TorchVision 0.15.2 Release

This is a minor release, which is compatible with PyTorch 2.0.1 and contains some minor bug fixes.

Highlights

Bug Fixes

• Move parameter sampling of v2.RandomPhotometricDistort into _get_params #7442
• Fix split parameter for MovingMNIST #7449
• Prevent unwrapping in v2.SanitizeBoundingBoxes #7446

TorchVision 0.15 - New transforms API!

Highlights

[BETA] New transforms API

TorchVision is extending its Transforms API! Here is what’s new:

• You can use them not only for Image Classification but also for Object Detection, Instance & Semantic Segmentation and Video Classification.
• You can use new functional transforms for transforming Videos, Bounding Boxes and Segmentation Masks.

The API is completely backward compatible with the previous one, and remains the same to assist the migration and adoption. We are now releasing this new API as Beta in the torchvision.transforms.v2 namespace, and we would love to get early feedback from you to improve its functionality. Please reach out to us if you have any questions or suggestions.

import torchvision.transforms.v2 as transforms

# Exactly the same interface as V1:
trans = transforms.Compose([
    transforms.ColorJitter(contrast=0.5),
    transforms.RandomRotation(30),
    transforms.CenterCrop(480),
])
imgs, bboxes, masks, labels = trans(imgs, bboxes, masks, labels)

You can read more about these new transforms in our docs, and you can also check out our examples:

• End-to-end object detection example
  
• Getting started with transforms v2
  

Note that this API is still Beta. While we do not expect major breaking changes, some APIs may still change according to user feedback. Please submit any feedback you may have in #6753, and you can also check out #7319 to learn more about the APIs that we suspect might involve future changes.

[BETA] New Video Swin Transformer

We added a Video SwinTransformer model is based on the Video Swin Transformer paper.

import torch
from torchvision.models.video import swin3d_t

video = torch.rand(1, 3, 32, 800, 600)
# or swin3d_b, swin3d_s
model = swin3d_t(weights="DEFAULT")
model.eval()
with torch.inference_mode():
    prediction = model(video)
print(prediction)

The model has the following accuracies on the Kinetics-400 dataset:

Model	Acc@1	Acc@5
swin3d_t	77.7	93.5
swin3d_s	79.5	94.1
swin3d_b	79.4	94.4

We would like to thank oke-aditya for this contribution.

Detailed Changes (PRs)

BC-breaking changes

[models] Fixed a bug inside ops.MLP when backpropagating with dropout>0 by implicitly setting the inplace argument of nn.Dropout to False (#7209)
[models, transforms] remove functionality scheduled for 0.15 after deprecation (#7176)
We removed deprecated functionalities according to the deprecation cycle: gen_bar_updater, model_urls/quant_model_urls in models.

Deprecations

[transforms] Change default of antialias parameter from None to 'warn' (#7160)
For all transforms / functionals that have the interpolate parameter, we change its current default from None to "warn" value that behaves exactly like None, but raises a warning indicating users to explicitly set either True, False or None. In v0.17.0 we plan remove "warn" and set the default to True.

[transforms] Deprecate functional_pil and functional_tensor and make them private (#7269)
Since v0.15.0 torchvision.transforms.functional_pil and torchvision.transforms.functional_tensor have become private and will be removed in v0.17.0. Please use torchvision.transforms.functional or torchvision.transforms.v2.functional instead.

[transforms] Undeprecate PIL int constants for interpolation (#7241)
We restored the support for integer interpolation mode (Pillow constants) which was deprecated since v0.13.0 (as PIL un-deprecated those as well).

New Features

[transforms] New transforms API (see highlight)
[models] Add Video SwinTransformer (see highlight) (#6521)

Improvements

[transforms] introduce nearest-exact interpolation (#6754)
[transforms] add sequence fill support for ElasticTransform (#7141)
[transforms] perform out of bounds check for single values and two tuples in ColorJitter (#7133)
[datasets] Fixes use download of SBU dataset (#7046) (#7051)
[hub] Add video models to torchhub (#7083)
[hub] Expose maxvit and swin_v2 models to torchhub (#7078)
[io] suppress warning in VideoReader (#6976, 6971)
[io] Set pytorch vision decoder probesize for getting stream info based on the value from decode setting (#6900) (#6950)
[io] improve warning message for missing image extension (#7150)
[io] Read video from memory newapi (#6771)
[models] Allow dropout overwrites on EfficientNet (#7031)
[models] Don't use named args in MHA calls to allow applying pytorch forward hooks to VIT (#6956)
[onnx] Support exporting RoiAlign align=True to ONNX with opset 16 (#6685)
[ops] Handle invalid reduction values (#6675)
[datasets] Add MovingMNIST dataset (#7042)
Add torchvision maintainers guide (#7109)
[Documentation] Various doc improvements (#7041, #6947, #6690, #7142, #7156, #7025, #7048, #7074, #6936, #6694, #7161, #7164, #6912, #6854, #6926, #7065, #6813)
[CI] Various CI improvements (#6864, #6863, #6855, #6856, #6803, #6893, #6865, #6804, #6866, #6742, #7273, #6999, #6713, #6972, #6954, #6968, #6987, #7004, #7010, #7014, #6915, #6797, #6759, #7060, #6857, #7212, #7199, #7186, #7183, #7178, #7163, #7181, #6789, #7110, #7088, #6955, #6788, #6970)
[tests] Various tests improvements (#7020, #6939, #6658, #7216, #6996, #7363, #7379, #7218, #7286, #6901, #7059, #7202, #6708, #7013, #7206, #7204, #7233)

