ultralytics/nn/autoshape.py

# Ultralytics YOLO 🚀, AGPL-3.0 license
"""
Common modules
"""

from copy import copy
from pathlib import Path

import cv2
import numpy as np
import requests
import torch
import torch.nn as nn
from PIL import Image, ImageOps
from torch.cuda import amp

from ultralytics.nn.autobackend import AutoBackend
from ultralytics.yolo.data.augment import LetterBox
from ultralytics.yolo.utils import LOGGER, colorstr
from ultralytics.yolo.utils.files import increment_path
from ultralytics.yolo.utils.ops import Profile, make_divisible, non_max_suppression, scale_boxes, xyxy2xywh
from ultralytics.yolo.utils.plotting import Annotator, colors, save_one_box
from ultralytics.yolo.utils.torch_utils import copy_attr, smart_inference_mode


class AutoShape(nn.Module):
    """YOLOv8 input-robust model wrapper for passing cv2/np/PIL/torch inputs. Includes preprocessing, inference and NMS."""
    conf = 0.25  # NMS confidence threshold
    iou = 0.45  # NMS IoU threshold
    agnostic = False  # NMS class-agnostic
    multi_label = False  # NMS multiple labels per box
    classes = None  # (optional list) filter by class, i.e. = [0, 15, 16] for COCO persons, cats and dogs
    max_det = 1000  # maximum number of detections per image
    amp = False  # Automatic Mixed Precision (AMP) inference

    def __init__(self, model, verbose=True):
        """Initializes object and copies attributes from model object."""
        super().__init__()
        if verbose:
            LOGGER.info('Adding AutoShape... ')
        copy_attr(self, model, include=('yaml', 'nc', 'hyp', 'names', 'stride', 'abc'), exclude=())  # copy attributes
        self.dmb = isinstance(model, AutoBackend)  # DetectMultiBackend() instance
        self.pt = not self.dmb or model.pt  # PyTorch model
        self.model = model.eval()
        if self.pt:
            m = self.model.model.model[-1] if self.dmb else self.model.model[-1]  # Detect()
            m.inplace = False  # Detect.inplace=False for safe multithread inference
            m.export = True  # do not output loss values

    def _apply(self, fn):
        """Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers."""
        self = super()._apply(fn)
        if self.pt:
            m = self.model.model.model[-1] if self.dmb else self.model.model[-1]  # Detect()
            m.stride = fn(m.stride)
            m.grid = list(map(fn, m.grid))
            if isinstance(m.anchor_grid, list):
                m.anchor_grid = list(map(fn, m.anchor_grid))
        return self

    @smart_inference_mode()
    def forward(self, ims, size=640, augment=False, profile=False):
        """Inference from various sources. For size(height=640, width=1280), RGB images example inputs are:."""
        #   file:        ims = 'data/images/zidane.jpg'  # str or PosixPath
        #   URI:             = 'https://ultralytics.com/images/zidane.jpg'
        #   OpenCV:          = cv2.imread('image.jpg')[:,:,::-1]  # HWC BGR to RGB x(640,1280,3)
        #   PIL:             = Image.open('image.jpg') or ImageGrab.grab()  # HWC x(640,1280,3)
        #   numpy:           = np.zeros((640,1280,3))  # HWC
        #   torch:           = torch.zeros(16,3,320,640)  # BCHW (scaled to size=640, 0-1 values)
        #   multiple:        = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...]  # list of images

        dt = (Profile(), Profile(), Profile())
        with dt[0]:
            if isinstance(size, int):  # expand
                size = (size, size)
            p = next(self.model.parameters()) if self.pt else torch.empty(1, device=self.model.device)  # param
            autocast = self.amp and (p.device.type != 'cpu')  # Automatic Mixed Precision (AMP) inference
            if isinstance(ims, torch.Tensor):  # torch
                with amp.autocast(autocast):
                    return self.model(ims.to(p.device).type_as(p), augment=augment)  # inference

