test.py

import argparse
import json

from torch.utils.data import DataLoader

from modelsori import *
from utils.datasets import *
from utils.utils import *
import torchvision

def box_iouv5(box1, box2):
    # https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py
    """
    Return intersection-over-union (Jaccard index) of boxes.
    Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
    Arguments:
        box1 (Tensor[N, 4])
        box2 (Tensor[M, 4])
    Returns:
        iou (Tensor[N, M]): the NxM matrix containing the pairwise
            IoU values for every element in boxes1 and boxes2
    """

    def box_area(box):
        # box = 4xn
        return (box[2] - box[0]) * (box[3] - box[1])

    area1 = box_area(box1.T)
    area2 = box_area(box2.T)

    # inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2)
    inter = (torch.min(box1[:, None, 2:], box2[:, 2:]) - torch.max(box1[:, None, :2], box2[:, :2])).clamp(0).prod(2)
    return inter / (area1[:, None] + area2 - inter)  # iou = inter / (area1 + area2 - inter)

def non_max_suppressionv5(prediction, conf_thres=0.1, iou_thres=0.6, merge=False, classes=None, agnostic=False):
    """Performs Non-Maximum Suppression (NMS) on inference results

    Returns:
         detections with shape: nx6 (x1, y1, x2, y2, conf, cls)
    """
    if prediction.dtype is torch.float16:
        prediction = prediction.float()  # to FP32

    nc = prediction[0].shape[1] - 5  # number of classes
    xc = prediction[..., 4] > conf_thres  # candidates

    # Settings
    min_wh, max_wh = 2, 4096  # (pixels) minimum and maximum box width and height
    max_det = 300  # maximum number of detections per image
    time_limit = 10.0  # seconds to quit after
    redundant = True  # require redundant detections
    multi_label = nc > 1  # multiple labels per box (adds 0.5ms/img)

    t = time.time()
    output = [None] * prediction.shape[0]
    for xi, x in enumerate(prediction):  # image index, image inference
        # Apply constraints
        # x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0  # width-height
        x = x[xc[xi]]  # confidence

        # If none remain process next image
        if not x.shape[0]:
            continue

        # Compute conf
        x[:, 5:] *= x[:, 4:5]  # conf = obj_conf * cls_conf

        # Box (center x, center y, width, height) to (x1, y1, x2, y2)
        box = xywh2xyxy(x[:, :4])

        # Detections matrix nx6 (xyxy, conf, cls)
        if multi_label:
            i, j = (x[:, 5:] > conf_thres).nonzero(as_tuple=False).T
            x = torch.cat((box[i], x[i, j + 5, None], j[:, None].float()), 1)
        else:  # best class only
            conf, j = x[:, 5:].max(1, keepdim=True)
            x = torch.cat((box, conf, j.float()), 1)[conf.view(-1) > conf_thres]

        # Filter by class
        if classes:
            x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)]

        # Apply finite constraint
        # if not torch.isfinite(x).all():
        #     x = x[torch.isfinite(x).all(1)]

        # If none remain process next image
        n = x.shape[0]  # number of boxes
        if not n:
            continue

        # Sort by confidence
        # x = x[x[:, 4].argsort(descending=True)]

        # Batched NMS
        c = x[:, 5:6] * (0 if agnostic else max_wh)  # classes
        boxes, scores = x[:, :4] + c, x[:, 4]  # boxes (offset by class), scores
        i = torchvision.ops.boxes.nms(boxes, scores, iou_thres)
        if i.shape[0] > max_det:  # limit detections
            i = i[:max_det]
        if merge and (1 < n < 3E3):  # Merge NMS (boxes merged using weighted mean)
            try:  # update boxes as boxes(i,4) = weights(i,n) * boxes(n,4)
                iou = box_iouv5(boxes[i], boxes) > iou_thres  # iou matrix
                weights = iou * scores[None]  # box weights
                x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True)  # merged boxes
                if redundant:
                    i = i[iou.sum(1) > 1]  # require redundancy
            except:  # possible CUDA error https://github.com/ultralytics/yolov3/issues/1139
                print(x, i, x.shape, i.shape)
                pass

        output[xi] = x[i]
        if (time.time() - t) > time_limit:
            break  # time limit exceeded

    return output

def test(cfg,
         data,
         weights=None,
         batch_size=16,
         img_size=416,
         iou_thres=0.5,
         conf_thres=0.001,
         nms_thres=0.5,
         stride=32.0,
         save_json=False,
         model=None):
    
