regnet_y_16gf¶

torchvision.models.
regnet_y_16gf
(*, weights: Optional[torchvision.models.regnet.RegNet_Y_16GF_Weights] = None, progress: bool = True, **kwargs: Any) → torchvision.models.regnet.RegNet[source]¶ Constructs a RegNetY_16GF architecture from Designing Network Design Spaces.
 Parameters
weights (
RegNet_Y_16GF_Weights
, optional) – The pretrained weights to use. SeeRegNet_Y_16GF_Weights
below for more details and possible values. By default, no pretrained weights are used.progress (bool, optional) – If True, displays a progress bar of the download to stderr. Default is True.
**kwargs – parameters passed to either
torchvision.models.regnet.RegNet
ortorchvision.models.regnet.BlockParams
class. Please refer to the source code for more detail about the classes.

class
torchvision.models.
RegNet_Y_16GF_Weights
(value)[source]¶ The model builder above accepts the following values as the
weights
parameter.RegNet_Y_16GF_Weights.DEFAULT
is equivalent toRegNet_Y_16GF_Weights.IMAGENET1K_V2
. You can also use strings, e.g.weights='DEFAULT'
orweights='IMAGENET1K_V1'
.RegNet_Y_16GF_Weights.IMAGENET1K_V1:
These weights reproduce closely the results of the paper using a simple training recipe.
acc@1 (on ImageNet1K)
80.424
acc@5 (on ImageNet1K)
95.24
min_size
height=1, width=1
categories
tench, goldfish, great white shark, … (997 omitted)
num_params
83590140
recipe
The inference transforms are available at
RegNet_Y_16GF_Weights.IMAGENET1K_V1.transforms
and perform the following preprocessing operations: AcceptsPIL.Image
, batched(B, C, H, W)
and single(C, H, W)
imagetorch.Tensor
objects. The images are resized toresize_size=[256]
usinginterpolation=InterpolationMode.BILINEAR
, followed by a central crop ofcrop_size=[224]
. Finally the values are first rescaled to[0.0, 1.0]
and then normalized usingmean=[0.485, 0.456, 0.406]
andstd=[0.229, 0.224, 0.225]
.RegNet_Y_16GF_Weights.IMAGENET1K_V2:
These weights improve upon the results of the original paper by using a modified version of TorchVision’s new training recipe. Also available as
RegNet_Y_16GF_Weights.DEFAULT
.acc@1 (on ImageNet1K)
82.886
acc@5 (on ImageNet1K)
96.328
min_size
height=1, width=1
categories
tench, goldfish, great white shark, … (997 omitted)
num_params
83590140
recipe
The inference transforms are available at
RegNet_Y_16GF_Weights.IMAGENET1K_V2.transforms
and perform the following preprocessing operations: AcceptsPIL.Image
, batched(B, C, H, W)
and single(C, H, W)
imagetorch.Tensor
objects. The images are resized toresize_size=[232]
usinginterpolation=InterpolationMode.BILINEAR
, followed by a central crop ofcrop_size=[224]
. Finally the values are first rescaled to[0.0, 1.0]
and then normalized usingmean=[0.485, 0.456, 0.406]
andstd=[0.229, 0.224, 0.225]
.RegNet_Y_16GF_Weights.IMAGENET1K_SWAG_E2E_V1:
These weights are learnt via transfer learning by endtoend finetuning the original SWAG weights on ImageNet1K data.
acc@1 (on ImageNet1K)
86.012
acc@5 (on ImageNet1K)
98.054
min_size
height=1, width=1
categories
tench, goldfish, great white shark, … (997 omitted)
recipe
license
num_params
83590140
The inference transforms are available at
RegNet_Y_16GF_Weights.IMAGENET1K_SWAG_E2E_V1.transforms
and perform the following preprocessing operations: AcceptsPIL.Image
, batched(B, C, H, W)
and single(C, H, W)
imagetorch.Tensor
objects. The images are resized toresize_size=[384]
usinginterpolation=InterpolationMode.BICUBIC
, followed by a central crop ofcrop_size=[384]
. Finally the values are first rescaled to[0.0, 1.0]
and then normalized usingmean=[0.485, 0.456, 0.406]
andstd=[0.229, 0.224, 0.225]
.RegNet_Y_16GF_Weights.IMAGENET1K_SWAG_LINEAR_V1:
These weights are composed of the original frozen SWAG trunk weights and a linear classifier learnt on top of them trained on ImageNet1K data.
acc@1 (on ImageNet1K)
83.976
acc@5 (on ImageNet1K)
97.244
min_size
height=1, width=1
categories
tench, goldfish, great white shark, … (997 omitted)
recipe
license
num_params
83590140
The inference transforms are available at
RegNet_Y_16GF_Weights.IMAGENET1K_SWAG_LINEAR_V1.transforms
and perform the following preprocessing operations: AcceptsPIL.Image
, batched(B, C, H, W)
and single(C, H, W)
imagetorch.Tensor
objects. The images are resized toresize_size=[224]
usinginterpolation=InterpolationMode.BICUBIC
, followed by a central crop ofcrop_size=[224]
. Finally the values are first rescaled to[0.0, 1.0]
and then normalized usingmean=[0.485, 0.456, 0.406]
andstd=[0.229, 0.224, 0.225]
.