            # Preprocess
            n, ims = (len(ims), list(ims)) if isinstance(ims, (list, tuple)) else (1, [ims])  # number, list of images
            shape0, shape1, files = [], [], []  # image and inference shapes, filenames
            for i, im in enumerate(ims):
                f = f'image{i}'  # filename
                if isinstance(im, (str, Path)):  # filename or uri
                    im, f = Image.open(requests.get(im, stream=True).raw if str(im).startswith('http') else im), im
                    im = np.asarray(ImageOps.exif_transpose(im))
                elif isinstance(im, Image.Image):  # PIL Image
                    im, f = np.asarray(ImageOps.exif_transpose(im)), getattr(im, 'filename', f) or f
                files.append(Path(f).with_suffix('.jpg').name)
                if im.shape[0] < 5:  # image in CHW
                    im = im.transpose((1, 2, 0))  # reverse dataloader .transpose(2, 0, 1)
                im = im[..., :3] if im.ndim == 3 else cv2.cvtColor(im, cv2.COLOR_GRAY2BGR)  # enforce 3ch input
                s = im.shape[:2]  # HWC
                shape0.append(s)  # image shape
                g = max(size) / max(s)  # gain
                shape1.append([y * g for y in s])
                ims[i] = im if im.data.contiguous else np.ascontiguousarray(im)  # update
            shape1 = [make_divisible(x, self.stride) for x in np.array(shape1).max(0)] if self.pt else size  # inf shape
            x = [LetterBox(shape1, auto=False)(image=im)['img'] for im in ims]  # pad
            x = np.ascontiguousarray(np.array(x).transpose((0, 3, 1, 2)))  # stack and BHWC to BCHW
            x = torch.from_numpy(x).to(p.device).type_as(p) / 255  # uint8 to fp16/32

        with amp.autocast(autocast):
            # Inference
            with dt[1]:
                y = self.model(x, augment=augment)  # forward

            # Postprocess
            with dt[2]:
                y = non_max_suppression(y if self.dmb else y[0],
                                        self.conf,
                                        self.iou,
                                        self.classes,
                                        self.agnostic,
                                        self.multi_label,
                                        max_det=self.max_det)  # NMS
                for i in range(n):
                    scale_boxes(shape1, y[i][:, :4], shape0[i])

            return Detections(ims, y, files, dt, self.names, x.shape)


class Detections:
    """ YOLOv8 detections class for inference results"""

    def __init__(self, ims, pred, files, times=(0, 0, 0), names=None, shape=None):
        """Initialize object attributes for YOLO detection results."""
        super().__init__()
        d = pred[0].device  # device
        gn = [torch.tensor([*(im.shape[i] for i in [1, 0, 1, 0]), 1, 1], device=d) for im in ims]  # normalizations
        self.ims = ims  # list of images as numpy arrays
        self.pred = pred  # list of tensors pred[0] = (xyxy, conf, cls)
        self.names = names  # class names
        self.files = files  # image filenames
        self.times = times  # profiling times
        self.xyxy = pred  # xyxy pixels
        self.xywh = [xyxy2xywh(x) for x in pred]  # xywh pixels
        self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)]  # xyxy normalized
        self.xywhn = [x / g for x, g in zip(self.xywh, gn)]  # xywh normalized
        self.n = len(self.pred)  # number of images (batch size)
        self.t = tuple(x.t / self.n * 1E3 for x in times)  # timestamps (ms)
        self.s = tuple(shape)  # inference BCHW shape