    # Initialize/load model and set device
    if model is None:
        device = torch_utils.select_device(opt.device)
        verbose = True

        # Initialize model
        model = Darknet(cfg, img_size).to(device)

        # Load weights
        attempt_download(weights)
        if weights.endswith('.pt'):  # pytorch format
            model.load_state_dict(torch.load(weights, map_location=device)['model'])
        else:  # darknet format
            _ = load_darknet_weights(model, weights)

        if torch.cuda.device_count() > 1:
            model = nn.DataParallel(model)
    else:
        device = next(model.parameters()).device  # get model device
        verbose = False

    # Configure run
    data = parse_data_cfg(data)
    nc = int(data['classes'])  # number of classes
    test_path = data['valid']  # path to test images
    names = load_classes(data['names'])  # class names

    # Dataloader
    dataset = LoadImagesAndLabels(test_path, img_size, batch_size,stride=stride)
    dataloader = DataLoader(dataset,
                            batch_size=batch_size,
                            num_workers=min([os.cpu_count(), batch_size, 16]),
                            pin_memory=True,
                            collate_fn=dataset.collate_fn)

    seen = 0
    model.eval()
    coco91class = coco80_to_coco91_class()
    s = ('%20s' + '%10s' * 6) % ('Class', 'Images', 'Targets', 'P', 'R', 'mAP', 'F1')
    p, r, f1, mp, mr, map, mf1 = 0., 0., 0., 0., 0., 0., 0.
    loss = torch.zeros(3)
    jdict, stats, ap, ap_class = [], [], [], []
    for batch_i, (imgs, targets, paths, shapes) in enumerate(tqdm(dataloader, desc=s)):
        targets = targets.to(device)
        imgs = imgs.to(device)
        _, _, height, width = imgs.shape  # batch size, channels, height, width

        # Plot images with bounding boxes
        if batch_i == 0 and not os.path.exists('test_batch0.jpg'):
            plot_images(imgs=imgs, targets=targets, paths=paths, fname='test_batch0.jpg')

        # Run model
        inf_out, train_out = model(imgs)  # inference and training outputs

        # Compute loss
        if hasattr(model, 'hyp'):  # if model has loss hyperparameters
            loss += compute_loss(train_out, targets, model)[1][:3].cpu()  # GIoU, obj, cls

        # Run NMS
        # output = non_max_suppression(inf_out, conf_thres=conf_thres, nms_thres=nms_thres)
        output = non_max_suppressionv5(inf_out,conf_thres=conf_thres, iou_thres=nms_thres, classes=None,agnostic=False)

        # Statistics per image
        for si, pred in enumerate(output):
            labels = targets[targets[:, 0] == si, 1:]
            nl = len(labels)
            tcls = labels[:, 0].tolist() if nl else []  # target class
            seen += 1

            if pred is None:
                if nl:
                    stats.append(([], torch.Tensor(), torch.Tensor(), tcls))
                continue

            # Append to text file
            # with open('test.txt', 'a') as file:
            #    [file.write('%11.5g' * 7 % tuple(x) + '\n') for x in pred]

            # Append to pycocotools JSON dictionary
            if save_json:
                # [{"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}, ...
                image_id = int(Path(paths[si]).stem.split('_')[-1])
                box = pred[:, :4].clone()  # xyxy
                scale_coords(imgs[si].shape[1:], box, shapes[si])  # to original shape
                box = xyxy2xywh(box)  # xywh
                box[:, :2] -= box[:, 2:] / 2  # xy center to top-left corner
                for di, d in enumerate(pred):
                    jdict.append({'image_id': image_id,
                                  'category_id': coco91class[int(d[6])],
                                  'bbox': [floatn(x, 3) for x in box[di]],
                                  'score': floatn(d[4], 5)})

            # Clip boxes to image bounds
            clip_coords(pred, (height, width))

            # Assign all predictions as incorrect
            correct = [0] * len(pred)
            if nl:
                detected = []
                tcls_tensor = labels[:, 0]

                # target boxes
                tbox = xywh2xyxy(labels[:, 1:5])
                tbox[:, [0, 2]] *= width
                tbox[:, [1, 3]] *= height

