dwSun commented on a change in pull request #9614: MobileNetV2
URL: https://github.com/apache/incubator-mxnet/pull/9614#discussion_r168051072
 
 

 ##########
 File path: python/mxnet/gluon/model_zoo/vision/mobilenet.py
 ##########
 @@ -74,13 +123,69 @@ def hybrid_forward(self, F, x):
         x = self.output(x)
         return x
 
+
+class MobileNetV2(nn.HybridBlock):
+    r"""MobileNetV2 model from the
+    `"Inverted Residuals and Linear Bottlenecks:
+      Mobile Networks for Classification, Detection and Segmentation"
+    <https://arxiv.org/abs/1801.04381>`_ paper.
+
+    Parameters
+    ----------
+    multiplier : float, default 1.0
+        The width multiplier for controling the model size. The actual number 
of channels
+        is equal to the original channel size multiplied by this multiplier.
+    classes : int, default 1000
+        Number of classes for the output layer.
+    """
+
+    def __init__(self, multiplier=1.0, classes=1000, **kwargs):
+        super(MobileNetV2, self).__init__(**kwargs)
+        with self.name_scope():
+            self.features = nn.HybridSequential(prefix='features_')
+            with self.features.name_scope():
+                _add_conv(self.features, int(32 * multiplier), kernel=3, 
stride=2, pad=1)
+
+                in_channels_group = [int(x * multiplier) for x in [32] + [16] 
+ [24] * 2
+                                     + [32] * 3 + [64] * 4 + [96] * 3 + [160] 
* 3]
+                channels_group = [int(x * multiplier) for x in [16] + [24] * 2 
+ [32] * 3
+                                  + [64] * 4 + [96] * 3 + [160] * 3 + [320]]
+                ts = [1] + [6] * 16
+                strides = [1, 2] * 2 + [1] * 2 + [2] + [1] * 3 + [1] * 3 + [2] 
+ [1] * 3
 
 Review comment:
   The strides are correct in paper. We are applying stride 2 to last block of 
previous group of blocks.
   
   BTW, we are using output node as top-most node in model graph. While the 
output node should be the last few lines in our code. So the graph is looking 
like upside down. Should it be more convenient if we revert it?

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org


With regards,
Apache Git Services

Reply via email to