Skip to content

M
mindspore

magicwindyyd / mindspore
与 Fork 源项目一致

Fork自 MindSpore / mindspore

通知 1
Star 1
Fork 0
M
mindspore
提交 e0b8302a 编写于 作者: H hanhuifeng2020
浏览文件
操作

improve performance for yolov3_darknet53 and update performance data to readme

上级 57215ef0
隐藏空白更改
内联 并排
Showing with 36 addition and 36 deletion
model_zoo/official/cv/yolov3_darknet53/README.md
浏览文件 @ e0b8302a
......@@ -302,38 +302,38 @@ The above python command will run in the background. You can view the results th
### Evaluation Performance
| Parameters | YOLO |
| -------------------------- | ----------------------------------------------------------- |
| Model Version | YOLOv3 |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory, 755G |
| uploaded Date | 06/31/2020 (month/day/year) |
| MindSpore Version | 0.5.0-alpha |
| Dataset | COCO2014 |
| Training Parameters | epoch=320, batch_size=32, lr=0.001, momentum=0.9 |
| Optimizer | Momentum |
| Loss Function | Sigmoid Cross Entropy with logits |
| outputs | boxes and label |
| Loss | 34 |
| Speed | 1pc: 350 ms/step; |
| Total time | 8pc: 25 hours |
| Parameters (M) | 62.1 |
| Checkpoint for Fine tuning | 474M (.ckpt file) |
| Scripts | https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/yolov3_darknet53 |
| Parameters | YOLO |YOLO |
| -------------------------- | ----------------------------------------------------------- |----------------------------------------------------------- |
| 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 |
| 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 |
| Loss Function | Sigmoid Cross Entropy with logits | Sigmoid Cross Entropy with logits |
| outputs | boxes and label | boxes and label |
| Loss | 34 | 34 |
| Speed | 1pc: 350 ms/step; | 1pc: 600 ms/step; |
| Total time | 8pc: 25 hours | 8pc: 18 hours(shape=416) |
| Parameters (M) | 62.1 | 62.1 |
| Checkpoint for Fine tuning | 474M (.ckpt file) | 474M (.ckpt file) |
| Scripts | https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/yolov3_darknet53 | https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/yolov3_darknet53 |
### Inference Performance
| Parameters | YOLO |
| ------------------- | --------------------------- |
| Model Version | YOLOv3 |
| Resource | Ascend 910 |
| Uploaded Date | 06/31/2020 (month/day/year) |
| MindSpore Version | 0.5.0-alpha |
| Dataset | COCO2014, 40,504 images |
| batch_size | 1 |
| outputs | mAP |
| Accuracy | 8pcs: 31.1% |
| Model for inference | 474M (.ckpt file) |
| Parameters | YOLO |YOLO |
| ------------------- | --------------------------- |------------------------------|
| 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 |
| Dataset | COCO2014, 40,504 images | COCO2014, 40,504 images |
| batch_size | 1 | 1 |
| outputs | mAP | mAP |
| Accuracy | 8pcs: 31.1% | 8pcs: 29.7%~30.3% (shape=416)|
| Model for inference | 474M (.ckpt file) | 474M (.ckpt file) |
# [Description of Random Situation](#contents)
......
model_zoo/official/cv/yolov3_darknet53/train.py
浏览文件 @ e0b8302a
......@@ -304,14 +304,14 @@ def train():
input_shape = images.shape[2:4]
args.logger.info('iter[{}], shape{}'.format(i, input_shape[0]))
images = Tensor(images)
batch_y_true_0 = Tensor(data['bbox1'])
batch_y_true_1 = Tensor(data['bbox2'])
batch_y_true_2 = Tensor(data['bbox3'])
batch_gt_box0 = Tensor(data['gt_box1'])
batch_gt_box1 = Tensor(data['gt_box2'])
batch_gt_box2 = Tensor(data['gt_box3'])
images = Tensor.from_numpy(images)
batch_y_true_0 = Tensor.from_numpy(data['bbox1'])
batch_y_true_1 = Tensor.from_numpy(data['bbox2'])
batch_y_true_2 = Tensor.from_numpy(data['bbox3'])
batch_gt_box0 = Tensor.from_numpy(data['gt_box1'])
batch_gt_box1 = Tensor.from_numpy(data['gt_box2'])
batch_gt_box2 = Tensor.from_numpy(data['gt_box3'])
input_shape = Tensor(tuple(input_shape[::-1]), ms.float32)
loss = network(images, batch_y_true_0, batch_y_true_1, batch_y_true_2, batch_gt_box0, batch_gt_box1,
......
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