问为什么我有错误:给定groups=1，大小的权重[8,1024，1，1]，期望输入[8,304，9，40]有1024个通道，但得到304个通道

EN

RuntimeError: Given groups=1, weight of size [8, 1024, 1, 1], expected input[8, 304, 9, 40] to have 1024 channels, but got 304 channels instead

class YoloStereo3DCore(nn.Module):
    """
        Inference Structure of YoloStereo3D
        Similar to YoloMono3D,
        Left and Right image are fed into the backbone in batch. So they will affect each other with BatchNorm2d.
    """
    def __init__(self, backbone_arguments):
        f = open("/home/zakaseb/Thesis/YoloStereo3D/Stereo3D/Sequence.txt", "a")
        f.write("yolosterero3dCore_init \n")
        f.close()
        super(YoloStereo3DCore, self).__init__()
        self.backbone =edgenext_small(**backbone_arguments) # Resnet, change backbone from here

        base_features = 256 #if backbone_arguments['depth'] > 34 else 64 # meaning which depth of resnet
        self.neck = StereoMerging(base_features) #stereomerging outputs features and depth output.

@BACKBONE_DICT.register_module
def edgenext_small(pretrained=False, **kwargs):
    FPS @ BS=1: 93.84 & @ BS=256: 1785.92 for MobileViT_S
    model = EdgeNeXt(depths=[3, 3, 9, 3], dims=[48, 96, 160, 304], expan_ratio=4,
                     global_block=[0, 1, 1, 1],
                     global_block_type=['None', 'SDTA', 'SDTA', 'SDTA'],
                     use_pos_embd_xca=[False, True, False, False],
                     kernel_sizes=[3, 5, 7, 9],
                     d2_scales=[2, 2, 3, 4],
                     classifier_dropout=0.0)

    return model