Patta
Image Test Time Augmentation with Paddle2.0!
Input
| # input batch of images
/ / /|\ \ \ # apply augmentations (flips, rotation, scale, etc.)
| | | | | | | # pass augmented batches through model
| | | | | | | # reverse transformations for each batch of masks/labels
\ \ \ / / / # merge predictions (mean, max, gmean, etc.)
| # output batch of masks/labels
Output
Table of Contents
Quick start (Default Transforms)
Test
We support that you can use the following to test after defining the network.
Segmentation model wrapping [docstring]:
import patta as tta
tta_model = tta.SegmentationTTAWrapper(model, tta.aliases.d4_transform(), merge_mode='mean')
Classification model wrapping [docstring]:
tta_model = tta.ClassificationTTAWrapper(model, tta.aliases.five_crop_transform())
Keypoints model wrapping [docstring]:
tta_model = tta.KeypointsTTAWrapper(model, tta.aliases.flip_transform(), scaled=True)
Note: the model must return keypoints in the format Tensor([x1, y1, ..., xn, yn])
Predict
We support that you can use the following to test when you have the static model: *.pdmodel、*.pdiparams、*.pdiparams.info.
Load model [docstring]:
import patta as tta
model = tta.load_model(path='output/model')
Segmentation model wrapping [docstring]:
tta_model = tta.SegmentationTTAWrapper(model, tta.aliases.d4_transform(), merge_mode='mean')
Classification model wrapping [docstring]:
tta_model = tta.ClassificationTTAWrapper(model, tta.aliases.five_crop_transform())
Keypoints model wrapping [docstring]:
tta_model = tta.KeypointsTTAWrapper(model, tta.aliases.flip_transform(), scaled=True)
Use-Tools
Segmentation model [docstring]:
We recommend modifying the file seg.py according to your own model.
python seg.py --model_path='output/model' \
--batch_size=16 \
--test_dataset='test.txt'
Note: Related to paddleseg
Advanced-Examples (DIY Transforms)
Custom transform:
# defined 2 * 2 * 3 * 3 = 36 augmentations !
transforms = tta.Compose(
[
tta.HorizontalFlip(),
tta.Rotate90(angles=[0, 180]),
tta.Scale(scales=[1, 2, 4]),
tta.Multiply(factors=[0.9, 1, 1.1]),
]
)
tta_model = tta.SegmentationTTAWrapper(model, transforms)
Custom model (multi-input / multi-output)
# Example how to process ONE batch on images with TTA
# Here `image`/`mask` are 4D tensors (B, C, H, W), `label` is 2D tensor (B, N)
for transformer in transforms: # custom transforms or e.g. tta.aliases.d4_transform()
# augment image
augmented_image = transformer.augment_image(image)
# pass to model
model_output = model(augmented_image, another_input_data)
# reverse augmentation for mask and label
deaug_mask = transformer.deaugment_mask(model_output['mask'])
deaug_label = transformer.deaugment_label(model_output['label'])
# save results
labels.append(deaug_mask)
masks.append(deaug_label)
# reduce results as you want, e.g mean/max/min
label = mean(labels)
mask = mean(masks)
Optional Transforms
| Transform | Parameters | Values |
|---|---|---|
| HorizontalFlip | - | - |
| VerticalFlip | - | - |
| Rotate90 | angles | List[0, 90, 180, 270] |
| Scale | scales interpolation |
List[float] "nearest"/"linear" |
| Resize | sizes original_size interpolation |
List[Tuple[int, int]] Tuple[int,int] "nearest"/"linear" |
| Add | values | List[float] |
| Multiply | factors | List[float] |
| FiveCrops | crop_height crop_width |
int int |
Aliases (Combos)
- flip_transform (horizontal + vertical flips)
- hflip_transform (horizontal flip)
- d4_transform (flips + rotation 0, 90, 180, 270)
- multiscale_transform (scale transform, take scales as input parameter)
- five_crop_transform (corner crops + center crop)
- ten_crop_transform (five crops + five crops on horizontal flip)
Merge-modes
- mean
- gmean (geometric mean)
- sum
- max
- min
- tsharpen (temperature sharpen with t=0.5)
Installation
PyPI:
# After downloading the whole dir
$ git clone https://github.com/AgentMaker/PaTTA.git
$ pip install PaTTA/
# or
$ pip install git+https://github.com/AgentMaker/PaTTA.git
Run tests
# run test_transforms.py and test_base.py for test
python test/test_transforms.py
python test/test_base.py
2 Dec 23, 2021
5 Oct 29, 2022
399 Jan 05, 2023
1.5k Jan 02, 2023
54 Dec 03, 2022
74 Dec 10, 2021
129 Dec 17, 2022
579 Jan 08, 2023
14 Nov 01, 2022
15 Dec 11, 2022
7 Nov 24, 2022
353 Dec 31, 2022
10 Apr 30, 2022
95 Jan 05, 2023
2 Oct 02, 2022
116 Dec 27, 2022
111 Dec 23, 2022
317 Dec 18, 2022
6 Nov 08, 2022
2.3k Dec 29, 2022