IOPaint/inpaint/plugins/segment_anything/utils/transforms.py
root 70af4845af new file: inpaint/__init__.py
new file:   inpaint/__main__.py
	new file:   inpaint/api.py
	new file:   inpaint/batch_processing.py
	new file:   inpaint/benchmark.py
	new file:   inpaint/cli.py
	new file:   inpaint/const.py
	new file:   inpaint/download.py
	new file:   inpaint/file_manager/__init__.py
	new file:   inpaint/file_manager/file_manager.py
	new file:   inpaint/file_manager/storage_backends.py
	new file:   inpaint/file_manager/utils.py
	new file:   inpaint/helper.py
	new file:   inpaint/installer.py
	new file:   inpaint/model/__init__.py
	new file:   inpaint/model/anytext/__init__.py
	new file:   inpaint/model/anytext/anytext_model.py
	new file:   inpaint/model/anytext/anytext_pipeline.py
	new file:   inpaint/model/anytext/anytext_sd15.yaml
	new file:   inpaint/model/anytext/cldm/__init__.py
	new file:   inpaint/model/anytext/cldm/cldm.py
	new file:   inpaint/model/anytext/cldm/ddim_hacked.py
	new file:   inpaint/model/anytext/cldm/embedding_manager.py
	new file:   inpaint/model/anytext/cldm/hack.py
	new file:   inpaint/model/anytext/cldm/model.py
	new file:   inpaint/model/anytext/cldm/recognizer.py
	new file:   inpaint/model/anytext/ldm/__init__.py
	new file:   inpaint/model/anytext/ldm/models/__init__.py
	new file:   inpaint/model/anytext/ldm/models/autoencoder.py
	new file:   inpaint/model/anytext/ldm/models/diffusion/__init__.py
	new file:   inpaint/model/anytext/ldm/models/diffusion/ddim.py
	new file:   inpaint/model/anytext/ldm/models/diffusion/ddpm.py
	new file:   inpaint/model/anytext/ldm/models/diffusion/dpm_solver/__init__.py
	new file:   inpaint/model/anytext/ldm/models/diffusion/dpm_solver/dpm_solver.py
	new file:   inpaint/model/anytext/ldm/models/diffusion/dpm_solver/sampler.py
	new file:   inpaint/model/anytext/ldm/models/diffusion/plms.py
	new file:   inpaint/model/anytext/ldm/models/diffusion/sampling_util.py
	new file:   inpaint/model/anytext/ldm/modules/__init__.py
	new file:   inpaint/model/anytext/ldm/modules/attention.py
	new file:   inpaint/model/anytext/ldm/modules/diffusionmodules/__init__.py
	new file:   inpaint/model/anytext/ldm/modules/diffusionmodules/model.py
	new file:   inpaint/model/anytext/ldm/modules/diffusionmodules/openaimodel.py
	new file:   inpaint/model/anytext/ldm/modules/diffusionmodules/upscaling.py
	new file:   inpaint/model/anytext/ldm/modules/diffusionmodules/util.py
	new file:   inpaint/model/anytext/ldm/modules/distributions/__init__.py
	new file:   inpaint/model/anytext/ldm/modules/distributions/distributions.py
	new file:   inpaint/model/anytext/ldm/modules/ema.py
	new file:   inpaint/model/anytext/ldm/modules/encoders/__init__.py
	new file:   inpaint/model/anytext/ldm/modules/encoders/modules.py
	new file:   inpaint/model/anytext/ldm/util.py
	new file:   inpaint/model/anytext/main.py
	new file:   inpaint/model/anytext/ocr_recog/RNN.py
	new file:   inpaint/model/anytext/ocr_recog/RecCTCHead.py
	new file:   inpaint/model/anytext/ocr_recog/RecModel.py
	new file:   inpaint/model/anytext/ocr_recog/RecMv1_enhance.py
	new file:   inpaint/model/anytext/ocr_recog/RecSVTR.py
	new file:   inpaint/model/anytext/ocr_recog/__init__.py
	new file:   inpaint/model/anytext/ocr_recog/common.py
	new file:   inpaint/model/anytext/ocr_recog/en_dict.txt
	new file:   inpaint/model/anytext/ocr_recog/ppocr_keys_v1.txt
	new file:   inpaint/model/anytext/utils.py
	new file:   inpaint/model/base.py
	new file:   inpaint/model/brushnet/__init__.py
	new file:   inpaint/model/brushnet/brushnet.py
	new file:   inpaint/model/brushnet/brushnet_unet_forward.py
	new file:   inpaint/model/brushnet/brushnet_wrapper.py
	new file:   inpaint/model/brushnet/pipeline_brushnet.py
	new file:   inpaint/model/brushnet/unet_2d_blocks.py
	new file:   inpaint/model/controlnet.py
	new file:   inpaint/model/ddim_sampler.py
	new file:   inpaint/model/fcf.py
	new file:   inpaint/model/helper/__init__.py
	new file:   inpaint/model/helper/controlnet_preprocess.py
	new file:   inpaint/model/helper/cpu_text_encoder.py
	new file:   inpaint/model/helper/g_diffuser_bot.py
	new file:   inpaint/model/instruct_pix2pix.py
	new file:   inpaint/model/kandinsky.py
