-
Notifications
You must be signed in to change notification settings - Fork 1.1k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
10 changed files
with
264 additions
and
25 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Large diffs are not rendered by default.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,83 @@ | ||
| # Copyright (c) OpenMMLab. All rights reserved. | ||
| import os | ||
| from typing import Dict, List | ||
|
|
||
| import numpy as np | ||
| from mmengine import mkdir_or_exist | ||
| from torchvision.utils import save_image | ||
|
|
||
| from .base_mmedit_inferencer import BaseMMEditInferencer, InputsType, PredType | ||
|
|
||
|
|
||
| class Text2ImageInferencer(BaseMMEditInferencer): | ||
| """inferencer that predicts with text2image models.""" | ||
|
|
||
| func_kwargs = dict( | ||
| preprocess=['text'], | ||
| forward=[], | ||
| visualize=['result_out_dir'], | ||
| postprocess=[]) | ||
|
|
||
| extra_parameters = dict( | ||
| scheduler_kwargs=None, | ||
| height=None, | ||
| width=None, | ||
| init_image=None, | ||
| batch_size=1, | ||
| num_inference_steps=1000, | ||
| skip_steps=0, | ||
| show_progress=False, | ||
| text_prompts=[], | ||
| image_prompts=[], | ||
| eta=0.8, | ||
| clip_guidance_scale=5000, | ||
| init_scale=1000, | ||
| tv_scale=0., | ||
| sat_scale=0., | ||
| range_scale=150, | ||
| cut_overview=[12] * 400 + [4] * 600, | ||
| cut_innercut=[4] * 400 + [12] * 600, | ||
| cut_ic_pow=[1] * 1000, | ||
| cut_icgray_p=[0.2] * 400 + [0] * 600, | ||
| cutn_batches=4, | ||
| seed=2022) | ||
|
|
||
| def preprocess(self, text: InputsType) -> Dict: | ||
| """Process the inputs into a model-feedable format. | ||
| Args: | ||
| text(InputsType): text input for text-to-image model. | ||
| Returns: | ||
| result(Dict): Results of preprocess. | ||
| """ | ||
| result = self.extra_parameters | ||
| result['text_prompts'] = text | ||
|
|
||
| return result | ||
|
|
||
| def forward(self, inputs: InputsType) -> PredType: | ||
| """Forward the inputs to the model.""" | ||
| image = self.model.infer(**inputs)['samples'] | ||
|
|
||
| return image | ||
|
|
||
| def visualize(self, | ||
| preds: PredType, | ||
| result_out_dir: str = None) -> List[np.ndarray]: | ||
| """Visualize predictions. | ||
| Args: | ||
| preds (List[Union[str, np.ndarray]]): Forward results | ||
| by the inferencer. | ||
| result_out_dir (str): Output directory of image. | ||
| Defaults to ''. | ||
| Returns: | ||
| List[np.ndarray]: Result of visualize | ||
| """ | ||
| if result_out_dir: | ||
| mkdir_or_exist(os.path.dirname(result_out_dir)) | ||
| save_image(preds, result_out_dir, normalize=True) | ||
|
|
||
| return preds |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
33 changes: 33 additions & 0 deletions
33
tests/test_apis/test_inferencers/test_text2image_inferencers.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,33 @@ | ||
| # Copyright (c) OpenMMLab. All rights reserved. | ||
| import os.path as osp | ||
|
|
||
| import pytest | ||
| import torch | ||
|
|
||
| from mmedit.apis.inferencers.text2image_inferencer import Text2ImageInferencer | ||
| from mmedit.utils import register_all_modules | ||
|
|
||
| register_all_modules() | ||
|
|
||
|
|
||
| @pytest.mark.skipif(not torch.cuda.is_available(), reason='requires cuda') | ||
| def test_translation_inferencer(): | ||
| cfg = osp.join( | ||
| osp.dirname(__file__), '..', '..', '..', 'configs', 'disco_diffusion', | ||
| 'disco-diffusion_adm-u-finetuned_imagenet-512x512.py') | ||
| text = {0: ['sad']} | ||
| result_out_dir = osp.join( | ||
| osp.dirname(__file__), '..', '..', 'data', 'disco_result.png') | ||
|
|
||
| inferencer_instance = \ | ||
| Text2ImageInferencer( | ||
| cfg, None, extra_parameters={'num_inference_steps': 2}) | ||
| inferencer_instance(text=text) | ||
| inference_result = inferencer_instance( | ||
| text=text, result_out_dir=result_out_dir) | ||
| result_img = inference_result[1] | ||
| assert result_img[0].cpu().numpy().shape == (3, 512, 512) | ||
|
|
||
|
|
||
| if __name__ == '__main__': | ||
| test_translation_inferencer() |