You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by jx...@apache.org on 2018/05/10 04:40:48 UTC
[incubator-mxnet] branch master updated: add mobilenetv2 pretrained
models (#10879)
This is an automated email from the ASF dual-hosted git repository.
jxie pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-mxnet.git
The following commit(s) were added to refs/heads/master by this push:
new 5088ca9 add mobilenetv2 pretrained models (#10879)
5088ca9 is described below
commit 5088ca9a65641ddf905b60deae00fa6006f5e431
Author: Tong He <he...@gmail.com>
AuthorDate: Wed May 9 21:40:42 2018 -0700
add mobilenetv2 pretrained models (#10879)
* add mobilenetv2 pretrained models
* improve docs
---
docs/api/python/gluon/model_zoo.md | 12 +++++++++---
python/mxnet/gluon/model_zoo/model_store.py | 5 ++++-
2 files changed, 13 insertions(+), 4 deletions(-)
diff --git a/docs/api/python/gluon/model_zoo.md b/docs/api/python/gluon/model_zoo.md
index 950e2c0..453fe8d 100644
--- a/docs/api/python/gluon/model_zoo.md
+++ b/docs/api/python/gluon/model_zoo.md
@@ -42,9 +42,12 @@ The following table summarizes the available models.
| mobilenet0.5 | [MobileNet 0.5](https://arxiv.org/abs/1704.04861) | 1,342,536 | 0.6307 | 0.8475 | Trained with [script](https://github.com/apache/incubator-mxnet/blob/master/example/gluon/image_classification.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/apache/incubator-mxnet/blob/master/example/gluon/image_classification.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/apache/incubator-mxnet/blob/master/example/gluon/image_classification.py) |
-| mobilenetv2_1.0 | [MobileNetV2 1.0](https://arxiv.org/abs/1801.04381) | 3,539,136 | 0.7159 | 0.9047 | Trained with [script](https://github.com/dmlc/gluon-cv/blob/15ed8a4c71d411b878f0d71d1c7afdce6710c913/scripts/classification/imagenet/train_imagenet.py) |
-| resnet18_v1 | [ResNet-18 V1](http://arxiv.org/abs/1512.03385) | 11,699,112 | 0.7039 | 0.8959 | Trained with [script](https://github.com/dmlc/gluon-cv/blob/15ed8a4c71d411b878f0d71d1c7afdce6710c913/scripts/classification/imagenet/train_imagenet.py) |
-| resnet34_v1 | [ResNet-34 V1](http://arxiv.org/abs/1512.03385) | 21,814,696 | 0.7411 | 0.9184 | Trained with [script](https://github.com/dmlc/gluon-cv/blob/15ed8a4c71d411b878f0d71d1c7afdce6710c913/scripts/classification/imagenet/train_imagenet.py) |
+| mobilenetv2_1.0 | [MobileNetV2 1.0](https://arxiv.org/abs/1801.04381) | 3,539,136 | 0.7192 | 0.9056 | Trained with [script](https://gluon-cv.mxnet.io/model_zoo/index.html#image-classification) |
+| mobilenetv2_0.75 | [MobileNetV2 0.75](https://arxiv.org/abs/1801.04381) | 2,653,864 | 0.6961 | 0.8895 | Trained with [script](https://gluon-cv.mxnet.io/model_zoo/index.html#image-classification) |
+| mobilenetv2_0.5 | [MobileNetV2 0.5](https://arxiv.org/abs/1801.04381) | 1,983,104 | 0.6449 | 0.8547 | Trained with [script](https://gluon-cv.mxnet.io/model_zoo/index.html#image-classification) |
+| mobilenetv2_0.25 | [MobileNetV2 0.25](https://arxiv.org/abs/1801.04381) | 1,526,856 | 0.5074 | 0.7456 | Trained with [script](https://gluon-cv.mxnet.io/model_zoo/index.html#image-classification) |
+| resnet18_v1 | [ResNet-18 V1](http://arxiv.org/abs/1512.03385) | 11,699,112 | 0.7039 | 0.8959 | Trained with [script](https://gluon-cv.mxnet.io/model_zoo/index.html#image-classification) |
+| resnet34_v1 | [ResNet-34 V1](http://arxiv.org/abs/1512.03385) | 21,814,696 | 0.7411 | 0.9184 | Trained with [script](https://gluon-cv.mxnet.io/model_zoo/index.html#image-classification) |
| resnet50_v1 | [ResNet-50 V1](http://arxiv.org/abs/1512.03385) | 25,629,032 | 0.7540 | 0.9266 | Trained with [script](https://github.com/apache/incubator-mxnet/blob/master/example/gluon/image_classification.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/apache/incubator-mxnet/blob/master/example/gluon/image_classification.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/apache/incubator-mxnet/blob/master/example/gluon/image_classification.py) |
@@ -205,6 +208,9 @@ The following table summarizes the available models.
mobilenet0_5
mobilenet0_25
mobilenet_v2_1_0
+ mobilenet_v2_0_75
+ mobilenet_v2_0_5
+ mobilenet_v2_0_25
```
```eval_rst
diff --git a/python/mxnet/gluon/model_zoo/model_store.py b/python/mxnet/gluon/model_zoo/model_store.py
index 14ec8d0..cbd95cf 100644
--- a/python/mxnet/gluon/model_zoo/model_store.py
+++ b/python/mxnet/gluon/model_zoo/model_store.py
@@ -35,7 +35,10 @@ _model_sha1 = {name: checksum for checksum, name in [
('8e9d539cc66aa5efa71c4b6af983b936ab8701c3', 'mobilenet0.5'),
('529b2c7f4934e6cb851155b22c96c9ab0a7c4dc2', 'mobilenet0.75'),
('6b8c5106c730e8750bcd82ceb75220a3351157cd', 'mobilenet1.0'),
- ('3ab4967b7a12a9246a144c9dfff74506cb78a526', 'mobilenetv2_1.0'),
+ ('36da4ff1867abccd32b29592d79fc753bca5a215', 'mobilenetv2_1.0'),
+ ('e2be7b72a79fe4a750d1dd415afedf01c3ea818d', 'mobilenetv2_0.75'),
+ ('aabd26cd335379fcb72ae6c8fac45a70eab11785', 'mobilenetv2_0.5'),
+ ('ae8f9392789b04822cbb1d98c27283fc5f8aa0a7', 'mobilenetv2_0.25'),
('e54b379f50fa4b10bbd2506237e3bd74e6164778', 'resnet18_v1'),
('c1dc0967a3d25ee9127e03bc1046a5d44d92e2ba', 'resnet34_v1'),
('c940b1a062b32e3a5762f397c9d1e178b5abd007', 'resnet50_v1'),
--
To stop receiving notification emails like this one, please contact
jxie@apache.org.