p47068915
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

opt maskrnn preprocessing pref

This commit is contained in:
gengdongjie 2020-10-26 10:54:37 +08:00
parent d2b1e783e7
commit c8268df1d1
2 changed files with 11 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
model_zoo/official/cv/maskrcnn/README.md
View File

@ -35,6 +35,9 @@ MaskRCNN is a two-stage target detection network. It extends FasterRCNN by addin
[Paper](http://cn.arxiv.org/pdf/1703.06870v3): Kaiming He, Georgia Gkioxari, Piotr Dollar and Ross Girshick. "MaskRCNN" [Paper](http://cn.arxiv.org/pdf/1703.06870v3): Kaiming He, Georgia Gkioxari, Piotr Dollar and Ross Girshick. "MaskRCNN"
# [Dataset](#contents) # [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.
- [COCO2017](https://cocodataset.org/) is a popular dataset with bounding-box and pixel-level stuff annotations. These annotations can be used for scene understanding tasks like semantic segmentation, object detection and image captioning. There are 118K/5K images for train/val. - [COCO2017](https://cocodataset.org/) is a popular dataset with bounding-box and pixel-level stuff annotations. These annotations can be used for scene understanding tasks like semantic segmentation, object detection and image captioning. There are 118K/5K images for train/val.
- Dataset size: 19G - Dataset size: 19G
@ -398,12 +401,12 @@ Accumulating evaluation results...
### Evaluation Performance ### Evaluation Performance
| Parameters | MaskRCNN | | Parameters | Ascend |
| -------------------------- | ----------------------------------------------------------- | | -------------------------- | ----------------------------------------------------------- |
| Model Version | V1 | | Model Version | V1 |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory, 755G | | Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory, 755G |
| uploaded Date | 08/01/2020 (month/day/year) | | uploaded Date | 08/01/2020 (month/day/year) |
| MindSpore Version | 0.6.0-alpha | | MindSpore Version | 1.0.0 |
| Dataset | COCO2017 | | Dataset | COCO2017 |
| Training Parameters | epoch=12, batch_size = 2 | | Training Parameters | epoch=12, batch_size = 2 |
| Optimizer | SGD | | Optimizer | SGD |
@ -420,12 +423,12 @@ Accumulating evaluation results...
### Inference Performance ### Inference Performance
| Parameters | MaskRCNN | | Parameters | Ascend |
| ------------------- | --------------------------- | | ------------------- | --------------------------- |
| Model Version | V1 | | Model Version | V1 |
| Resource | Ascend 910 | | Resource | Ascend 910 |
| Uploaded Date | 08/01/2020 (month/day/year) | | Uploaded Date | 08/01/2020 (month/day/year) |
| MindSpore Version | 0.6.0-alpha | | MindSpore Version | 1.0.0 |
| Dataset | COCO2017 | | Dataset | COCO2017 |
| batch_size | 2 | | batch_size | 2 |
| outputs | mAP | | outputs | mAP |

6
model_zoo/official/cv/maskrcnn/src/dataset.py
View File

@ -301,10 +301,8 @@ def pad_to_max(img, img_shape, gt_bboxes, gt_label, gt_num, gt_mask, instance_co
gt_label_new = np.pad(gt_label, ((0, pad_max_number - instance_count)), mode="constant", constant_values=-1) gt_label_new = np.pad(gt_label, ((0, pad_max_number - instance_count)), mode="constant", constant_values=-1)
gt_iscrowd_new = np.pad(gt_num, ((0, pad_max_number - instance_count)), mode="constant", constant_values=1) gt_iscrowd_new = np.pad(gt_num, ((0, pad_max_number - instance_count)), mode="constant", constant_values=1)
gt_iscrowd_new_revert = ~(gt_iscrowd_new.astype(np.bool)) gt_iscrowd_new_revert = ~(gt_iscrowd_new.astype(np.bool))
gt_mask_new = np.pad(gt_mask, ((0, pad_max_number - instance_count), (0, 0), (0, 0)), mode="constant",
constant_values=0)
return img, img_shape, gt_box_new, gt_label_new, gt_iscrowd_new_revert, gt_mask_new return img, img_shape, gt_box_new, gt_label_new, gt_iscrowd_new_revert, gt_mask
def preprocess_fn(image, box, mask, mask_shape, is_training): def preprocess_fn(image, box, mask, mask_shape, is_training):
"""Preprocess function for dataset.""" """Preprocess function for dataset."""
@ -518,7 +516,7 @@ def create_maskrcnn_dataset(mindrecord_file, batch_size=2, device_num=1, rank_id
column_order=["image", "image_shape", "box", "label", "valid_num", "mask"], column_order=["image", "image_shape", "box", "label", "valid_num", "mask"],
python_multiprocessing=False, python_multiprocessing=False,
num_parallel_workers=num_parallel_workers) num_parallel_workers=num_parallel_workers)
ds = ds.batch(batch_size, drop_remainder=True) ds = ds.batch(batch_size, drop_remainder=True, pad_info={"mask": ([config.max_instance_count, None, None], 0)})
else: else:
ds = ds.map(operations=compose_map_func, ds = ds.map(operations=compose_map_func,