Update info about ShuffleNetV2 x0.5 model

osmr · Oct 4, 2018 · ad1a98f · ad1a98f
1 parent 5efbb9d
commit ad1a98f
Show file tree

Hide file tree

Showing 5 changed files with 8 additions and 8 deletions.
diff --git a/README.md b/README.md
@@ -188,7 +188,7 @@ bottleneck block. Respectively a network without b-suffix has the stride in the
 | DarkNet Ref | 38.00 | 16.68 | 7,319,416 | 365.55M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.64/darknet_ref-1668-3011b4e1.params.log)) |
 | SqueezeNet v1.0 | 40.97 | 18.96 | 1,248,424 | 828.30M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.19/squeezenet_v1_0-1896-b69a4607.params.log)) |
 | SqueezeNet v1.1 | 41.37 | 19.20 | 1,235,496 | 354.88M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.15/squeezenet_v1_1-1920-6d01104e.params.log)) |
-| ShuffleNetV2 x0.5 | 41.20 | 18.90 | 1,366,792 | 42.34M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.37/shufflenetv2_wd2-1890-9c617398.params.log)) |
+| ShuffleNetV2 x0.5 | 40.98 | 18.53 | 1,366,792 | 42.34M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.67/shufflenetv2_wd2-1853-3f6182b6.params.log)) |
 | ShuffleNetV2 x1.0 | 33.97 | 13.41 | 2,278,604 | 147.92M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.48/shufflenetv2_w1-1341-275f1d2e.params.log)) |
 | ShuffleNetV2 x1.5 | 32.38 | 12.37 | 4,406,098 | 318.61M | Training ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.65/shufflenetv2_w3d2-1237-08c01388.params.log)) |
 | 108-MENet-8x1 (g=3) | 46.11 | 22.37 | 654,516 | 40.64M | From [clavichord93/MENet] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.6/menet108_8x1_g3-2237-d3bb5a4f.params.log)) |
@@ -260,7 +260,7 @@ bottleneck block. Respectively a network without b-suffix has the stride in the
 | DarkNet Ref | 38.58 | 17.18 | 7,319,416 | 365.55M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.64/darknet_ref-1718-034595b4.pth.log)) |
 | SqueezeNet v1.0 | 41.31 | 19.32 | 1,248,424 | 828.30M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.19/squeezenet_v1_0-1932-e4017303.pth.log)) |
 | SqueezeNet v1.1 | 41.82 | 19.38 | 1,235,496 | 354.88M | Converted from TorchVision ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.5/squeezenet_v1_1-1938-8dcd1cc5.pth.log)) |
-| ShuffleNetV2 x0.5 | 41.66 | 19.38 | 1,366,792 | 42.34M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.37/shufflenetv2_wd2-1938-d7b48d82.pth.log)) |
+| ShuffleNetV2 x0.5 | 41.48 | 19.02 | 1,366,792 | 42.34M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.67/shufflenetv2_wd2-1902-75dbfcc1.pth.log)) |
 | ShuffleNetV2 x1.0 | 34.39 | 13.78 | 2,278,604 | 147.92M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.48/shufflenetv2_w1-1378-dc6a33c9.pth.log)) |
 | ShuffleNetV2 x1.5 | 32.82 | 12.69 | 4,406,098 | 318.61M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.65/shufflenetv2_w3d2-1269-536ad5b1.pth.log)) |
 | 108-MENet-8x1 (g=3) | 43.92 | 20.76 | 654,516 | 40.64M | From [clavichord93/MENet] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.6/menet108_8x1_g3-2076-7f47b37e.pth.log)) |
@@ -332,7 +332,7 @@ bottleneck block. Respectively a network without b-suffix has the stride in the
 | DarkNet Ref | 38.09 | 16.71 | 7,319,416 | 365.55M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.64/darknet_ref-1671-b2d5721f.npz.log)) |
 | SqueezeNet v1.0 | 41.01 | 18.96 | 1,248,424 | 828.30M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.20/squeezenet_v1_0-1896-6cbb35ce.npz.log)) |
 | SqueezeNet v1.1 | 41.36 | 19.25 | 1,235,496 | 354.88M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.20/squeezenet_v1_1-1925-0ca73cf3.npz.log)) |
-| ShuffleNetV2 x0.5 | 43.77 | 21.17 | 1,366,792 | 42.34M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.37/shufflenetv2_wd2-2117-b19589d8.npz.log)) |
+| ShuffleNetV2 x0.5 | 43.80 | 20.87 | 1,366,792 | 42.34M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.67/shufflenetv2_wd2-2087-1b600e1d.npz.log)) |
 | ShuffleNetV2 x1.0 | 36.48 | 15.19 | 2,278,604 | 147.92M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.48/shufflenetv2_w1-1519-2156e7df.npz.log)) |
 | ShuffleNetV2 x1.5 | 33.96 | 13.37 | 4,406,098 | 318.61M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.65/shufflenetv2_w3d2-1337-66c1d6ed.npz.log)) |
 | 108-MENet-8x1 (g=3) | 46.07 | 22.42 | 654,516 | 40.64M | From [clavichord93/MENet] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.33/menet108_8x1_g3-2242-7c1b69e0.npz.log)) |
@@ -399,7 +399,7 @@ bottleneck block. Respectively a network without b-suffix has the stride in the
 | DarkNet Ref | 37.99 | 16.68 | 7,319,416 | 365.55M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.64/darknet_ref-1668-2ef080bb.h5.log)) |
 | SqueezeNet v1.0 | 41.07 | 19.04 | 1,248,424 | 828.30M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.57/squeezenet_v1_0-1904-c2c87509.h5.log)) |
 | SqueezeNet v1.1 | 41.37 | 19.20 | 1,235,496 | 354.88M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.57/squeezenet_v1_1-1920-5557ef36.h5.log)) |
-| ShuffleNetV2 x0.5 | 41.43 | 18.85 | 1,366,792 | 42.34M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.63/shufflenetv2_wd2-1885-aa64e676.h5.log)) |
+| ShuffleNetV2 x0.5 | 41.00 | 18.68 | 1,366,792 | 42.34M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.67/shufflenetv2_wd2-1868-d86e9c2e.h5.log)) |
 | ShuffleNetV2 x1.0 | 33.82 | 13.49 | 2,278,604 | 147.92M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.63/shufflenetv2_w1-1349-f42e0113.h5.log)) |
 | ShuffleNetV2 x1.5 | 32.46 | 12.47 | 4,406,098 | 318.61M | Converted from GL model ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.65/shufflenetv2_w3d2-1247-f7f813b4.h5.log)) |
 | 108-MENet-8x1 (g=3) | 46.09 | 22.37 | 654,516 | 40.64M | From [clavichord93/MENet] ([log](https://github.com/osmr/imgclsmob/releases/download/v0.0.58/menet108_8x1_g3-2237-beb28c9b.h5.log)) |

