YOLOv8改进，融合Gold-YOLO Neck

# Ultralytics YOLO 🚀, AGPL-3.0 license import contextlib from copy import deepcopy from pathlib import Path import torch import torch.nn as nn from ultralytics.nn.modules import (AIFI, C1, C2, C3, C3TR, SPP, SPPF, Bottleneck, BottleneckCSP, C2f, C3Ghost, C3x, Classify, Concat, Conv, Conv2, ConvTranspose, Detect, DWConv, DWConvTranspose2d, Focus, GhostBottleneck, GhostConv, HGBlock, HGStem, Pose, RepC3, RepConv, RTDETRDecoder, Segment, Low_FAM, Low_IFM, Split, SimConv, Low_LAF, Inject, RepBlock, High_FAM, High_IFM, High_LAF) from ultralytics.utils import DEFAULT_CFG_DICT, DEFAULT_CFG_KEYS, LOGGER, colorstr, emojis, yaml_load from ultralytics.utils.checks import check_requirements, check_suffix, check_yaml from ultralytics.utils.loss import v8ClassificationLoss, v8DetectionLoss, v8PoseLoss, v8SegmentationLoss from ultralytics.utils.plotting import feature_visualization from ultralytics.utils.torch_utils import (fuse_conv_and_bn, fuse_deconv_and_bn, initialize_weights, intersect_dicts, make_divisible, model_info, scale_img, time_sync) try: import thop except ImportError: thop = None class BaseModel(nn.Module): """ The BaseModel class serves as a base class for all the models in the Ultralytics YOLO family. """ def forward(self, x, *args, **kwargs): """ Forward pass of the model on a single scale. Wrapper for `_forward_once` method. Args: x (torch.Tensor | dict): The input image tensor or a dict including image tensor and gt labels. Returns: (torch.Tensor): The output of the network. """ if isinstance(x, dict): # for cases of training and validating while training. return self.loss(x, *args, **kwargs) return self.predict(x, *args, **kwargs) def predict(self, x, profile=False, visualize=False, augment=False): """ Perform a forward pass through the network. Args: x (torch.Tensor): The input tensor to the model. profile (bool): Print the computation time of each layer if True, defaults to False. visualize (bool): Save the feature maps of the model if True, defaults to False. augment (bool): Augment image during prediction, defaults to False. Returns: (torch.Tensor): The last output of the model. """ if augment: return self._predict_augment(x) return self._predict_once(x, profile, visualize) def _predict_once(self, x, profile=False, visualize=False): """ Perform a forward pass through the network. Args: x (torch.Tensor): The input tensor to the model. profile (bool): Print the computation time of each layer if True, defaults to False. visualize (bool): Save the feature maps of the model if True, defaults to False. Returns: (torch.Tensor): The last output of the model. """ y, dt = [], [] # outputs for m in self.model: if m.f != -1: # if not from previous layer x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers if profile: self._profile_one_layer(m, x, dt) try: if m.input_nums > 1: # input nums more than one x = m(*x) # run else: x = m(x) except AttributeError: # AttributeError: 'Conv' object has no attribute 'input_nums' x = m(x) y.append(x if m.i in self.save else None) # save output if visualize: feature_visualization(x, m.type, m.i, save_dir=visualize) return x def _predict_augment(self, x): """Perform augmentations on input image x and return augmented inference.""" LOGGER.warning(f'WARNING ⚠️ {self.__class__.__name__} does not support augmented inference yet. ' f'Reverting to single-scale inference instead.') return self._predict_once(x) def _profile_one_layer(self, m, x, dt): """ Profile the computation time and FLOPs of a single layer of the model on a given input. Appends the results to the provided list. Args: m (nn.Module): The layer to be profiled. x (torch.Tensor): The input data to the layer. dt (list): A list to store the computation time of the layer. Returns: None """ c = m == self.model[-1] and isinstance(x, list) # is final layer list, copy input as inplace fix flops = thop.profile(m, inputs=[x.copy() if c else x], verbose=False)[0] / 1E9 * 2 if thop else 0 # FLOPs t = time_sync() for _ in range(10): m(x.copy() if c else x) dt.append((time_sync() - t) * 100) if m == self.model[0]: LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s} module") LOGGER.info(f'{dt[-1]:10.2f} {flops:10.2f} {m.np:10.0f} {m.type}') if c: LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s} Total") def fuse(self, verbose=True): """ Fuse the `Conv2d()` and `BatchNorm2d()` layers of the model into a single layer, in order to improve the computation efficiency. Returns: (nn.Module): The fused model is returned. """ if not self.is_fused(): for m in self.model.modules(): if isinstance(m, (Conv, Conv2, DWConv)) and hasattr(m, 'bn'): if isinstance(m, Conv2): m.fuse_convs() m.conv = fuse_conv_and_bn(m.conv, m.bn) # update conv delattr(m, 'bn') # remove batchnorm m.forward = m.forward_fuse # update forward if isinstance(m, ConvTranspose) and hasattr(m, 'bn'): m.conv_transpose = fuse_deconv_and_bn(m.conv_transpose, m.bn) delattr(m, 'bn') # remove batchnorm m.forward = m.forward_fuse # update forward if isinstance(m, RepConv): m.fuse_convs() m.forward = m.forward_fuse # update forward self.info(verbose=verbose) return self def is_fused(self, thresh=10): """ Check if the model has less than a certain threshold of BatchNorm layers. Args: thresh (int, optional): The threshold number of BatchNorm layers. Default is 10. Returns: (bool): True if the number of BatchNorm layers in the model is less than the threshold, False otherwise. """ bn = tuple(v for k, v in nn.__dict__.items() if 'Norm' in k) # normalization layers, i.e. BatchNorm2d() return sum(isinstance(v, bn) for v in self.modules()) < thresh # True if < 'thresh' BatchNorm layers in model def info(self, detailed=False, verbose=True, imgsz=640): """ Prints model information Args: detailed (bool): if True, prints out detailed information about the model. Defaults to False verbose (bool): if True, prints out the model information. Defaults to False imgsz (int): the size of the image that the model will be trained on. Defaults to 640 """ return model_info(self, detailed=detailed, verbose=verbose, imgsz=imgsz) def _apply(self, fn): """ Applies a function to all the tensors in the model that are not parameters or registered buffers. Args: fn (function): the function to apply to the model Returns: A model that is a Detect