inception_v3¶
- torchvision.models.quantization.inception_v3(*, weights: Optional[Union[Inception_V3_QuantizedWeights, Inception_V3_Weights]] = None, progress: bool = True, quantize: bool = False, **kwargs: Any) QuantizableInception3 [source]¶
Inception v3 model architecture from Rethinking the Inception Architecture for Computer Vision.
Note
Important: In contrast to the other models the inception_v3 expects tensors with a size of N x 3 x 299 x 299, so ensure your images are sized accordingly.
Note
Note that
quantize = True
returns a quantized model with 8 bit weights. Quantized models only support inference and run on CPUs. GPU inference is not yet supported.- Parameters:
weights (
Inception_V3_QuantizedWeights
orInception_V3_Weights
, optional) – The pretrained weights for the model. SeeInception_V3_QuantizedWeights
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.
quantize (bool, optional) – If True, return a quantized version of the model. Default is False.
**kwargs – parameters passed to the
torchvision.models.quantization.QuantizableInception3
base class. Please refer to the source code for more details about this class.
- class torchvision.models.quantization.Inception_V3_QuantizedWeights(value)[source]¶
The model builder above accepts the following values as the
weights
parameter.Inception_V3_QuantizedWeights.DEFAULT
is equivalent toInception_V3_QuantizedWeights.IMAGENET1K_FBGEMM_V1
. You can also use strings, e.g.weights='DEFAULT'
orweights='IMAGENET1K_FBGEMM_V1'
.Inception_V3_QuantizedWeights.IMAGENET1K_FBGEMM_V1:
These weights were produced by doing Post Training Quantization (eager mode) on top of the unquantized weights listed below. Also available as
Inception_V3_QuantizedWeights.DEFAULT
.acc@1 (on ImageNet-1K)
77.176
acc@5 (on ImageNet-1K)
93.354
num_params
27161264
min_size
height=75, width=75
categories
tench, goldfish, great white shark, … (997 omitted)
backend
fbgemm
recipe
unquantized
Inception_V3_Weights.IMAGENET1K_V1
GIPS
5.71
File size
23.1 MB
The inference transforms are available at
Inception_V3_QuantizedWeights.IMAGENET1K_FBGEMM_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=[342]
usinginterpolation=InterpolationMode.BILINEAR
, followed by a central crop ofcrop_size=[299]
. 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]
.
- class torchvision.models.Inception_V3_Weights(value)[source]
The model builder above accepts the following values as the
weights
parameter.Inception_V3_Weights.DEFAULT
is equivalent toInception_V3_Weights.IMAGENET1K_V1
. You can also use strings, e.g.weights='DEFAULT'
orweights='IMAGENET1K_V1'
.Inception_V3_Weights.IMAGENET1K_V1:
These weights are ported from the original paper. Also available as
Inception_V3_Weights.DEFAULT
.acc@1 (on ImageNet-1K)
77.294
acc@5 (on ImageNet-1K)
93.45
num_params
27161264
min_size
height=75, width=75
categories
tench, goldfish, great white shark, … (997 omitted)
recipe
GFLOPS
5.71
File size
103.9 MB
The inference transforms are available at
Inception_V3_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=[342]
usinginterpolation=InterpolationMode.BILINEAR
, followed by a central crop ofcrop_size=[299]
. 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]
.