@@ -166,16 +166,23 @@ The image classification models currently supported by PaddlePaddle are listed i
As the activation function ```swish``` and ```relu6``` which separately used in ShuffleNetV2_swish and MobileNetV2 net are not supported by Paddle TensorRT, inference acceleration performance of them doesn't significient improve. Pretrained models can be downloaded by clicking related model names.
- Note1: ResNet50_vd_v2 is the distilled version of ResNet50_vd.
- Note2: In addition to the image resolution feeded in InceptionV4 and Xception net is ```299x299```, others are ```224x224```.
- Note2: The image resolution feeded in InceptionV4 and Xception net is ```299x299```, Fix_ResNeXt101_32x48d_wsl is ```320x320```, DarkNet is ```256x256```, others are ```224x224```.In test time, the resize_short_size of the DarkNet53 and Fix_ResNeXt101_32x48d_wsl series networks is the same as the width or height of the input image resolution, the InceptionV4 and Xception network resize_short_size is 320, and the other networks resize_short_size are 256.
- Note3: It's necessary to convert the train model to a binary model when appling dynamic link library to infer, One can do it by running following command:
```python infer.py --save_inference=True```
- Note4: The pretrained model of the ResNeXt101_wsl series network is converted from the pytorch model. Please go to [RESNEXT WSL](https://pytorch.org/hub/facebookresearch_WSL-Images_resnext/) for details.
@@ -272,7 +301,11 @@ Enforce failed. Expected x_dims[1] == labels_dims[1], but received x_dims[1]:100
- GoogLeNet: [Going Deeper with Convolutions](https://www.cs.unc.edu/~wliu/papers/GoogLeNet.pdf), Christian Szegedy1, Wei Liu2, Yangqing Jia
- Xception: [Xception: Deep Learning with Depthwise Separable Convolutions](https://arxiv.org/abs/1610.02357), Franc ̧ois Chollet
- InceptionV4: [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://arxiv.org/abs/1602.07261), Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, Alex Alemi
- DarkNet: [YOLOv3: An Incremental Improvement](https://pjreddie.com/media/files/papers/YOLOv3.pdf), Joseph Redmon, Ali Farhadi
- DenseNet: [Densely Connected Convolutional Networks](https://arxiv.org/abs/1608.06993), Gao Huang, Zhuang Liu, Laurens van der Maaten
- SqueezeNet: [SQUEEZENET: ALEXNET-LEVEL ACCURACY WITH 50X FEWER PARAMETERS AND <0.5MB MODEL SIZE](https://arxiv.org/abs/1602.07360), Forrest N. Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, William J. Dally, Kurt Keutzer
- ResNeXt101_wsl: [Exploring the Limits of Weakly Supervised Pretraining](https://arxiv.org/abs/1805.00932), Dhruv Mahajan, Ross Girshick, Vignesh Ramanathan, Kaiming He, Manohar Paluri, Yixuan Li, Ashwin Bharambe, Laurens van der Maaten
- Fix_ResNeXt101_wsl: [Fixing the train-test resolution discrepancy](https://arxiv.org/abs/1906.06423), Hugo Touvron, Andrea Vedaldi, Matthijs Douze, Herve ́ Je ́gou
## Update
...
...
@@ -284,6 +317,7 @@ Enforce failed. Expected x_dims[1] == labels_dims[1], but received x_dims[1]:100
- GoogLeNet: [Going Deeper with Convolutions](https://www.cs.unc.edu/~wliu/papers/GoogLeNet.pdf), Christian Szegedy1, Wei Liu2, Yangqing Jia
- Xception: [Xception: Deep Learning with Depthwise Separable Convolutions](https://arxiv.org/abs/1610.02357), Franc ̧ois Chollet
- InceptionV4: [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://arxiv.org/abs/1602.07261), Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, Alex Alemi
- DarkNet: [YOLOv3: An Incremental Improvement](https://pjreddie.com/media/files/papers/YOLOv3.pdf), Joseph Redmon, Ali Farhadi
- DenseNet: [Densely Connected Convolutional Networks](https://arxiv.org/abs/1608.06993), Gao Huang, Zhuang Liu, Laurens van der Maaten
- SqueezeNet: [SQUEEZENET: ALEXNET-LEVEL ACCURACY WITH 50X FEWER PARAMETERS AND <0.5MB MODEL SIZE](https://arxiv.org/abs/1602.07360), Forrest N. Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, William J. Dally, Kurt Keutzer
- ResNeXt101_wsl: [Exploring the Limits of Weakly Supervised Pretraining](https://arxiv.org/abs/1805.00932), Dhruv Mahajan, Ross Girshick, Vignesh Ramanathan, Kaiming He, Manohar Paluri, Yixuan Li, Ashwin Bharambe, Laurens van der Maaten
- Fix_ResNeXt101_wsl: [Fixing the train-test resolution discrepancy](https://arxiv.org/abs/1906.06423), Hugo Touvron, Andrea Vedaldi, Matthijs Douze, Herve ́ Je ́gou
