You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by GitBox <gi...@apache.org> on 2018/01/03 18:38:18 UTC
[GitHub] piiswrong closed pull request #9286: update front-page model zoo to gluon model zoo
piiswrong closed pull request #9286: update front-page model zoo to gluon model zoo
URL: https://github.com/apache/incubator-mxnet/pull/9286
This is a PR merged from a forked repository.
As GitHub hides the original diff on merge, it is displayed below for
the sake of provenance:
As this is a foreign pull request (from a fork), the diff is supplied
below (as it won't show otherwise due to GitHub magic):
diff --git a/docs/_static/mxnet-theme/index.html b/docs/_static/mxnet-theme/index.html
index 96f61de30a..f3f98f7bdc 100644
--- a/docs/_static/mxnet-theme/index.html
+++ b/docs/_static/mxnet-theme/index.html
@@ -47,10 +47,10 @@ <h3>MXNet Joining Apache</h3>
<div class="row">
<div id="model-zoo-blk" class="col-lg-4 col-sm-12">
<span class="glyphicon glyphicon-folder-open"></span>
- <h2>Model Zoo</h2>
- <p>Off the shelf pre-trained models. Fast implementations of many state-of-art models.</p>
+ <h2>Gluon Model Zoo</h2>
+ <p>One-click pre-trained models, included in Gluon. Fast implementations of many state-of-the-art models, for plug-and-play effortless use.</p>
<div class='util-btn'>
- <a id="model-zoo-link" href="model_zoo/index.html">Model zoo</a>
+ <a id="model-zoo-link" href="api/python/gluon/model_zoo.html">Gluon model zoo</a>
</div>
</div>
<div id="example-blk" class="col-lg-4 col-sm-12">
diff --git a/docs/api/python/gluon/model_zoo.md b/docs/api/python/gluon/model_zoo.md
index 8310461242..27d2647767 100644
--- a/docs/api/python/gluon/model_zoo.md
+++ b/docs/api/python/gluon/model_zoo.md
@@ -28,6 +28,41 @@ In the rest of this document, we list routines provided by the `gluon.model_zoo`
.. automodule:: mxnet.gluon.model_zoo.vision
```
+The following table summarizes the available models.
+
+| Alias | Network | # Parameters | Top-1 Accuracy | Top-5 Accuracy | Origin |
+|---------------|---------------------------------------------------------------------------------------|--------------|----------------|----------------|------------------------------------------------------------------------------------------------------------------------------------------------------|
+| alexnet | [AlexNet](https://arxiv.org/abs/1404.5997) | 61,100,840 | 0.5492 | 0.7803 | Converted from pytorch vision |
+| densenet121 | [DenseNet-121](https://arxiv.org/pdf/1608.06993.pdf) | 8,062,504 | 0.7497 | 0.9225 | Converted from pytorch vision |
+| densenet161 | [DenseNet-161](https://arxiv.org/pdf/1608.06993.pdf) | 28,900,936 | 0.7770 | 0.9380 | Converted from pytorch vision |
+| densenet169 | [DenseNet-169](https://arxiv.org/pdf/1608.06993.pdf) | 14,307,880 | 0.7617 | 0.9317 | Converted from pytorch vision |
+| densenet201 | [DenseNet-201](https://arxiv.org/pdf/1608.06993.pdf) | 20,242,984 | 0.7732 | 0.9362 | Converted from pytorch vision |
+| inceptionv3 | [Inception V3 299x299](http://arxiv.org/abs/1512.00567) | 23,869,000 | 0.7755 | 0.9364 | Converted from pytorch vision |
+| mobilenet0.25 | [MobileNet 0.25](https://arxiv.org/abs/1704.04861) | 475,544 | 0.5185 | 0.7608 | Trained with [script](https://github.com/zhreshold/mxnet/blob/2fbfdbcbacff8b738bd9f44e9c8cefc84d6dfbb5/example/gluon/train_imagenet.py) |
+| mobilenet0.5 | [MobileNet 0.5](https://arxiv.org/abs/1704.04861) | 1,342,536 | 0.6307 | 0.8475 | Trained with [script](https://github.com/zhreshold/mxnet/blob/2fbfdbcbacff8b738bd9f44e9c8cefc84d6dfbb5/example/gluon/train_imagenet.py) |
+| mobilenet0.75 | [MobileNet 0.75](https://arxiv.org/abs/1704.04861) | 2,601,976 | 0.6738 | 0.8782 | Trained with [script](https://github.com/zhreshold/mxnet/blob/2fbfdbcbacff8b738bd9f44e9c8cefc84d6dfbb5/example/gluon/train_imagenet.py) |
+| mobilenet1.0 | [MobileNet 1.0](https://arxiv.org/abs/1704.04861) | 4,253,864 | 0.7105 | 0.9006 | Trained with [script](https://github.com/zhreshold/mxnet/blob/2fbfdbcbacff8b738bd9f44e9c8cefc84d6dfbb5/example/gluon/train_imagenet.py) |
+| resnet18_v1 | [ResNet-18 V1](http://arxiv.org/abs/1512.03385) | 11,699,112 | 0.6803 | 0.8818 | Converted from pytorch vision |
