博客新址: http://blog.xuezhisd.top
邮箱:xuezhisd@126.com
MXNet 突出了学术论文中报告的最先进模型的快速实现。我们的模型园地(Modle Zoo)包含了完整的模型,Python脚本,预训练的权重和如何进行微调的说明文档。
提交一个包含下列内容的 Pull 请求:
Readme 文件应该包含:
卷积神经网络对于很多图像和视频处理问题来说,是最先进的架构。一些可用的数据库有:
Model Definition | Dataset | Model Weights | Research Basis | Contributors |
---|---|---|---|---|
CaffeNet | ImageNet | Krizhevsky, 2012 | @… | |
Network in Network (NiN) | CIFAR-10 | Lin et al…, 2014 | ||
SqueezeNet | ImageNet | Iandola et al…, 2016 | ||
VGG16 | ImageNet | Simonyan et al…, 2015 | ||
VGG19 | ImageNet | Simonyan et al…, 2015 | ||
Inception v3 w/BatchNorm | ImageNet | Szegedy et al…, 2015 | ||
ResidualNet152 | ImageNet | He et al…, 2015 | ||
Fast-RCNN | PASCAL VOC | Girshick, 2015 | ||
Faster-RCNN | PASCAL VOC | Ren et al…,2016 | ||
Single Shot Detection (SSD) | PASCAL VOC | Liu et al…, 2016 |
MXNet 支持循环神经网络(recurrent neural networks, RNNs),也支持长短时记忆网络( Long short-term memory, LSTM)和 GRU网络(Gated Recurrent Units)。一些可用的数据集有:
Model Definition | Dataset | Model Weights | Research Basis | Contributors |
---|---|---|---|---|
LSTM - Image Captioning | Flickr8k, MS COCO | [Vinyals et al…, 2015](https://arxiv.org/pdf/ 1411.4555v2.pdf) | @… | |
LSTM - Q&A System | bAbl | Weston et al…, 2015 | ||
LSTM - Sentiment Analysis | IMDB | Li et al…, 2015 |
Model Definition | Dataset | Model Weights | Research Basis | Contributors |
---|---|---|---|---|
DCGANs | ImageNet | Radford et al…,2016 | @… | |
Text to Image Synthesis | MS COCO | Reed et al…, 2016 | ||
Deep Jazz | Deepjazz.io |
MXNet 支持多种模型,不限于经典的CNN和LSTM。包括深度增强学习,线性模型等。下面是一些可用的的数据集和资源:
Model Definition | Dataset | Model Weights | Research Basis | Contributors |
---|---|---|---|---|
Word2Vec | Google News | Mikolov et al…, 2013 | @… | |
Matrix Factorization | MovieLens 20M | Huang et al…, 2013 | ||
Deep Q-Network | Atari video games | Minh et al…, 2015 | ||
Asynchronous advantage actor-critic (A3C) | Atari video games | Minh et al…, 2016 |