forked from mindspore-Ecosystem/mindspore
!7850 modify mindspore version info about ssd&yolov3 README
Merge pull request !7850 from chengxb7532/master
This commit is contained in:
Gitee
commit
c79f245b2c
|
|
@ -31,6 +31,8 @@ SSD discretizes the output space of bounding boxes into a set of default boxes o
|
|||
The SSD approach is based on a feed-forward convolutional network that produces a fixed-size collection of bounding boxes and scores for the presence of object class instances in those boxes, followed by a non-maximum suppression step to produce the final detections. The early network layers are based on a standard architecture used for high quality image classification, which is called the base network. Then add auxiliary structure to the network to produce detections.
|
||||
|
||||
# [Dataset](#contents)
|
||||
Note that you can run the scripts based on the dataset mentioned in original paper or widely used in relevant domain/network architecture. In the following sections, we will introduce how to run the scripts using the related dataset below.
|
||||
|
||||
Dataset used: [COCO2017](<http://images.cocodataset.org/>)
|
||||
|
||||
- Dataset size：19G
|
||||
|
|
@ -299,14 +301,14 @@ mAP: 0.2244936111705981
|
|||
| -------------------------- | -------------------------------------------------------------| -------------------------------------------------------------|
|
||||
| Model Version | SSD V1 | SSD V1 |
|
||||
| Resource | Ascend 910 ；CPU 2.60GHz，192cores；Memory，755G | NV SMX2 V100-16G |
|
||||
| uploaded Date | 06/01/2020 (month/day/year) | 09/24/2020 (month/day/year) |
|
||||
| MindSpore Version | 0.3.0-alpha | 1.0.0 |
|
||||
| uploaded Date | 09/15/2020 (month/day/year) | 09/24/2020 (month/day/year) |
|
||||
| MindSpore Version | 1.0.0 | 1.0.0 |
|
||||
| Dataset | COCO2017 | COCO2017 |
|
||||
| Training Parameters | epoch = 500, batch_size = 32 | epoch = 800, batch_size = 32 |
|
||||
| Optimizer | Momentum | Momentum |
|
||||
| Loss Function | Sigmoid Cross Entropy,SmoothL1Loss | Sigmoid Cross Entropy,SmoothL1Loss |
|
||||
| Speed | 8pcs: 90ms/step | 8pcs: 121ms/step |
|
||||
| Total time | 8pcs: 4.81hours | 8pcs: 12.31hours |
|
||||
| Total time | 8pcs: 4.81hours | 8pcs: 12.31hours |
|
||||
| Parameters (M) | 34 | 34 |
|
||||
| Scripts | https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/ssd | https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/ssd |
|
||||
|
||||
|
|
@ -317,8 +319,8 @@ mAP: 0.2244936111705981
|
|||
| ------------------- | ----------------------------| ----------------------------|
|
||||
| Model Version | SSD V1 | SSD V1 |
|
||||
| Resource | Ascend 910 | GPU |
|
||||
| Uploaded Date | 06/01/2020 (month/day/year) | 09/24/2020 (month/day/year) |
|
||||
| MindSpore Version | 0.3.0-alpha | 1.0.0 |
|
||||
| Uploaded Date | 09/15/2020 (month/day/year) | 09/24/2020 (month/day/year) |
|
||||
| MindSpore Version | 1.0.0 | 1.0.0 |
|
||||
| Dataset | COCO2017 | COCO2017 |
|
||||
| batch_size | 1 | 1 |
|
||||
| outputs | mAP | mAP |
|
||||
|
|
|
|||
|
|
@ -40,6 +40,7 @@ YOLOv3 use DarkNet53 for performing feature extraction, which is a hybrid approa
|
|||
|
||||
|
||||
# [Dataset](#contents)
|
||||
Note that you can run the scripts based on the dataset mentioned in original paper or widely used in relevant domain/network architecture. In the following sections, we will introduce how to run the scripts using the related dataset below.
|
||||
|
||||
Dataset used: [COCO2014](https://cocodataset.org/#download)
|
||||
|
||||
|
|
@ -307,8 +308,8 @@ The above python command will run in the background. You can view the results th
|
|||
| -------------------------- | ----------------------------------------------------------- |------------------------------------------------------------ |
|
||||
| Model Version | YOLOv3 |YOLOv3 |
|
||||
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory, 755G | NV SMX2 V100-16G; CPU 2.10GHz, 96cores; Memory, 251G |
|
||||
| uploaded Date | 06/31/2020 (month/day/year) | 09/02/2020 (month/day/year) |
|
||||
| MindSpore Version | 0.5.0-alpha | 0.7.0 |
|
||||
| uploaded Date | 09/15/2020 (month/day/year) | 09/02/2020 (month/day/year) |
|
||||
| MindSpore Version | 1.0.0 | 1.0.0 |
|
||||
| Dataset | COCO2014 | COCO2014 |
|
||||
| Training Parameters | epoch=320, batch_size=32, lr=0.001, momentum=0.9 | epoch=320, batch_size=32, lr=0.001, momentum=0.9 |
|
||||
| Optimizer | Momentum | Momentum |
|
||||
|
|
@ -328,8 +329,8 @@ The above python command will run in the background. You can view the results th
|
|||
| ------------------- | --------------------------- |------------------------------|
|
||||
| Model Version | YOLOv3 | YOLOv3 |
|
||||
| Resource | Ascend 910 | NV SMX2 V100-16G |
|
||||
| Uploaded Date | 06/31/2020 (month/day/year) | 08/20/2020 (month/day/year) |
|
||||
| MindSpore Version | 0.5.0-alpha | 0.7.0 |
|
||||
| Uploaded Date | 09/15/2020 (month/day/year) | 08/20/2020 (month/day/year) |
|
||||
| MindSpore Version | 1.0.0 | 1.0.0 |
|
||||
| Dataset | COCO2014, 40,504 images | COCO2014, 40,504 images |
|
||||
| batch_size | 1 | 1 |
|
||||
| outputs | mAP | mAP |
|
||||
|
|
|
|||
|
|
@ -42,6 +42,7 @@ YOLOv3 use DarkNet53 for performing feature extraction, which is a hybrid approa
|
|||
|
||||
|
||||
# [Dataset](#contents)
|
||||
Note that you can run the scripts based on the dataset mentioned in original paper or widely used in relevant domain/network architecture. In the following sections, we will introduce how to run the scripts using the related dataset below.