                # Search for correct predictions
                for i, (*pbox, pconf, pcls) in enumerate(pred):
                # for i, (*pbox, pconf, pcls_conf, pcls) in enumerate(pred):

                    # Break if all targets already located in image
                    if len(detected) == nl:
                        break

                    # Continue if predicted class not among image classes
                    if pcls.item() not in tcls:
                        continue

                    # Best iou, index between pred and targets
                    m = (pcls == tcls_tensor).nonzero(as_tuple=False).view(-1)
                    iou, bi = bbox_iou(pbox, tbox[m]).max(0)

                    # If iou > threshold and class is correct mark as correct
                    if iou > iou_thres and m[bi] not in detected:  # and pcls == tcls[bi]:
                        correct[i] = 1
                        detected.append(m[bi])

            # Append statistics (correct, conf, pcls, tcls)
            # stats.append((correct, pred[:, 4].cpu(), pred[:, 6].cpu(), tcls))
            stats.append((correct, pred[:, 4].cpu(), pred[:, 5].cpu(), tcls))

    # Compute statistics
    stats = [np.concatenate(x, 0) for x in list(zip(*stats))]  # to numpy
    if len(stats):
        p, r, ap, f1, ap_class = ap_per_class(*stats)
        mp, mr, map, mf1 = p.mean(), r.mean(), ap.mean(), f1.mean()
        nt = np.bincount(stats[3].astype(np.int64), minlength=nc)  # number of targets per class
    else:
        nt = torch.zeros(1)

    # Print results
    pf = '%20s' + '%10.3g' * 6  # print format
    print(pf % ('all', seen, nt.sum(), mp, mr, map, mf1))

    # Print results per class
    if verbose and nc > 1 and len(stats):
        for i, c in enumerate(ap_class):
            print(pf % (names[c], seen, nt[c], p[i], r[i], ap[i], f1[i]))

    # Save JSON
    if save_json and map and len(jdict):
        try:
            imgIds = [int(Path(x).stem.split('_')[-1]) for x in dataset.img_files]
            with open('results.json', 'w') as file:
                json.dump(jdict, file)

            from pycocotools.coco import COCO
            from pycocotools.cocoeval import COCOeval

            # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
            cocoGt = COCO('../coco/annotations/instances_val2014.json')  # initialize COCO ground truth api
            cocoDt = cocoGt.loadRes('results.json')  # initialize COCO pred api

            cocoEval = COCOeval(cocoGt, cocoDt, 'bbox')
            cocoEval.params.imgIds = imgIds  # [:32]  # only evaluate these images
            cocoEval.evaluate()
            cocoEval.accumulate()
            cocoEval.summarize()
            map = cocoEval.stats[1]  # update mAP to pycocotools mAP
        except:
            print('WARNING: missing dependency pycocotools from requirements.txt. Can not compute official COCO mAP.')

    # Return results
    maps = np.zeros(nc) + map
    for i, c in enumerate(ap_class):
        maps[c] = ap[i]
    return (mp, mr, map, mf1, *(loss / len(dataloader)).tolist()), maps


if __name__ == '__main__':
    parser = argparse.ArgumentParser(prog='test.py')
    parser.add_argument('--cfg', type=str, default='cfg/yolov5s.cfg', help='cfg file path')
    parser.add_argument('--data', type=str, default='data/coco.data', help='coco.data file path')
    parser.add_argument('--weights', type=str, default='weights/yolov3-spp.weights', help='path to weights file')
    parser.add_argument('--batch-size', type=int, default=16, help='size of each image batch')
    parser.add_argument('--img-size', type=int, default=416, help='inference size (pixels)')
    parser.add_argument('--iou-thres', type=float, default=0.5, help='iou threshold required to qualify as detected')
    parser.add_argument('--conf-thres', type=float, default=0.001, help='object confidence threshold')
    parser.add_argument('--nms-thres', type=float, default=0.5, help='iou threshold for non-maximum suppression')
    parser.add_argument('--save-json', action='store_true', help='save a cocoapi-compatible JSON results file')
    parser.add_argument('--device', default='', help='device id (i.e. 0 or 0,1) or cpu')
    opt = parser.parse_args()
    print(opt)

    with torch.no_grad():
        test(opt.cfg,
             opt.data,
             opt.weights,
             opt.batch_size,
             opt.img_size,
             opt.iou_thres,
             opt.conf_thres,
             opt.nms_thres,
             opt.save_json)