	new file:   inpaint/model/lama.py
	new file:   inpaint/model/ldm.py
	new file:   inpaint/model/manga.py
	new file:   inpaint/model/mat.py
	new file:   inpaint/model/mi_gan.py
	new file:   inpaint/model/opencv2.py
	new file:   inpaint/model/original_sd_configs/__init__.py
	new file:   inpaint/model/original_sd_configs/sd_xl_base.yaml
	new file:   inpaint/model/original_sd_configs/sd_xl_refiner.yaml
	new file:   inpaint/model/original_sd_configs/v1-inference.yaml
	new file:   inpaint/model/original_sd_configs/v2-inference-v.yaml
	new file:   inpaint/model/paint_by_example.py
	new file:   inpaint/model/plms_sampler.py
	new file:   inpaint/model/power_paint/__init__.py
	new file:   inpaint/model/power_paint/pipeline_powerpaint.py
	new file:   inpaint/model/power_paint/power_paint.py
	new file:   inpaint/model/power_paint/power_paint_v2.py
	new file:   inpaint/model/power_paint/powerpaint_tokenizer.py
2024-08-20 21:17:33 +02:00

113 lines
4.0 KiB
Python

# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
import numpy as np
import torch
from torch.nn import functional as F
from torchvision.transforms.functional import resize, to_pil_image # type: ignore
from copy import deepcopy
from typing import Tuple
class ResizeLongestSide:
"""
Resizes images to longest side 'target_length', as well as provides
methods for resizing coordinates and boxes. Provides methods for
transforming both numpy array and batched torch tensors.
"""
def __init__(self, target_length: int) -> None:
self.target_length = target_length
def apply_image(self, image: np.ndarray) -> np.ndarray:
"""
Expects a numpy array with shape HxWxC in uint8 format.
"""
target_size = self.get_preprocess_shape(
image.shape[0], image.shape[1], self.target_length
)
return np.array(resize(to_pil_image(image), target_size))
def apply_coords(
self, coords: np.ndarray, original_size: Tuple[int, ...]
) -> np.ndarray:
"""
Expects a numpy array of length 2 in the final dimension. Requires the
original image size in (H, W) format.
"""
old_h, old_w = original_size
new_h, new_w = self.get_preprocess_shape(
original_size[0], original_size[1], self.target_length
)
coords = deepcopy(coords).astype(float)
coords[..., 0] = coords[..., 0] * (new_w / old_w)
coords[..., 1] = coords[..., 1] * (new_h / old_h)
return coords
def apply_boxes(
self, boxes: np.ndarray, original_size: Tuple[int, ...]
) -> np.ndarray:
"""
Expects a numpy array shape Bx4. Requires the original image size
in (H, W) format.
"""
boxes = self.apply_coords(boxes.reshape(-1, 2, 2), original_size)
return boxes.reshape(-1, 4)
def apply_image_torch(self, image: torch.Tensor) -> torch.Tensor:
"""
Expects batched images with shape BxCxHxW and float format. This
transformation may not exactly match apply_image. apply_image is
the transformation expected by the model.
"""
# Expects an image in BCHW format. May not exactly match apply_image.
target_size = self.get_preprocess_shape(
image.shape[0], image.shape[1], self.target_length
)
return F.interpolate(
image, target_size, mode="bilinear", align_corners=False, antialias=True
)
def apply_coords_torch(
self, coords: torch.Tensor, original_size: Tuple[int, ...]
) -> torch.Tensor:
"""
Expects a torch tensor with length 2 in the last dimension. Requires the
original image size in (H, W) format.
"""
old_h, old_w = original_size
new_h, new_w = self.get_preprocess_shape(
original_size[0], original_size[1], self.target_length
)
coords = deepcopy(coords).to(torch.float)
coords[..., 0] = coords[..., 0] * (new_w / old_w)
coords[..., 1] = coords[..., 1] * (new_h / old_h)
return coords
def apply_boxes_torch(
self, boxes: torch.Tensor, original_size: Tuple[int, ...]
) -> torch.Tensor:
"""
Expects a torch tensor with shape Bx4. Requires the original image
size in (H, W) format.
"""
boxes = self.apply_coords_torch(boxes.reshape(-1, 2, 2), original_size)
return boxes.reshape(-1, 4)
@staticmethod
def get_preprocess_shape(
oldh: int, oldw: int, long_side_length: int
) -> Tuple[int, int]:
"""
Compute the output size given input size and target long side length.
"""
scale = long_side_length * 1.0 / max(oldh, oldw)
newh, neww = oldh * scale, oldw * scale
neww = int(neww + 0.5)
newh = int(newh + 0.5)
return (newh, neww)