YOLOv8-16bit/ultralytics/yolo/utils/modeling/__init__.py

import contextlib

import torchvision

from ultralytics.yolo.utils.downloads import attempt_download
from ultralytics.yolo.utils.modeling.modules import *


def attempt_load_weights(weights, device=None, inplace=True, fuse=True):
    # Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a

    model = Ensemble()
    for w in weights if isinstance(weights, list) else [weights]:
        ckpt = torch.load(attempt_download(w), map_location='cpu')  # load
        ckpt = (ckpt.get('ema') or ckpt['model']).to(device).float()  # FP32 model

        # Model compatibility updates
        if not hasattr(ckpt, 'stride'):
            ckpt.stride = torch.tensor([32.])
        if hasattr(ckpt, 'names') and isinstance(ckpt.names, (list, tuple)):
            ckpt.names = dict(enumerate(ckpt.names))  # convert to dict

        model.append(ckpt.fuse().eval() if fuse and hasattr(ckpt, 'fuse') else ckpt.eval())  # model in eval mode

    # Module compatibility updates
    for m in model.modules():
        t = type(m)
        if t in (nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect):
            m.inplace = inplace  # torch 1.7.0 compatibility
            if t is Detect and not isinstance(m.anchor_grid, list):
                delattr(m, 'anchor_grid')
                setattr(m, 'anchor_grid', [torch.zeros(1)] * m.nl)
        elif t is nn.Upsample and not hasattr(m, 'recompute_scale_factor'):
            m.recompute_scale_factor = None  # torch 1.11.0 compatibility

    # Return model
    if len(model) == 1:
        return model[-1]

    # Return detection ensemble
    print(f'Ensemble created with {weights}\n')
    for k in 'names', 'nc', 'yaml':
        setattr(model, k, getattr(model[0], k))
    model.stride = model[torch.argmax(torch.tensor([m.stride.max() for m in model])).int()].stride  # max stride
    assert all(model[0].nc == m.nc for m in model), f'Models have different class counts: {[m.nc for m in model]}'
    return model


def parse_model(d, ch):  # model_dict, input_channels(3)
    # Parse a YOLOv5 model.yaml dictionary
    LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10}  {'module':<40}{'arguments':<30}")
    anchors, nc, gd, gw, act = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple'], d.get('activation')
    if act:
        Conv.default_act = eval(act)  # redefine default activation, i.e. Conv.default_act = nn.SiLU()
        LOGGER.info(f"{colorstr('activation:')} {act}")  # print
    na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors  # number of anchors
    no = na * (nc + 5)  # number of outputs = anchors * (classes + 5)

    layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out
    for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):  # from, number, module, args
        m = eval(m) if isinstance(m, str) else m  # eval strings
        for j, a in enumerate(args):
            with contextlib.suppress(NameError):
                args[j] = eval(a) if isinstance(a, str) else a  # eval strings

        n = n_ = max(round(n * gd), 1) if n > 1 else n  # depth gain
        if m in {
                Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, Focus, CrossConv, BottleneckCSP, C3,
                C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x}:
            c1, c2 = ch[f], args[0]
            if c2 != no:  # if not output
                c2 = make_divisible(c2 * gw, 8)

            args = [c1, c2, *args[1:]]
            if m in {BottleneckCSP, C3, C3TR, C3Ghost, C3x}:
                args.insert(2, n)  # number of repeats
                n = 1
        elif m is nn.BatchNorm2d:
            args = [ch[f]]
        elif m is Concat:
            c2 = sum(ch[x] for x in f)
        # TODO: channel, gw, gd
        elif m in {Detect, Segment}:
            args.append([ch[x] for x in f])
            if isinstance(args[1], int):  # number of anchors
                args[1] = [list(range(args[1] * 2))] * len(f)
            if m is Segment:
                args[3] = make_divisible(args[3] * gw, 8)
        elif m is Contract:
            c2 = ch[f] * args[0] ** 2
        elif m is Expand:
            c2 = ch[f] // args[0] ** 2
        else:
            c2 = ch[f]

        m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args)  # module
        t = str(m)[8:-2].replace('__main__.', '')  # module type
        np = sum(x.numel() for x in m_.parameters())  # number params
        m_.i, m_.f, m_.type, m_.np = i, f, t, np  # attach index, 'from' index, type, number params
        LOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{np:10.0f}  {t:<40}{str(args):<30}')  # print
        save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
        layers.append(m_)
        if i == 0:
            ch = []
        ch.append(c2)
    return nn.Sequential(*layers), sorted(save)


def get_model(model='s.pt', pretrained=True):
    # Load a YOLO model locally, from torchvision, or from Ultralytics assets
    if model.endswith(".pt"):
        model = model.split(".")[0]

    if Path(f"{model}.pt").is_file():  # local file
        return attempt_load_weights(f"{model}.pt", device='cpu')
    elif model in torchvision.models.__dict__:  # TorchVision models i.e. resnet50, efficientnet_b0
        return torchvision.models.__dict__[model](weights='IMAGENET1K_V1' if pretrained else None)
    else:  # Ultralytics assets
        return attempt_load_weights(f"{model}.pt", device='cpu')