diff --git a/chainer_/chainercv2/models/model_store.py b/chainer_/chainercv2/models/model_store.py
@@ -55,7 +55,7 @@
     ('darknet_ref', '1671', 'b2d5721f3a5f6f05cc785d57ff7a63fe82f6325e', 'v0.0.64'),
     ('squeezenet_v1_0', '1896', '6cbb35ce171a38c7dc47c402511ca2800e9d7e99', 'v0.0.20'),
     ('squeezenet_v1_1', '1925', '0ca73cf33c7d6e3d1295fcb372b08528ffafbe2a', 'v0.0.20'),
-    ('shufflenetv2_wd2', '2117', 'b19589d8fd3e6b0a05cd13b92e522f2dc2a71ca6', 'v0.0.37'),
+    ('shufflenetv2_wd2', '2087', '1b600e1dcb7fe3423374acb69901c1ccaf0f5f03', 'v0.0.67'),
     ('shufflenetv2_w1', '1519', '2156e7dff4d3ec5e8f6634c3919f4da85a63bea1', 'v0.0.48'),
     ('shufflenetv2_w3d2', '1337', '66c1d6ed56e77d7bbf172e698e4a0d9f8a3bb442', 'v0.0.65'),
     ('menet108_8x1_g3', '2242', '7c1b69e03fc0400e8bb4c53d38057941db4a1b93', 'v0.0.33'),

