Update info about ResNet(A) models

chainer_/README.md

@@ -116,6 +116,7 @@ Some remarks:
 - Top1/Top5 are the standard 1-crop Top-1/Top-5 errors (in percents) on the validation subset of the ImageNet-1K dataset.
 - FLOPs/2 is the number of FLOPs divided by two to be similar to the number of MACs.
 - Remark `Converted from GL model` means that the model was trained on `MXNet/Gluon` and then converted to Chainer.
+- ResNet(A) is an average downsampled ResNet intended for use as an feature extractor in some pose estimation networks.
 - ResNet(D) is a dilated ResNet intended for use as an feature extractor in some segmentation networks.
 - Models with *-suffix use non-standard preprocessing (see the training log).
 
@@ -368,6 +369,9 @@ Some remarks:
 | MixNet-S | 24.32 | 7.28 | 4,134,606 | 260.76M | From [rwightman/pyt...models] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.412/mixnet_s-0728-dc6c60c8.npz.log)) |
 | MixNet-M | 23.15 | 6.75 | 5,014,382 | 366.68M | From [rwightman/pyt...models] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.413/mixnet_m-0675-4979acf0.npz.log)) |
 | MixNet-L | 21.55 | 5.90 | 7,329,252 | 591.34M | From [rwightman/pyt...models] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.414/mixnet_l-0590-f942b4c5.npz.log)) |
+| ResNet(A)-50b | 20.81 | 5.41 | 25,576,264 | 4,352.93M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.452/resneta50b-0541-9c56b041.npz.log)) |
+| ResNet(A)-101b | 19.52 | 4.91 | 44,568,392 | 8,072.93M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.452/resneta101b-0491-5c892558.npz.log)) |
+| ResNet(A)-152b | 19.41 | 4.67 | 60,212,040 | 11,796.83M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.452/resneta152b-0467-d7e00a1b.npz.log)) |
 | ResNet(D)-50b | 20.80 | 5.50 | 25,680,808 | 20,497.60M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.296/resnetd50b-0550-7ba88f04.npz.log)) |
 | ResNet(D)-101b | 19.49 | 4.60 | 44,672,936 | 35,392.65M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.296/resnetd101b-0460-b90f971e.npz.log)) |
 | ResNet(D)-152b | 19.36 | 4.70 | 60,316,584 | 47,662.18M | From [dmlc/gluon-cv] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.296/resnetd152b-0470-41442334.npz.log)) |

chainer_/chainercv2/model_provider.py

@@ -88,6 +88,7 @@
 
 from .models.octresnet import *
 
+from .models.resneta import *
 from .models.resnetd import *
 
 from .models.resnet_cub import *
@@ -814,6 +815,10 @@
     'diapreresnet1202_cifar100': diapreresnet1202_cifar100,
     'diapreresnet1202_svhn': diapreresnet1202_svhn,
 
+    'resneta50b': resneta50b,
+    'resneta101b': resneta101b,
+    'resneta152b': resneta152b,
+
     'resnetd50b': resnetd50b,
     'resnetd101b': resnetd101b,
     'resnetd152b': resnetd152b,

chainer_/chainercv2/models/model_store.py

@@ -257,6 +257,9 @@
     ('mixnet_s', '0728', 'dc6c60c8cfac2e7a90ae68a76ed4fda17b44cf7a', 'v0.0.412'),
     ('mixnet_m', '0675', '4979acf0bd7ddef39f30f80ae296d480e5120609', 'v0.0.413'),
     ('mixnet_l', '0590', 'f942b4c57f08316283841a18ae2bd8fe4a9b1b1a', 'v0.0.414'),
+    ('resneta50b', '0541', '9c56b0411616f7435b98524920bfe566589cf55a', 'v0.0.452'),
+    ('resneta101b', '0491', '5c892558fdf39f4f182ca03628825b00cc3af7f0', 'v0.0.452'),
+    ('resneta152b', '0467', 'd7e00a1b09390ceda24edbce89f8421097b6a741', 'v0.0.452'),
     ('resnetd50b', '0550', '7ba88f0436b3fa598520424bb463ac985ffb0caf', 'v0.0.296'),
     ('resnetd101b', '0460', 'b90f971e4514345fb885de95165ddcc4e6610234', 'v0.0.296'),
     ('resnetd152b', '0470', '41442334cde93c9744d2a86288d11614c848503a', 'v0.0.296'),