Open feixiangdekaka opened 5 years ago
So,how to use this autoaugment_util.py file?could you please give me a example?Thanks
So,how to use this autoaugment_util.py file?could you please give me a example?Thanks
In detection.dataloader.retinanet_parser.py line 221
` if self._use_autoaugment:
image, boxes = autoaugment_utils.distort_image_with_autoaugment(
image, boxes, self._autoaugment_policy_name)`
make self._autoaugment_policy_name='v0'
does it work on coco? I found several bugs in autoaugment_utils.py.
Yes it does work on COCO. What bugs did you find in autoaugment_utils.py?
I think I didn"t meet bugs here
Yes it does work on COCO. What bugs did you find in autoaugment_utils.py?
Yes it does work on COCO. What bugs did you find in autoaugment_utils.py?
- When it does bbox only flip / shear / translate, if a bbox has box in it, it will cause the smaller bboxes mismatch with correspoinding objects.
- if a bbox is out of image range after a transform, the box will still exist in image, and it's shape is totally wrong.
I can't reply you the first question,. The second question's answer is that : it's not wrong , this is what augment should do .This situation has been displayed in their paper.
Yes it does work on COCO. What bugs did you find in autoaugment_utils.py?
- When it does bbox only flip / shear / translate, if a bbox has box in it, it will cause the smaller bboxes mismatch with correspoinding objects.
- if a bbox is out of image range after a transform, the box will still exist in image, and it's shape is totally wrong.
I can't reply you the first question,. The second question's answer is that : it's not wrong , this is what augment should do .This situation has been displayed in their paper.
But in my experiments, If I do not fix these 'bugs', mAP on COCO only achieves 10.5%。after I fix these, mAP start to be resonable.
Yes it does work on COCO. What bugs did you find in autoaugment_utils.py?
- When it does bbox only flip / shear / translate, if a bbox has box in it, it will cause the smaller bboxes mismatch with correspoinding objects.
- if a bbox is out of image range after a transform, the box will still exist in image, and it's shape is totally wrong.
I can't reply you the first question,. The second question's answer is that : it's not wrong , this is what augment should do .This situation has been displayed in their paper.
But in my experiments, If I do not fix these 'bugs', mAP on COCO only achieves 10.5%。after I fix these, mAP start to be resonable.
When these two bugs which you said above been applied in training , it means the unstable increased in training data . Did you run more 5 or 10 epoch in training . If MAP in test_data correspoinding increased , it meas it's not a bug , or if MAP doesn't changed ,I think you are right . If you do these experiment above , please inform me.
Yes it does work on COCO. What bugs did you find in autoaugment_utils.py?
- When it does bbox only flip / shear / translate, if a bbox has box in it, it will cause the smaller bboxes mismatch with correspoinding objects.
- if a bbox is out of image range after a transform, the box will still exist in image, and it's shape is totally wrong.
I can't reply you the first question,. The second question's answer is that : it's not wrong , this is what augment should do .This situation has been displayed in their paper.
But in my experiments, If I do not fix these 'bugs', mAP on COCO only achieves 10.5%。after I fix these, mAP start to be resonable.
When these two bugs which you said above been applied in training , it means the unstable increased in training data . Did you run more 5 or 10 epoch in training . If MAP in test_data correspoinding increased , it meas it's not a bug , or if MAP doesn't changed ,I think you are right . If you do these experiment above , please inform me.
Have you tried on COCO?
Yes it does work on COCO. What bugs did you find in autoaugment_utils.py?
- When it does bbox only flip / shear / translate, if a bbox has box in it, it will cause the smaller bboxes mismatch with correspoinding objects.
- if a bbox is out of image range after a transform, the box will still exist in image, and it's shape is totally wrong.
I can't reply you the first question,. The second question's answer is that : it's not wrong , this is what augment should do .This situation has been displayed in their paper.
But in my experiments, If I do not fix these 'bugs', mAP on COCO only achieves 10.5%。after I fix these, mAP start to be resonable.
When these two bugs which you said above been applied in training , it means the unstable increased in training data . Did you run more 5 or 10 epoch in training . If MAP in test_data correspoinding increased , it meas it's not a bug , or if MAP doesn't changed ,I think you are right . If you do these experiment above , please inform me.
Have you tried on COCO?
COCO is a little large for my 1050ti (:
I've convert the tf version to numpy, so everyone can run using any dl framework.
https://github.com/poodarchu/learn_aug_for_object_detection.numpy
Great work ,thanks for sharing
@BarretZoph @aman2930 @saberkun I think I've found another bug for Learning Data Augmentation Strategies for Object Detection seen above link, in which an image is augmented as many time as the number of bboxes in it. Assuming we are augmenting the bboxes and images by random flipping, in this case, each bbox is flipped by a probability P, but the image will be flip many times and the probability is not equal to P.
Yes it does work on COCO. What bugs did you find in autoaugment_utils.py?
- When it does bbox only flip / shear / translate, if a bbox has box in it, it will cause the smaller bboxes mismatch with correspoinding objects.
- if a bbox is out of image range after a transform, the box will still exist in image, and it's shape is totally wrong.
Yes these two things do occur, but the performance is still good on COCO. Some of these could actually potentially benefit the training by acting as a regularizer.
I have since fixed 2 and noticed that on COCO the performance on ResNet-50 improves by about 0 to 0.2 mAP depending on the augmentation policy. I am playing around with both fixes to see if the performance could be better improved still, but the performance in the paper is obtained with both of these features in it.
@BarretZoph @aman2930 @saberkun I think I've found another bug for Learning Data Augmentation Strategies for Object Detection seen above link, in which an image is augmented as many time as the number of bboxes in it. Assuming we are augmenting the bboxes and images by random flipping, in this case, each bbox is flipped by a probability P, but the image will be flip many times and the probability is not equal to P.
I am not sure I understand this. There operations that are applied I.I.D to each bbox with the image.
Yes it does work on COCO. What bugs did you find in autoaugment_utils.py?
- When it does bbox only flip / shear / translate, if a bbox has box in it, it will cause the smaller bboxes mismatch with correspoinding objects.
- if a bbox is out of image range after a transform, the box will still exist in image, and it's shape is totally wrong.
I can't reply you the first question,. The second question's answer is that : it's not wrong , this is what augment should do .This situation has been displayed in their paper.
But in my experiments, If I do not fix these 'bugs', mAP on COCO only achieves 10.5%。after I fix these, mAP start to be resonable.
@poodarchu What AP did you get when these bugs got fixed? BTW, could you share the fixed version? Thanks.
Just to clarify, with the two issues listed above, you should be able to reproduce the results in the original paper. When fixing them I found little to no mAP performance improvement on COCO.
When using augmentation, it triggers https://github.com/tensorflow/tpu/blob/master/models/official/detection/utils/autoaugment_utils.py#L15
Yaml config is https://github.com/tensorflow/tpu/blob/master/models/official/detection/configs/yaml/retinanet_autoaugment.yaml
Excuse me, where is the code of the RNN controller?
This method works for small objects?
Where is the code for implement the 《Learning Data Augmentation Strategies for Object Detection》?