IOPaint/inpaint/plugins/segment_anything2/utils/misc.py

# 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 warnings

import numpy as np
import torch
from PIL import Image


def get_sdpa_settings():
    if torch.cuda.is_available():
        old_gpu = torch.cuda.get_device_properties(0).major < 7
        # only use Flash Attention on Ampere (8.0) or newer GPUs
        use_flash_attn = torch.cuda.get_device_properties(0).major >= 8
        if not use_flash_attn:
            warnings.warn(
                "Flash Attention is disabled as it requires a GPU with Ampere (8.0) CUDA capability.",
                category=UserWarning,
                stacklevel=2,
            )
        # keep math kernel for PyTorch versions before 2.2 (Flash Attention v2 is only
        # available on PyTorch 2.2+, while Flash Attention v1 cannot handle all cases)
        pytorch_version = tuple(int(v) for v in torch.__version__.split(".")[:2])
        if pytorch_version < (2, 2):
            warnings.warn(
                f"You are using PyTorch {torch.__version__} without Flash Attention v2 support. "
                "Consider upgrading to PyTorch 2.2+ for Flash Attention v2 (which could be faster).",
                category=UserWarning,
                stacklevel=2,
            )
        math_kernel_on = pytorch_version < (2, 2) or not use_flash_attn
    else:
        old_gpu = True
        use_flash_attn = False
        math_kernel_on = True

    return old_gpu, use_flash_attn, math_kernel_on


def mask_to_box(masks: torch.Tensor):
    """
    compute bounding box given an input mask

    Inputs:
    - masks: [B, 1, H, W] boxes, dtype=torch.Tensor

    Returns:
    - box_coords: [B, 1, 4], contains (x, y) coordinates of top left and bottom right box corners, dtype=torch.Tensor
    """
    B, _, h, w = masks.shape
    device = masks.device
    xs = torch.arange(w, device=device, dtype=torch.int32)
    ys = torch.arange(h, device=device, dtype=torch.int32)
    grid_xs, grid_ys = torch.meshgrid(xs, ys, indexing="xy")
    grid_xs = grid_xs[None, None, ...].expand(B, 1, h, w)
    grid_ys = grid_ys[None, None, ...].expand(B, 1, h, w)
    min_xs, _ = torch.min(torch.where(masks, grid_xs, w).flatten(-2), dim=-1)
    max_xs, _ = torch.max(torch.where(masks, grid_xs, -1).flatten(-2), dim=-1)
    min_ys, _ = torch.min(torch.where(masks, grid_ys, h).flatten(-2), dim=-1)
    max_ys, _ = torch.max(torch.where(masks, grid_ys, -1).flatten(-2), dim=-1)
    bbox_coords = torch.stack((min_xs, min_ys, max_xs, max_ys), dim=-1)

    return bbox_coords


def _load_img_as_tensor(img_path, image_size):
    img_pil = Image.open(img_path)
    img_np = np.array(img_pil.convert("RGB").resize((image_size, image_size)))
    if img_np.dtype == np.uint8:  # np.uint8 is expected for JPEG images
        img_np = img_np / 255.0
    else:
        raise RuntimeError(f"Unknown image dtype: {img_np.dtype} on {img_path}")
    img = torch.from_numpy(img_np).permute(2, 0, 1)
    video_width, video_height = img_pil.size  # the original video size
    return img, video_height, video_width


def concat_points(old_point_inputs, new_points, new_labels):
    """Add new points and labels to previous point inputs (add at the end)."""
    if old_point_inputs is None:
        points, labels = new_points, new_labels
    else:
        points = torch.cat([old_point_inputs["point_coords"], new_points], dim=1)
        labels = torch.cat([old_point_inputs["point_labels"], new_labels], dim=1)

    return {"point_coords": points, "point_labels": labels}