图像分类-VGG

Very Deep Convolutional Networks for Large-Scale Image Recognition

图像分类-AlexNet

ImageNet Classification with Deep Convolutional Neural Networks

图像分类-ResNet

Deep Residual Learning for Image Recognition

图像分类-MobileNetV2

MobileNetV2: Inverted Residuals and Linear Bottlenecks

图像分类-MobilenetV3

图像分类-ShuffleNetV2

ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

图像分类-InceptionV3

Rethinking the Inception Architecture for Computer Vision

图像分类-ResNext50_32x4d

Aggregated Residual Transformations for Deep Neural Networks

图像分类-RepVGG

RepVGG: Making VGG-style ConvNets Great Again

图像分类-LeNet

Gradient-based learning applied to document recognition

图像分类-PoseNet

PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization

图像分类-ReID

图像分类-Ghostnet

 GhostNet: More Features from Cheap Operations

图像分类-FaceNet

FaceNet: A Unified Embedding for Face Recognition and Clustering

图像分类-InsightFace

ArcFace: Additive Angular Margin Loss for Deep Face Recognition

目标检测-YOLOv3

目标检测-TCA

目标检测-Multi-Object Tracking

Simple Online and Realtime Tracking with a Deep Association Metric

图像分割-Face_Segmentation

https://github.com/nasir6/face-segmentation

图像生成-DCGAN

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

图像生成-Pix2Pix

Image-to-Image Translation with Conditional Adversarial Networks

图像生成-SRGAN

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial

图像生成-CycleGAN

Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

图像生成-FastNeuralStyle

Perceptual Losses for Real-Time Style Transfer and Super-Resolution 

图像生成-TTSR

Learning Texture Transformer Network for Image Super-Resolution 

图像生成-Pix2PixHD

High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

视频-TSN（视频分类）

Temporal Segment Networks: Towards Good Practices for Deep Action Recognition

视频-AP3D（视频分类）

Appearance-Preserving 3D Convolution for Video-based Person Re-identification 

关键点检测-HRNet

 Deep High-Resolution Representation Learning for Human Pose Estimation

智能文本处理(NLP)-RNN& LSTM

Finding Structure in Time  Long Short-Term Memory

智能文本处理(NLP)-BiLSTM

Bidirectional LSTM-CRF Models for Sequence Tagging 

智能文本处理(NLP)-TextCNN

 Convolutional Neural Networks for Sentence Classification

智能文本处理(NLP)-GPT-2

Language Models are Unsupervised Multitask Learners 

智能文本处理(NLP)-BERT

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

智能文本处理(NLP)-RoBERTa

RoBERTa: A Robustly Optimized BERT Pretraining Approach

智能文本处理(NLP)-Seq2Seq

Sequence to Sequence Learning with Neural Networks

智能语音(Speech)-Speaker_Verification_GE2Eloss

GENERALIZED END-TO-END LOSS FOR SPEAKER VERIFICATION

强化学习(RL)-AlphaStar RL Demo with Oneflow

Grandmaster level in StarCraft II using multi-agent reinforcement learning 

强化学习(RL)-DQN-FlappyBird

Playing Atari with Deep Reinforcement Learning

剪枝Model-bn

 Learning Efficient Convolutional Networks through Network Slimming

剪枝Model-conv_avg

剪枝Model-conv_all

剪枝Model-conv_max

剪枝Model-random

剪枝Model-conv_threshold

量化Model-ResNet50

 Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference

蒸馏Model-KD

Distilling the knowledge in a neural network

蒸馏Model-Distilled-BiLSTM

Distilling Task-Specific Knowledge from BERT into Simple Neural Networks

蒸馏Model-BERT-PKD

Patient Knowledge Distillation for BERT Model Compression 

蒸馏Model-TinyBERT

TinyBERT: Distilling BERT for Natural Language Understanding 

蒸馏Model-BERT-Theseus

BERT-of-Theseus: Compressing BERT by Progressive Module Replacing

模型库

联系我们

钉钉交流群