diff --git a/gluon/gluoncv2/models/model_store.py b/gluon/gluoncv2/models/model_store.py
@@ -55,7 +55,7 @@
     ('darknet_ref', '1668', '3011b4e14b629f80da54ab57bef305d588f748ab', 'v0.0.64'),
     ('squeezenet_v1_0', '1896', 'b69a46072eba69b5a1967b721a01d2e8c385e0ff', 'v0.0.19'),
     ('squeezenet_v1_1', '1920', '6d01104eaf6f03ee18589896b2c0d5a6d7c5b164', 'v0.0.15'),
-    ('shufflenetv2_wd2', '1890', '9c6173984534cb96c542653d027ce25ef60c9cee', 'v0.0.37'),
+    ('shufflenetv2_wd2', '1853', '3f6182b61e883f5cfcd84e74b666bb2d2599868d', 'v0.0.67'),
     ('shufflenetv2_w1', '1341', '275f1d2ea7e706fb805603306656d03bec9f6a0f', 'v0.0.48'),
     ('shufflenetv2_w3d2', '1237', '08c013888fc1f782683eccdb201739b05dfd43aa', 'v0.0.65'),
     ('menet108_8x1_g3', '2237', 'd3bb5a4fa19a5e1dad2d036ffe64cc2a376defcc', 'v0.0.6'),

diff --git a/keras_/kerascv/models/model_store.py b/keras_/kerascv/models/model_store.py
@@ -50,7 +50,7 @@
     ('darknet_ref', '1668', '2ef080bb6f470e5ffb0c625ff3047de97cfeb6e2', 'v0.0.64'),
     ('squeezenet_v1_0', '1904', 'c2c87509293fa4dc4de21877d389ff01d5b6bf4e', 'v0.0.57'),
     ('squeezenet_v1_1', '1920', '5557ef36f64d84c6343378f36773b245c14cd6a0', 'v0.0.57'),
-    ('shufflenetv2_wd2', '1885', 'aa64e676fbcfd9641d95ce93ff4406924f265b9e', 'v0.0.63'),
+    ('shufflenetv2_wd2', '1868', 'd86e9c2e4d9cbdda06ad32302b84456735af27a6', 'v0.0.67'),
     ('shufflenetv2_w1', '1349', 'f42e01131a1b534812443a9935ed9b351be99d37', 'v0.0.63'),
     ('shufflenetv2_w3d2', '1247', 'f7f813b4b9de6d2b7b36ccec69fe9120f0669edc', 'v0.0.65'),
     ('menet108_8x1_g3', '2237', 'beb28c9bd24cc1c8864f1475df78937978fcf5d2', 'v0.0.58'),

diff --git a/pytorch/pytorchcv/models/model_store.py b/pytorch/pytorchcv/models/model_store.py
@@ -55,7 +55,7 @@
     ('darknet_ref', '1718', '034595b49113ee23de72e36f7d8a3dbb594615f6', 'v0.0.64'),
     ('squeezenet_v1_0', '1932', 'e4017303477daaaee6dfb687c17717c1c82c59f5', 'v0.0.19'),
     ('squeezenet_v1_1', '1938', '8dcd1cc5d955f3d154bfa5be20cd278f3e77f21b', 'v0.0.5'),
-    ('shufflenetv2_wd2', '1938', 'd7b48d8226e74912afcb8b8327d94bc17172bdf9', 'v0.0.37'),
+    ('shufflenetv2_wd2', '1902', '75dbfcc1c93a35e410968bf399d5e5d251f810e0', 'v0.0.67'),
     ('shufflenetv2_w1', '1378', 'dc6a33c9d34e54e7f12eac4f731b20493bc0c57e', 'v0.0.48'),
     ('shufflenetv2_w3d2', '1269', '536ad5b11bc169022ea6752cc288fb468b2856bf', 'v0.0.65'),
     ('menet108_8x1_g3', '2076', '7f47b37e10912a55ea85fefa616f822fc6b32859', 'v0.0.6'),