+| resnet34_v1 | [ResNet-34 V1](http://arxiv.org/abs/1512.03385) | 21,814,696 | 0.7202 | 0.9066 | Converted from pytorch vision |
+| resnet50_v1 | [ResNet-50 V1](http://arxiv.org/abs/1512.03385) | 25,629,032 | 0.7540 | 0.9266 | Trained with [script](https://github.com/zhreshold/mxnet/blob/2fbfdbcbacff8b738bd9f44e9c8cefc84d6dfbb5/example/gluon/train_imagenet.py) |
+| resnet101_v1 | [ResNet-101 V1](http://arxiv.org/abs/1512.03385) | 44,695,144 | 0.7693 | 0.9334 | Trained with [script](https://github.com/zhreshold/mxnet/blob/2fbfdbcbacff8b738bd9f44e9c8cefc84d6dfbb5/example/gluon/train_imagenet.py) |
+| resnet152_v1 | [ResNet-152 V1](http://arxiv.org/abs/1512.03385) | 60,404,072 | 0.7727 | 0.9353 | Trained with [script](https://github.com/zhreshold/mxnet/blob/2fbfdbcbacff8b738bd9f44e9c8cefc84d6dfbb5/example/gluon/train_imagenet.py) |
+| resnet18_v2 | [ResNet-18 V2](https://arxiv.org/abs/1603.05027) | 11,695,796 | 0.6961 | 0.8901 | Trained with [script](https://github.com/apache/incubator-mxnet/blob/4dcd96ae2f6820e01455079d00f49db1cd21eda9/example/gluon/image_classification.py) |
+| resnet34_v2 | [ResNet-34 V2](https://arxiv.org/abs/1603.05027) | 21,811,380 | 0.7324 | 0.9125 | Trained with [script](https://github.com/apache/incubator-mxnet/blob/4dcd96ae2f6820e01455079d00f49db1cd21eda9/example/gluon/image_classification.py) |
+| resnet50_v2 | [ResNet-50 V2](https://arxiv.org/abs/1603.05027) | 25,595,060 | 0.7622 | 0.9297 | Trained with [script](https://github.com/zhreshold/mxnet/blob/2fbfdbcbacff8b738bd9f44e9c8cefc84d6dfbb5/example/gluon/train_imagenet.py) |
+| resnet101_v2 | [ResNet-101 V2](https://arxiv.org/abs/1603.05027) | 44,639,412 | 0.7747 | 0.9375 | Trained with [script](https://github.com/zhreshold/mxnet/blob/2fbfdbcbacff8b738bd9f44e9c8cefc84d6dfbb5/example/gluon/train_imagenet.py) |
+| resnet152_v2 | [ResNet-152 V2](https://arxiv.org/abs/1603.05027) | 60,329,140 | 0.7833 | 0.9409 | Trained with [script](https://github.com/zhreshold/mxnet/blob/2fbfdbcbacff8b738bd9f44e9c8cefc84d6dfbb5/example/gluon/train_imagenet.py) |
+| squeezenet1.0 | [SqueezeNet 1.0](https://arxiv.org/abs/1602.07360) | 1,248,424 | 0.5611 | 0.7909 | Converted from pytorch vision |
+| squeezenet1.1 | [SqueezeNet 1.1](https://github.com/DeepScale/SqueezeNet/tree/master/SqueezeNet_v1.1) | 1,235,496 | 0.5496 | 0.7817 | Converted from pytorch vision |
+| vgg11 | [VGG-11](https://arxiv.org/abs/1409.1556) | 132,863,336 | 0.6662 | 0.8734 | Converted from pytorch vision |
+| vgg13 | [VGG-13](https://arxiv.org/abs/1409.1556) | 133,047,848 | 0.6774 | 0.8811 | Converted from pytorch vision |
+| vgg16 | [VGG-16](https://arxiv.org/abs/1409.1556) | 138,357,544 | 0.6986 | 0.8945 | Converted from pytorch vision |
+| vgg19 | [VGG-19](https://arxiv.org/abs/1409.1556) | 143,667,240 | 0.7072 | 0.8988 | Converted from pytorch vision |
+| vgg11_bn | [VGG-11 with batch normalization](https://arxiv.org/abs/1409.1556) | 132,874,344 | 0.6859 | 0.8872 | Converted from pytorch vision |
+| vgg13_bn | [VGG-13 with batch normalization](https://arxiv.org/abs/1409.1556) | 133,059,624 | 0.6884 | 0.8882 | Converted from pytorch vision |
+| vgg16_bn | [VGG-16 with batch normalization](https://arxiv.org/abs/1409.1556) | 138,374,440 | 0.7142 | 0.9043 | Converted from pytorch vision |
+| vgg19_bn | [VGG-19 with batch normalization](https://arxiv.org/abs/1409.1556) | 143,689,256 | 0.7241 | 0.9093 | Converted from pytorch vision |
+
```eval_rst
.. autosummary::
:nosignatures:
diff --git a/python/mxnet/gluon/model_zoo/vision/__init__.py b/python/mxnet/gluon/model_zoo/vision/__init__.py
index 619711e71d..5df777fd5f 100644
--- a/python/mxnet/gluon/model_zoo/vision/__init__.py
+++ b/python/mxnet/gluon/model_zoo/vision/__init__.py
@@ -39,8 +39,8 @@
squeezenet = vision.squeezenet1_0()
densenet = vision.densenet_161()
-We provide pre-trained models for all the models except ResNet V2.
-These can constructed by passing ``pretrained=True``:
+We provide pre-trained models for all the listed models.
+These models can constructed by passing ``pretrained=True``:
.. code::
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services