convnext_large

torchvision.models.convnext_large(*, weights: Optional[ConvNeXt_Large_Weights] = None, progress: bool = True, **kwargs: Any) → ConvNeXt

ConvNeXt Large model architecture from the A ConvNet for the 2020s paper.

Parameters:

• weights (ConvNeXt_Large_Weights, optional) – The pretrained weights to use. See ConvNeXt_Large_Weights below for more details and possible values. By default, no pre-trained weights are used.

• progress (bool, optional) – If True, displays a progress bar of the download to stderr. Default is True.

• **kwargs – parameters passed to the torchvision.models.convnext.ConvNext base class. Please refer to the source code for more details about this class.

class torchvision.models.ConvNeXt_Large_Weights(value)

The model builder above accepts the following values as the weights parameter. ConvNeXt_Large_Weights.DEFAULT is equivalent to ConvNeXt_Large_Weights.IMAGENET1K_V1. You can also use strings, e.g. weights='DEFAULT' or weights='IMAGENET1K_V1'.

ConvNeXt_Large_Weights.IMAGENET1K_V1:

These weights improve upon the results of the original paper by using a modified version of TorchVision’s new training recipe. Also available as ConvNeXt_Large_Weights.DEFAULT.

acc@1 (on ImageNet-1K)	84.414
acc@5 (on ImageNet-1K)	96.976
min_size	height=32, width=32
categories	tench, goldfish, great white shark, … (997 omitted)
recipe	link
num_params	197767336
GFLOPS	34.36
File size	754.5 MB

The inference transforms are available at ConvNeXt_Large_Weights.IMAGENET1K_V1.transforms and perform the following preprocessing operations: Accepts PIL.Image, batched (B, C, H, W) and single (C, H, W) image torch.Tensor objects. The images are resized to resize_size=[232] using interpolation=InterpolationMode.BILINEAR, followed by a central crop of crop_size=[224]. Finally the values are first rescaled to [0.0, 1.0] and then normalized using mean=[0.485, 0.456, 0.406] and std=[0.229, 0.224, 0.225].