googlenet — Torchvision 0.16 documentation (original) (raw)
torchvision.models.googlenet(*, weights: Optional[GoogLeNet_Weights] = None, progress: bool = True, **kwargs: Any) → GoogLeNet[source]¶
GoogLeNet (Inception v1) model architecture fromGoing Deeper with Convolutions.
Parameters:
- weights (GoogLeNet_Weights, optional) – The pretrained weights for the model. SeeGoogLeNet_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.GoogLeNetbase class. Please refer to the source codefor more details about this class.
class torchvision.models.GoogLeNet_Weights(value)[source]¶
The model builder above accepts the following values as the weights parameter.GoogLeNet_Weights.DEFAULT is equivalent to GoogLeNet_Weights.IMAGENET1K_V1. You can also use strings, e.g. weights='DEFAULT' or weights='IMAGENET1K_V1'.
GoogLeNet_Weights.IMAGENET1K_V1:
These weights are ported from the original paper. Also available as GoogLeNet_Weights.DEFAULT.
| acc@1 (on ImageNet-1K) | 69.778 |
|---|---|
| acc@5 (on ImageNet-1K) | 89.53 |
| num_params | 6624904 |
| min_size | height=15, width=15 |
| categories | tench, goldfish, great white shark, … (997 omitted) |
| recipe | link |
| GFLOPS | 1.50 |
| File size | 49.7 MB |
The inference transforms are available at GoogLeNet_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=[256] 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].