torchelie.models¶
We provide trained models. Use the argument pretrained=task
in order to
use them. Example: torchelie.models.resnet18(1000, pretrained='classification/imagenet')
.
Alternatively: torchelie.models.get_model('resnet18', 1000, pretrained='classification/imagenet')
model |
task |
notes |
source |
---|---|---|---|
resnet18 |
classification/imagenet |
top1: 69.75% |
torchvision |
resnet34 |
classification/imagenet |
top1: 73.31% |
torchvision |
resnet50 |
classification/imagenet |
top1: 76.13% |
torchvision |
resnet101 |
classification/imagenet |
top1: 77.37% |
torchvision |
resnet152 |
classification/imagenet |
top1: 78.31% |
torchvision |
preact_resnet18 |
classification/imagenet |
top1: 68.41% (192x192 crop) |
torchelie |
vgg11 |
classification/imagenet |
top1: 69.02% |
torchvision |
vgg13 |
classification/imagenet |
top1: 69.92% |
torchvision |
vgg16 |
classification/imagenet |
top1: 71.59% |
torchvision |
vgg19 |
classification/imagenet |
top1: 72.37% |
torchvision |
vgg11_bn |
classification/imagenet |
top1: 70.37% |
torchvision |
vgg13_bn |
classification/imagenet |
top1: 71.58% |
torchvision |
vgg16_bn |
classification/imagenet |
top1: 73.36% |
torchvision |
vgg19_bn |
classification/imagenet |
top1: 74.21% |
torchvision |
vgg19 |
perceptual/imagenet |
activations normalized to have mean 1 for perceptual losses |
torchelie |
Resnets¶
Pix2Pix¶
UNet generator from Pix2Pix. |
|
The architecture used in Pix2Pix, able to train on 256x256 or 512x512 images. |
|
A version of pix2pix_256 with less filter to use less memory and compute. |
|
Patch Discriminator from pix2pix |
|
Patch Discriminator from pix2pix |
|
Patch Discriminator from pix2pix |
|
Patch Discriminator from pix2pix |
|
StyleGAN2¶
Generator from StyleGAN2 |
|
Experimental: Build the discriminator for StyleGAN2 |
Other GANs¶
Experimental: Generator discovered in AutoGAN: Neural Architecture Search for Generative Adversarial Networks. |
|
Experimental |
|
Experimental |
|
Experimental |
|
Make a VGG16 with appropriately named layers that records intermediate activations. |
|
Image classifiers¶
Attention56 bone |
|
Experimental: Build a attention56 network |
|
Experimental: Hourglass model from Deep Image Prior. .. warning:: Hourglass() is experimental, and may change or be deleted soon if not already broken. |
Image Transformer¶
Experimental: U-Net from U-Net: Convolutional Networks for Biomedical Image Segmentation. |
|
Experimental: Hourglass model from Deep Image Prior. .. warning:: Hourglass() is experimental, and may change or be deleted soon if not already broken. |
Classification heads¶
A one layer classification head, turning activations / features into class log probabilities. |
|
Experimental: A classification head for conditional GANs discriminators using a projection discriminator . |