Update info for PreResNet-152 pretrained model

osmr · Aug 26, 2018 · 47c63c5 · 47c63c5
1 parent 070647a
commit 47c63c5
Show file tree

Hide file tree

Showing 3 changed files with 5 additions and 4 deletions.
diff --git a/README.md b/README.md
@@ -47,6 +47,7 @@ Some remarks:
 bottleneck block. Respectively a network without b-suffix has the stride in the first convolution.
 - ResNet/PreResNet models do not use biasses in convolutions at all.
 - CondenseNet models are only so-called converted versions.
+- All models have input 244x244 with ordinary mean and standard deviation normalization.
 
 ### For Gluon
 
@@ -72,7 +73,7 @@ bottleneck block. Respectively a network without b-suffix has the stride in the
 | PreResNet-50b | 23.16 | 6.64 | 25,549,480 | 4,100.90M | Converted from Gluon Model Zoo ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.2/preresnet50b-0664-2fcfddb1.params.log)) |
 | PreResNet-101 | 21.45 | 5.75 | 44,541,608 | 7,586.50M | Converted from Gluon Model Zoo ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.2/preresnet101-0575-e2887e53.params.log)) |
 | PreResNet-101b | 21.73 | 5.88 | 44,541,608 | 7,818.24M | Converted from Gluon Model Zoo ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.2/preresnet101b-0588-1015145a.params.log)) |
-| PreResNet-152 | 23.00 | 6.34 | 60,185,256 | 11,305.05M | Converted from Gluon Model Zoo ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.2/preresnet152-0634-a509a388.params.log)) |
+| PreResNet-152 | 20.70 | 5.32 | 60,185,256 | 11,305.05M | Converted from Gluon Model Zoo ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.14/preresnet152-0532-31505f71.params.log)) |
 | PreResNet-152b | 21.00 | 5.75 | 60,185,256 | 11,536.78M | Converted from Gluon Model Zoo ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.2/preresnet152b-0575-dc303191.params.log)) |
 | ResNeXt-101 (32x4d) | 21.32 | 5.79 | 44,177,704 | 7,991.62M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.10/resnext101_32x4d-0579-9afbfdbc.params.log)) |
 | ResNeXt-101 (64x4d) | 20.60 | 5.41 | 83,455,272 | 15,491.88M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.10/resnext101_64x4d-0541-0d4fd87b.params.log)) |
@@ -133,7 +134,7 @@ bottleneck block. Respectively a network without b-suffix has the stride in the
 | PreResNet-50b | 23.33 | 6.87 | 25,549,480 | 4,100.90M | Converted from Gluon Model Zoo ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.2/preresnet50b-0687-65be98fb.pth.log)) |
 | PreResNet-101 | 21.74 | 5.91 | 44,541,608 | 7,586.50M | Converted from Gluon Model Zoo ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.2/preresnet101-0591-4bacff79.pth.log)) |
 | PreResNet-101b | 21.95 | 6.03 | 44,541,608 | 7,818.24M | Converted from Gluon Model Zoo ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.2/preresnet101b-0603-b1e37a09.pth.log)) |
-| PreResNet-152 | 23.20 | 6.53 | 60,185,256 | 11,305.05M | Converted from Gluon Model Zoo ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.2/preresnet152-0653-426962af.pth.log)) |
+| PreResNet-152 | 20.94 | 5.55 | 60,185,256 | 11,305.05M | Converted from Gluon Model Zoo ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.14/preresnet152-0555-c842a030.pth.log)) |
 | PreResNet-152b | 21.34 | 5.91 | 60,185,256 | 11,536.78M | Converted from Gluon Model Zoo ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.2/preresnet152b-0591-2c91ab2c.pth.log)) |
 | ResNeXt-101 (32x4d) | 21.81 | 6.11 | 44,177,704 | 7,991.62M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.10/resnext101_32x4d-0611-cf962440.pth.log)) |
 | ResNeXt-101 (64x4d) | 21.04 | 5.75 | 83,455,272 | 15,491.88M | From [Cadene/pretrained...pytorch] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.10/resnext101_64x4d-0575-651abd02.pth.log)) |

diff --git a/gluon/models/model_store.py b/gluon/models/model_store.py
@@ -30,7 +30,7 @@
     ('preresnet50b', '0664', '2fcfddb13fbb8d7f58fb949f137610bf3d99a892', 'v0.0.2'),
     ('preresnet101', '0575', 'e2887e539f2519c36aea0fc991d6503ed384c4fc', 'v0.0.2'),
     ('preresnet101b', '0588', '1015145a6228aa16583a975b9c33f879ee2a6fc0', 'v0.0.2'),
-    ('preresnet152', '0634', 'a509a38809f455f00bff244754a3e187323ea150', 'v0.0.2'),
+    ('preresnet152', '0532', '31505f719ad76f5aee59d37a695ac7a9b06230fc', 'v0.0.14'),
     ('preresnet152b', '0575', 'dc303191ea47ca258f5abadd203b5de24d059d1a', 'v0.0.2'),
     ('resnext101_32x4d', '0579', '9afbfdbc5a420a9f56058be0bf80d12b21a627af', 'v0.0.10'),
     ('resnext101_64x4d', '0541', '0d4fd87b8de78c5c0295e1dcb9923a578dce7adb', 'v0.0.10'),

diff --git a/pytorch/models/model_store.py b/pytorch/models/model_store.py
@@ -31,7 +31,7 @@
     ('preresnet50b', '0687', '65be98fbe7b82c79bccd9c794ce9d9a3482aec9c', 'v0.0.2'),
     ('preresnet101', '0591', '4bacff796e113562e1dfdf71cfa7c6ed33e0ba86', 'v0.0.2'),
     ('preresnet101b', '0603', 'b1e37a09424dde15ecba72365d46b1f59abd479b', 'v0.0.2'),
-    ('preresnet152', '0653', '426962af4d9f6944611d36c29bcc83a3a24a268c', 'v0.0.2'),
+    ('preresnet152', '0555', 'c842a030abbcc21a0f2a9a8299fc42204897a611', 'v0.0.14'),
     ('preresnet152b', '0591', '2c91ab2c8d90f3990e7c30fd6ee2184f6c2c3bee', 'v0.0.2'),
     ('resnext101_32x4d', '0611', 'cf962440f11fe683fd02ec04f2102d9f47ce38a7', 'v0.0.10'),
     ('resnext101_64x4d', '0575', '651abd029bcc4ce88c62e1d900a710f284a8281e', 'v0.0.10'),