|
||||
|
||||
Dataset used: [COCO2014](https://cocodataset.org/#download)
|
||||
|
||||
|
|
@ -276,8 +277,8 @@ Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.558
|
|||
| -------------------------- | ---------------------------------------------------------------------------------------------- |
|
||||
| Model Version | YOLOv3_Darknet53_Quant V1 |
|
||||
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory, 755G |
|
||||
| uploaded Date | 06/31/2020 (month/day/year) |
|
||||
| MindSpore Version | 0.6.0-alpha |
|
||||
| uploaded Date | 09/15/2020 (month/day/year) |
|
||||
| MindSpore Version | 1.0.0 |
|
||||
| Dataset | COCO2014 |
|
||||
| Training Parameters | epoch=135, batch_size=16, lr=0.012, momentum=0.9 |
|
||||
| Optimizer | Momentum |
|
||||
|
|
@ -297,8 +298,8 @@ Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.558
|
|||
| ------------------- | --------------------------- |
|
||||
| Model Version | YOLOv3_Darknet53_Quant V1 |
|
||||
| Resource | Ascend 910 |
|
||||
| Uploaded Date | 06/31/2020 (month/day/year) |
|
||||
| MindSpore Version | 0.6.0-alpha |
|
||||
| Uploaded Date | 09/15/2020 (month/day/year) |
|
||||
| MindSpore Version | 1.0.0 |
|
||||
| Dataset | COCO2014, 40,504 images |
|
||||
| batch_size | 1 |
|
||||
| outputs | mAP |
|
||||
|
|
|
|||
|
|
@ -34,6 +34,7 @@ And we use ResNet18 as the backbone of YOLOv3_ResNet18. The architecture of ResN
|
|||
|
||||
|
||||
# [Dataset](#contents)
|
||||
Note that you can run the scripts based on the dataset mentioned in original paper or widely used in relevant domain/network architecture. In the following sections, we will introduce how to run the scripts using the related dataset below.
|
||||
|
||||
Dataset used: [COCO2017](<http://images.cocodataset.org/>)
|
||||
|
||||
|
|
@ -200,35 +201,35 @@ Note the precision and recall values are results of two-classification(person an
|
|||
|
||||
### Evaluation Performance
|
||||
|
||||
| Parameters | Ascend |
|
||||
| Parameters | Ascend |
|
||||
| -------------------------- | ----------------------------------------------------------- |
|
||||
| Model Version | YOLOv3_Resnet18 V1 |
|
||||
| Resource | Ascend 910 ；CPU 2.60GHz，192cores；Memory，755G |
|
||||
| uploaded Date | 06/01/2020 (month/day/year) |
|
||||
| MindSpore Version | 0.2.0-alpha |
|
||||
| Dataset | COCO2017 |
|
||||
| Resource | Ascend 910 ；CPU 2.60GHz，192cores；Memory，755G |
|
||||
| uploaded Date | 09/15/2020 (month/day/year) |
|
||||
| MindSpore Version | 1.0.0 |
|
||||
| Dataset | COCO2017 |
|
||||
| Training Parameters | epoch = 150, batch_size = 32, lr = 0.001 |
|
||||
| Optimizer | Adam |
|
||||
| Optimizer | Adam |
|
||||
| Loss Function | Sigmoid Cross Entropy |
|
||||
| outputs | probability |
|
||||
| Speed | 1pc: 120 ms/step; 8pcs: 160 ms/step |
|
||||
| Total time | 1pc: 150 mins; 8pcs: 70 mins |
|
||||
| Parameters (M) | 189 |
|
||||
| outputs | probability |
|
||||
| Speed | 1pc: 120 ms/step; 8pcs: 160 ms/step |
|
||||
| Total time | 1pc: 150 mins; 8pcs: 70 mins |
|
||||
| Parameters (M) | 189 |
|
||||
| Scripts | [yolov3_resnet18 script](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/yolov3_resnet18) | [yolov3_resnet18 script](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/yolov3_resnet18) |
|
||||
|
||||
|
||||
### Inference Performance
|
||||
|
||||
| Parameters | Ascend |
|
||||
| Parameters | Ascend |
|
||||
| ------------------- | ----------------------------------------------- |
|
||||
| Model Version | YOLOv3_Resnet18 V1 |
|
||||
| Model Version | YOLOv3_Resnet18 V1 |
|
||||
| Resource | Ascend 910 |
|
||||
| Uploaded Date | 06/01/2020 (month/day/year) |
|
||||
| MindSpore Version | 0.2.0-alpha |
|
||||
| Uploaded Date | 09/15/2020 (month/day/year) |
|
||||
| MindSpore Version | 1.0.0 |
|
||||
| Dataset | COCO2017 |
|
||||
| batch_size | 1 |
|
||||
| outputs | presion and recall |
|
||||
| Accuracy | class 0: 88.18%/66.00%; class 1: 85.34%/79.13% |
|
||||
| Accuracy | class 0: 88.18%/66.00%; class 1: 85.34%/79.13% |
|
||||
|
||||
# [Description of Random Situation](#contents)
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue