Added "Network in Network" to the list of validated models

Saumitro Dasgupta · Saumitro Dasgupta · commit c0100fcba1aa · 2016-05-16T02:14:58.000-07:00
diff --git a/README.md b/README.md
@@ -15,18 +15,19 @@ The output consists of two files:
 
 ### Examples
 
-See the `examples` folder for more details.
+See the [examples](examples/) folder for more details.
 
 ## Verification
 
 The following converted models have been verified on the ILSVRC2012 validation set.
 
-| Model                                          | Top 5 Accuracy |
-|:-----------------------------------------------|---------------:|
-| [VGG 16](http://arxiv.org/abs/1409.1556)       |         89.88% |
-| [GoogLeNet](http://arxiv.org/abs/1409.4842)    |         89.06% |
-| [CaffeNet](http://arxiv.org/abs/1408.5093)     |         79.93% |
-| [AlexNet](http://goo.gl/3BilWd)                |         79.84% |
+| Model                                                 | Top 5 Accuracy |
+|:------------------------------------------------------|---------------:|
+| [VGG 16](http://arxiv.org/abs/1409.1556)              |         89.88% |
+| [GoogLeNet](http://arxiv.org/abs/1409.4842)           |         89.06% |
+| [Network in Network](http://arxiv.org/abs/1312.4400)  |         81.21% |
+| [CaffeNet](http://arxiv.org/abs/1408.5093)            |         79.93% |
+| [AlexNet](http://goo.gl/3BilWd)                       |         79.84% |
 
 ## Notes
 
diff --git a/examples/imagenet/models/helper.py b/examples/imagenet/models/helper.py
@@ -9,6 +9,7 @@
 from vgg import VGG16
 from alexnet import AlexNet
 from caffenet import CaffeNet
+from nin import NiN
 
 
 class DataSpec(object):
@@ -32,7 +33,7 @@ def __init__(self, batch_size, scale_size, crop_size, isotropic, channels=3, mea
         self.mean = mean if mean is not None else np.array([104., 117., 124.])
 
 # Collection of sample auto-generated models
-MODELS = (AlexNet, CaffeNet, GoogleNet, VGG16)
+MODELS = (AlexNet, CaffeNet, GoogleNet, NiN, VGG16)
 
 # The corresponding data specifications for the sample models
 # These specifications are based on how the models were trained.
@@ -54,6 +55,11 @@ def __init__(self, batch_size, scale_size, crop_size, isotropic, channels=3, mea
                         crop_size=224,
                         isotropic=False),
 
+    NiN: DataSpec(batch_size=500,
+                  scale_size=256,
+                  crop_size=224,
+                  isotropic=True),
+
     VGG16: DataSpec(batch_size=25,
                     scale_size=256,
                     crop_size=224,
diff --git a/examples/imagenet/models/nin.py b/examples/imagenet/models/nin.py
@@ -0,0 +1,22 @@
+from kaffe.tensorflow import Network
+
+class NiN(Network):
+    def setup(self):
+        (self.feed('data')
+             .conv(11, 11, 96, 4, 4, padding='VALID', name='conv1')
+             .conv(1, 1, 96, 1, 1, name='cccp1')
+             .conv(1, 1, 96, 1, 1, name='cccp2')
+             .max_pool(3, 3, 2, 2, name='pool1')
+             .conv(5, 5, 256, 1, 1, name='conv2')
+             .conv(1, 1, 256, 1, 1, name='cccp3')
+             .conv(1, 1, 256, 1, 1, name='cccp4')
+             .max_pool(3, 3, 2, 2, padding='VALID', name='pool2')
+             .conv(3, 3, 384, 1, 1, name='conv3')
+             .conv(1, 1, 384, 1, 1, name='cccp5')
+             .conv(1, 1, 384, 1, 1, name='cccp6')
+             .max_pool(3, 3, 2, 2, padding='VALID', name='pool3')
+             .conv(3, 3, 1024, 1, 1, name='conv4-1024')
+             .conv(1, 1, 1024, 1, 1, name='cccp7-1024')
+             .conv(1, 1, 1000, 1, 1, name='cccp8-1024')
+             .avg_pool(6, 6, 1, 1, padding='VALID', name='pool4')
+             .softmax(name='prob'))