    def _run(self, pprint=False, show=False, save=False, crop=False, render=False, labels=True, save_dir=Path('')):
        """Return performance metrics and optionally cropped/save images or results."""
        s, crops = '', []
        for i, (im, pred) in enumerate(zip(self.ims, self.pred)):
            s += f'\nimage {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} '  # string
            if pred.shape[0]:
                for c in pred[:, -1].unique():
                    n = (pred[:, -1] == c).sum()  # detections per class
                    s += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, "  # add to string
                s = s.rstrip(', ')
                if show or save or render or crop:
                    annotator = Annotator(im, example=str(self.names))
                    for *box, conf, cls in reversed(pred):  # xyxy, confidence, class
                        label = f'{self.names[int(cls)]} {conf:.2f}'
                        if crop:
                            file = save_dir / 'crops' / self.names[int(cls)] / self.files[i] if save else None
                            crops.append({
                                'box': box,
                                'conf': conf,
                                'cls': cls,
                                'label': label,
                                'im': save_one_box(box, im, file=file, save=save)})
                        else:  # all others
                            annotator.box_label(box, label if labels else '', color=colors(cls))
                    im = annotator.im
            else:
                s += '(no detections)'

            im = Image.fromarray(im.astype(np.uint8)) if isinstance(im, np.ndarray) else im  # from np
            if show:
                im.show(self.files[i])  # show
            if save:
                f = self.files[i]
                im.save(save_dir / f)  # save
                if i == self.n - 1:
                    LOGGER.info(f"Saved {self.n} image{'s' * (self.n > 1)} to {colorstr('bold', save_dir)}")
            if render:
                self.ims[i] = np.asarray(im)
        if pprint:
            s = s.lstrip('\n')
            return f'{s}\nSpeed: %.1fms preprocess, %.1fms inference, %.1fms NMS per image at shape {self.s}' % self.t
        if crop:
            if save:
                LOGGER.info(f'Saved results to {save_dir}\n')
            return crops

    def show(self, labels=True):
        """Displays YOLO results with detected bounding boxes."""
        self._run(show=True, labels=labels)  # show results

    def save(self, labels=True, save_dir='runs/detect/exp', exist_ok=False):
        """Save detection results with optional labels to specified directory."""
        save_dir = increment_path(save_dir, exist_ok, mkdir=True)  # increment save_dir
        self._run(save=True, labels=labels, save_dir=save_dir)  # save results

    def crop(self, save=True, save_dir='runs/detect/exp', exist_ok=False):
        """Crops images into detections and saves them if 'save' is True."""
        save_dir = increment_path(save_dir, exist_ok, mkdir=True) if save else None
        return self._run(crop=True, save=save, save_dir=save_dir)  # crop results

    def render(self, labels=True):
        """Renders detected objects and returns images."""
        self._run(render=True, labels=labels)  # render results
        return self.ims

    def pandas(self):
        """Return detections as pandas DataFrames, i.e. print(results.pandas().xyxy[0])."""
        import pandas
        new = copy(self)  # return copy
        ca = 'xmin', 'ymin', 'xmax', 'ymax', 'confidence', 'class', 'name'  # xyxy columns
        cb = 'xcenter', 'ycenter', 'width', 'height', 'confidence', 'class', 'name'  # xywh columns
        for k, c in zip(['xyxy', 'xyxyn', 'xywh', 'xywhn'], [ca, ca, cb, cb]):
            a = [[x[:5] + [int(x[5]), self.names[int(x[5])]] for x in x.tolist()] for x in getattr(self, k)]  # update
            setattr(new, k, [pandas.DataFrame(x, columns=c) for x in a])
        return new

    def tolist(self):
        """Return a list of Detections objects, i.e. 'for result in results.tolist():'."""
        r = range(self.n)  # iterable
        x = [Detections([self.ims[i]], [self.pred[i]], [self.files[i]], self.times, self.names, self.s) for i in r]
        # for d in x:
        #    for k in ['ims', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']:
        #        setattr(d, k, getattr(d, k)[0])  # pop out of list
        return x

    def print(self):
        """Print the results of the `self._run()` function."""
        LOGGER.info(self.__str__())

    def __len__(self):  # override len(results)
        return self.n

    def __str__(self):  # override print(results)
        return self._run(pprint=True)  # print results

    def __repr__(self):
        """Returns a printable representation of the object."""
        return f'YOLOv8 {self.__class__} instance\n' + self.__str__()