Update info about SE-ResNet-101b model

AASHRITH1903 · Mar 20, 2020 · 5f49747 · 5f49747
1 parent 3a7fa91
commit 5f49747
Show file tree

Hide file tree

Showing 31 changed files with 2,839 additions and 327 deletions.
diff --git a/README.md b/README.md
@@ -169,7 +169,7 @@ Some remarks:
 
 | Model | [Gluon](gluon/README.md) | [PyTorch](pytorch/README.md) | [Chainer](chainer_/README.md) | [Keras](keras_/README.md) | [TF](tensorflow_/README.md)  | [TF2](tensorflow_/README.md) | Paper | Repo | Year |
 | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
-| CenterNet | a | - | - | - | - | - | [link](https://arxiv.org/abs/1904.07850) | [link](https://github.com/xingyizhou/CenterNet) | 2019 |
+| CenterNet | a | a | a | - | - | a | [link](https://arxiv.org/abs/1904.07850) | [link](https://github.com/xingyizhou/CenterNet) | 2019 |
 
 ## Table of implemented human pose estimation models
 

diff --git a/chainer_/README.md b/chainer_/README.md
@@ -3,7 +3,7 @@
 [![PyPI](https://img.shields.io/pypi/v/chainercv2.svg)](https://pypi.python.org/pypi/chainercv2)
 [![Downloads](https://pepy.tech/badge/chainercv2)](https://pepy.tech/project/chainercv2)
 
-This is a collection of image classification, segmentation, and pose estimation models. Many of them are pretrained on
+This is a collection of image classification, segmentation, detection, and pose estimation models. Many of them are pretrained on
 [ImageNet-1K](http://www.image-net.org), [CIFAR-10/100](https://www.cs.toronto.edu/~kriz/cifar.html),
 [SVHN](http://ufldl.stanford.edu/housenumbers), [CUB-200-2011](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html),
 [Pascal VOC2012](http://host.robots.ox.ac.uk/pascal/VOC/voc2012), [ADE20K](http://groups.csail.mit.edu/vision/datasets/ADE20K),
@@ -88,6 +88,7 @@ models are in the [`imgclsmob`](https://github.com/osmr/imgclsmob) repo.
 - FCN-8s (['Fully Convolutional Networks for Semantic Segmentation'](https://arxiv.org/abs/1411.4038))
 - ICNet (['ICNet for Real-Time Semantic Segmentation on High-Resolution Images'](https://arxiv.org/abs/1704.08545))
 - SINet (['SINet: Extreme Lightweight Portrait Segmentation Networks with Spatial Squeeze Modules and Information Blocking Decoder'](https://arxiv.org/abs/1911.09099))
+- CenterNet (['Objects as Points'](https://arxiv.org/abs/1904.07850))
 - AlphaPose (['RMPE: Regional Multi-person Pose Estimation'](https://arxiv.org/abs/1612.00137))
 - SimplePose (['Simple Baselines for Human Pose Estimation and Tracking'](https://arxiv.org/abs/1804.06208))
 - Lightweight OpenPose (['Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose'](https://arxiv.org/abs/1811.12004))
@@ -200,6 +201,7 @@ Some remarks:
 | SE-ResNet-50 | 21.11 | 5.59 | 28,088,024 | 3,883.25M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.441/seresnet50-0559-6c5585d5.npz.log)) |
 | SE-ResNet-50b | 20.56 | 5.30 | 28,088,024 | 4,115.78M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.387/seresnet50b-0530-1ac3bf50.npz.log)) |
 | SE-ResNet-101 | 21.90 | 5.88 | 49,326,872 | 7,602.76M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.24/seresnet101-0588-e45a9f8f.npz.log)) |
+| SE-ResNet-101b | 19.48 | 4.63 | 49,326,872 | 7,839.75M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.460/seresnet101b-0463-97cc55c3.npz.log)) |
 | SE-ResNet-152 | 21.46 | 5.77 | 66,821,848 | 11,328.52M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.24/seresnet152-0577-a089ba52.npz.log)) |
 | SE-PreResNet-10 | 33.63 | 13.11 | 5,461,668 | 894.42M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.377/sepreresnet10-1311-5e38607c.npz.log)) |
 | SE-PreResNet-18 | 27.72 | 9.39 | 11,776,928 | 1,821.03M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.380/sepreresnet18-0939-a78ded77.npz.log)) |

diff --git a/chainer_/chainercv2/model_provider.py b/chainer_/chainercv2/model_provider.py
@@ -110,6 +110,8 @@
 from .models.lwopenpose_cmupan import *
 from .models.ibppose_coco import *
 
+from .models.centernet import *
+
 __all__ = ['get_model']
 
 
@@ -949,6 +951,13 @@
     'lwopenpose3d_mobilenet_cmupan_coco': lwopenpose3d_mobilenet_cmupan_coco,
 
     'ibppose_coco': ibppose_coco,
+
+    'centernet_resnet18_voc': centernet_resnet18_voc,
+    'centernet_resnet18_coco': centernet_resnet18_coco,
+    'centernet_resnet50b_voc': centernet_resnet50b_voc,
+    'centernet_resnet50b_coco': centernet_resnet50b_coco,
+    'centernet_resnet101b_voc': centernet_resnet101b_voc,
+    'centernet_resnet101b_coco': centernet_resnet101b_coco,
 }