
gkmeans
an implementation of group k-means (including optimized Cartesian k-means)
maskrcnn-benchmark
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
od
An implementation of the algorithms in the paper, entitled 'Optimized Distances for Binary Code Ranking'.
pytorch-image-models
PyTorch image models, scripts, pretrained weights -- (SE)ResNet/ResNeXT, DPN, EfficientNet, MixNet, MobileNet-V3/V2, MNASNet, Single-Path NAS, FBNet, and more
setup
ViLT
Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"
amsword's Repositories
amsword/ViLT
Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"
amsword/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
amsword/maskrcnn-benchmark
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
amsword/pytorch-image-models
PyTorch image models, scripts, pretrained weights -- (SE)ResNet/ResNeXT, DPN, EfficientNet, MixNet, MobileNet-V3/V2, MNASNet, Single-Path NAS, FBNet, and more
amsword/setup
amsword/amsword.github.io
amsword/CMC
pytorch implementation of "Contrastive Multiview Coding", "Momentum Contrast for Unsupervised Visual Representation Learning", and "Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination"
amsword/image_text_contrastive
image-text contrastive loss implementation
amsword/AutoAugment
Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow
amsword/azfuse
A lightweight blobfuse-like python tool with the data transfer through azcopy
amsword/BBox-Label-Tool
A simple tool for labeling object bounding boxes in images
amsword/caffe-1
Caffe: a fast open framework for deep learning.
amsword/clean-fid
PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]
amsword/cocoapi
COCO API - Dataset @ http://cocodataset.org/
amsword/DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.
amsword/detectron2
Detectron2 is FAIR's next-generation research platform for object detection and segmentation.
amsword/FCOS
FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)
amsword/flash-attention
Fast and memory-efficient exact attention
amsword/fvcore
Collection of common code that's shared among different research projects in FAIR computer vision team.
amsword/gossipnet
Non-maximum suppression for object detection in a neural network
amsword/hnms
Hashing-based Non-Maximum Suppression
amsword/mmcv
Open MMLab Computer Vision Foundation
amsword/mmdetection
Open MMLab Detection Toolbox with PyTorch
amsword/nvimconfig
Personal Neovim configuration
amsword/pycocoevalcap
Python 3 support for the MS COCO caption evaluation tools
amsword/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
amsword/pytorch-OpCounter
Count the FLOPs of your PyTorch model.
amsword/qdv
amsword/scaleapex
Fairscale + Apex
amsword/vim-snippets
vim-snipmate default snippets (Previously snipmate-snippets)