update readme (#1576)

example/auto_compression/README.md

@@ -81,6 +81,7 @@ ACT相比传统的模型压缩方法，
 | [图像分类](./image_classification)  | InceptionV3                   | 79.14                  | 78.32                  | 4.79             | 1.47             | **3.26**   | NVIDIA Tesla T4 |
 | [图像分类](./image_classification)  | EfficientNetB0                | 77.02                  | 74.27                  | 1.95             | 1.44             | **1.35**   | NVIDIA Tesla T4 |
 | [图像分类](./image_classification)  | GhostNet_x1_0                 | 74.02                  | 72.62                  | 2.93             | 1.03             | **2.84**   | NVIDIA Tesla T4 |
+| [图像分类](./image_classification)  | ViT_base_patch16_224          | 81.89                  | 82.05                  | 367.17           | 51.70            | **7.10**   | NVIDIA Tesla T4 |
 | [语义分割](./semantic_segmentation) | PP-HumanSeg-Lite              | 92.87                  | 92.35                  | 56.36            | 37.71            | **1.49**   | SDM710          |
 | [语义分割](./semantic_segmentation) | PP-LiteSeg                    | 77.04                  | 76.93                  | 1.43             | 1.16             | **1.23**   | NVIDIA Tesla T4 |
 | [语义分割](./semantic_segmentation) | HRNet                         | 78.97                  | 78.90                  | 8.188            | 5.812            | **1.41**   | NVIDIA Tesla T4 |

example/auto_compression/image_classification/README.md

@@ -45,8 +45,8 @@
 | MobileNetV3_large_x1_0 | 量化+蒸馏 | 74.04 | - | 9.85 | [Config](./configs/MobileNetV3_large_x1_0/qat_dis.yaml) | [Model](https://paddle-slim-models.bj.bcebos.com/act/MobileNetV3_large_x1_0_QAT.tar) |
 | MobileNetV3_large_x1_0_ssld | Baseline | 78.96 | - | 16.62 | - | [Model](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/MobileNetV3_large_x1_0_ssld_infer.tar) |
 | MobileNetV3_large_x1_0_ssld | 量化+蒸馏 | 77.17 | - | 9.85 | [Config](./configs/MobileNetV3_large_x1_0/qat_dis.yaml) | [Model](https://paddle-slim-models.bj.bcebos.com/act/MobileNetV3_large_x1_0_ssld_QAT.tar) |
-| ViT_base_patch16_224 | Baseline | 81.89 | - | - | - | [Model](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/ViT_base_patch16_224_infer.tar) |
-| ViT_base_patch16_224 | 量化+蒸馏 | 82.05 | - | - | [Config](./configs/VIT/qat_dis.yaml) | [Model](https://bj.bcebos.com/v1/paddle-slim-models/act/ViT_base_patch16_224_QAT.tar) |
+| ViT_base_patch16_224 | Baseline | 81.89 | 367.17(batch_size=40) | - | - | [Model](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/ViT_base_patch16_224_infer.tar) |
+| ViT_base_patch16_224 | 量化+蒸馏 | 82.05 | 51.70(batch_size=40) | - | [Config](./configs/VIT/qat_dis.yaml) | [Model](https://bj.bcebos.com/v1/paddle-slim-models/act/ViT_base_patch16_224_QAT.tar) |
 
 - ARM CPU 测试环境：`SDM865(4xA77+4xA55)`
 - Nvidia GPU 测试环境：

example/auto_compression/nlp/README.md

@@ -31,6 +31,7 @@
 | ERNIE 3.0-Medium | 剪枝+量化训练| 74.17 | 56.84 | 59.75 | 80.54 | 76.03 | 76.97 | 80.80 | 72.16 |
 
 | 模型 | 策略 | 报销工单数据 |
+|:------:|:------:|:------:|
 | UIE-base | Base模型 | [91.83](https://bj.bcebos.com/v1/paddle-slim-models/act/uie_base.tar) |
 | UIE-base | 量化训练 | [95.80](https://bj.bcebos.com/v1/paddle-slim-models/act/uie_base_qat_model.tar) |