add mobilenetv3 large model

README.md

@@ -29,11 +29,11 @@ Following models are implemented, each one also has a readme inside.
 |[lenet](./lenet) | the simplest, as a "hello world" of this project |
 |[alexnet](./alexnet)| easy to implement, all layers are supported in tensorrt |
 |[googlenet](./googlenet)| GoogLeNet (Inception v1) |
-|[inception](./inception)| Inception v3 |
+|[inception](./inceptionv3)| Inception v3 |
 |[mnasnet](./mnasnet)| MNASNet with depth multiplier of 0.5 from the paper |
-|[mobilenet](./mobilenet)| MobileNet V2 |
+|[mobilenet](./mobilenetv2)| MobileNet V2 |
 |[resnet](./resnet)| resnet-18 and resnet-50 are implemented |
-|[shufflenet](./shufflenet)| ShuffleNetV2 with 0.5x output channels |
+|[shufflenet](./shufflenetv2)| ShuffleNetV2 with 0.5x output channels |
 |[squeezenet](./squeezenet)| SqueezeNet 1.1 model |
 |[vgg](./vgg)| VGG 11-layer model |
 |[yolov3](./yolov3)| darknet-53, weights from yolov3 authors |

mobilenetv3/README.md

@@ -1,23 +1,23 @@
-# mobilenet v2
+# mobilenet v3
 
-MobileNetV2 architecture from
-     "MobileNetV2: Inverted Residuals and Linear Bottlenecks" <https://arxiv.org/abs/1801.04381>.
+MobileNetV3 architecture from
+     "Searching for MobileNetV3" <https://arxiv.org/abs/1905.02244?context=cs>.
 
-For the Pytorch implementation, you can refer to [pytorchx/mobilenet](https://github.com/wang-xinyu/pytorchx/tree/master/mobilenet)
+For the Pytorch implementation, you can refer to [mobilenetv3.pytorch](https://github.com/d-li14/mobilenetv3.pytorch)
 
 Following tricks are used in this mobilenet,
 
-- Relu6 is used in mobilenet v2. We use `Relu6(x) = Relu(x) - Relu(x-6)` in tensorrt.
+- Hsigmoid is used in mobilenet v3. We create a plugin in tensorrt.
 - Batchnorm layer, implemented by scale layer.
 
 ```
-// 1. generate mobilenet.wts from [pytorchx/mobilenet](https://github.com/wang-xinyu/pytorchx/tree/master/mobilenet)
+// 1. generate mbv3_small.wts/mbv3_large.wts from pytorch implementation
 
-// 2. put mobilenet.wts into tensorrtx/mobilenet
+// 2. put mbv3_small.wts/mbv3_large.wts into tensorrtx/mobilenetv3
 
 // 3. build and run
 
-cd tensorrtx/mobilenet
+cd tensorrtx/mobilenetv3
 
 mkdir build
 
@@ -27,11 +27,11 @@ cmake ..
 
 make
 
-sudo ./mobilenet -s   // serialize model to plan file i.e. 'mobilenet.engine'
+sudo ./mobilenetv3 -s small(or large) // serialize model to plan file i.e. 'mobilenetv3_small.engine'
 
-sudo ./mobilenet -d   // deserialize plan file and run inference
+sudo ./mobilenetv3 -d small(or large)  // deserialize plan file and run inference
 
-// 4. see if the output is same as pytorchx/mobilenet
+// 4. see if the output is same as pytorch implementation
 ```