Skip to content

M
mindspore

MindSpore / mindspore

通知 35
Star 15
Fork 15
M
mindspore

体验新版 GitCode，发现更多精彩内容 >>

提交 02fe2f9f 编写于 作者: Z zhouyaqiang
浏览文件
操作

modify read me of inception v3

上级 61e8f102
隐藏空白更改
内联 并排
Showing with 14 addition and 12 deletion
model_zoo/official/cv/inceptionv3/README.md
浏览文件 @ 02fe2f9f
...@@ -35,7 +35,7 @@ The overall network architecture of InceptionV3 is show below: ...@@ -35,7 +35,7 @@ The overall network architecture of InceptionV3 is show below:
Dataset used can refer to paper. Dataset used can refer to paper.
- Dataset size: ~125G, 1.2W colorful images in 1000 classes - Dataset size: 125G, 1250k colorful images in 1000 classes
- Train: 120G, 1200k images - Train: 120G, 1200k images
- Test: 5G, 50k images - Test: 5G, 50k images
- Data format: RGB images. - Data format: RGB images.
...@@ -217,19 +217,21 @@ metric: {'Loss': 1.778, 'Top1-Acc':0.788, 'Top5-Acc':0.942} ...@@ -217,19 +217,21 @@ metric: {'Loss': 1.778, 'Top1-Acc':0.788, 'Top5-Acc':0.942}
### Training Performance ### Training Performance
| Parameters | InceptionV3 | | | Parameters | Ascend | GPU |
| -------------------------- | ---------------------------------------------- | ------------------------- | | -------------------------- | ---------------------------------------------- | ------------------------- |
| Model Version | V1 | V1 | | Model Version | InceptionV3 | InceptionV3 |
| Resource | Ascend 910, cpu:2.60GHz 56cores, memory:314G | NV SMI V100-16G(PCIE),cpu:2.10GHz 96cores, memory:250G | | Resource | Ascend 910, cpu:2.60GHz 56cores, memory:314G | NV SMI V100-16G(PCIE),cpu:2.10GHz 96cores, memory:250G |
| uploaded Date | 08/21/2020 | 08/21/2020 | | uploaded Date | 08/21/2020 | 08/21/2020 |
| MindSpore Version | 0.6.0-beta | 0.6.0-beta | | MindSpore Version | 0.6.0-beta | 0.6.0-beta |
| Dataset | 1200k images | 1200k images |
| Batch_size | 128 | 128 |
| Training Parameters | src/config.py | src/config.py | | Training Parameters | src/config.py | src/config.py |
| Optimizer | RMSProp | RMSProp | | Optimizer | RMSProp | RMSProp |
| Loss Function | SoftmaxCrossEntropy | SoftmaxCrossEntropy | | Loss Function | SoftmaxCrossEntropy | SoftmaxCrossEntropy |
| outputs | probability | probability | | Outputs | probability | probability |
| Loss | 1.98 | 1.98 | | Loss | 1.98 | 1.98 |
| Accuracy (8p) | ACC1[78.8%] ACC5[94.2%] | ACC1[78.7%] ACC5[94.1%] | | Accuracy (8p) | ACC1[78.8%] ACC5[94.2%] | ACC1[78.7%] ACC5[94.1%] |
| Total time (8p) | 11h | 72h | | Total time (8p) | 11h | 72h |
| Params (M) | 103M | 103M | | Params (M) | 103M | 103M |
| Checkpoint for Fine tuning | 313M | 312M | | Checkpoint for Fine tuning | 313M | 312M |
| Scripts | [inceptionv3 script](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/inceptionv3) | [inceptionv3 script](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/inceptionv3) | | Scripts | [inceptionv3 script](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/inceptionv3) | [inceptionv3 script](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/inceptionv3) |
...@@ -237,15 +239,15 @@ metric: {'Loss': 1.778, 'Top1-Acc':0.788, 'Top5-Acc':0.942} ...@@ -237,15 +239,15 @@ metric: {'Loss': 1.778, 'Top1-Acc':0.788, 'Top5-Acc':0.942}
#### Inference Performance #### Inference Performance
| Parameters | InceptionV3 | | Parameters | Ascend |
| ------------------- | --------------------------- | | ------------------- | --------------------------- |
| Model Version | V1 | | Model Version | InceptionV3 |
| Resource | Ascend 910 | | Resource | Ascend 910, cpu:2.60GHz 56cores, memory:314G |
| Uploaded Date | 08/22/2020 (month/day/year) | | Uploaded Date | 08/22/2020 |
| MindSpore Version | 0.6.0-beta | | MindSpore Version | 0.6.0-beta |
| Dataset | 50k images | | Dataset | 50k images |
| batch_size | 128 | | Batch_size | 128 |
| outputs | probability | | Outputs | probability |
| Accuracy | ACC1[78.8%] ACC5[94.2%] | | Accuracy | ACC1[78.8%] ACC5[94.2%] |
| Total time | 2mins | | Total time | 2mins |
| Model for inference | 92M (.onnx file) | | Model for inference | 92M (.onnx file) |
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或