Bug Fixes

[datasets] fix MNIST byte flipping (#7081)
[models] properly support deepcopying and serialization of model weights (#7107)
[models] Use inplace=None as default in ops.MLP (#7209)
[models] Fix dropout issue in swin transformers (#7224)
[reference scripts] Fix quantized classif reference - missing args (#7072)
[models, tests] [FBcode->GH] Fix GRACE_HOPPER file internal discovery (#6719)
[transforms] Replace getbands() with get_image_num_channels() (#6941)
[transforms] Switch view() with reshape() on equalize (#6772)
[transforms] add sequence fill support for ElasticTransform (#7141)
[transforms] make RandomErasing scriptable for integer value (#7134)
[video] fix bug in output format for pyav (#6672)
[video, datasets] [bugfix] Fix the output format for VideoClips.subset (#6700)
[onnx] Fix dtype for NonMaxSuppression (#7056)

Code Quality

[datasets] Remove unused import (#7245)
[models] Fix error message typo (#6682)
[models] make weights deepcopyable (#6883)
[models] Fix missing f-string prefix in error message (#6684)
[onnx] [ONNX] Rephrase ONNX RoiAlign warning for aligned=True (#6704)
[onnx] [ONNX] misc improvements (#7249)
[ops] Raise kernel launch errors instead of just print error message in cuda ops (#7080)
[ops, tests] Remove torch.jit.fuser("fuser2") in test (#7069)
[tests] replace assert torch.allclose with torch.testing.assert_allclose (#6895)
[transforms] Remove old TODO about using _log_api_usage_once() (#7277)
[transforms] Fixed repr for ElasticTransform (#6758)
[transforms] Use is False for some antialias checks (#7234)
[datasets, models] Various type-hints improvements (#6844, #6929, #6843, #7087, #6735, #6845, #6846)
[all] switch to C++17 following the core library (#7116)

Prototype

Most of these PRs (not all) relate to the transforms V2 work (#7122, #7120, #7113, #7270, #7037, #6665, #6944, #6919, #7033, #7138, #6718, #6068, #7194, #6997, #6647, #7279, #7232, #7225, #6663, #7235, #7236, #7275, #6791, #6786, #7203, #7009, #7278, #7238, #7230, #7118, #7119, #6876, #7190, #6995, #6879, #6904, #6921, #6905, #6977, #6714, #6924, #6984, #6631, #7276, #6757, #7227, #7197, #7170, #7228, #7246, #7255, #7254, #7253, #7248, #7256, #7257, #7252, #6724, #7215, #7260, #7261, #7244, #7271, #7231, #6738, #7268, #7258, #6933, #6891, #6890, #7012, #6896, #6881, #6880, #6877, #7045, #6858, #6830, #6935, #6938, #6914, #6907, #6897, #6903, #6859, #6835, #6837, #6807, #6776, #6784, #6795, #7135, #6930, #7153, #6762, #6681, #7139, #6831, #6826, #6821, #6819, #6820, #6805, #6811, #6783, #6978, #6667, #6741, #6763, #6774, #6748, #6749, #6722, #6756, #6712, #6733, #6736, #6874, #6767, #6902, #6847, #6851, #6777, #6770, #6800, #6812, #6702, #7223, #6906, #7226, #6860, #6934, #6726, #6730, #7196, #7211, #7229, #7177, #6923, #6949, #6913, #6775, #7091, #7136, #7154, #6833, #6824, #6785, #6710, #6653, #6751, #6503, #7266, #6729, #6989, #7002, #6892, #6888, #6894, #6988, #6940, #6942, #6945, #6983, #6773, #6832, #6834, #6828, #6801, #7084)

Contributors

We're grateful for our community, which helps us improve torchvision by submitting issues and PRs, and providing feedback and suggestions. The following persons have contributed patches for this release:

Aditya Gandhamal, Aditya Oke, Aidyn-A, Akira Noda, Andrey Talman, Bowen Bao, Bruno Korbar, Chen Liu, cyy, David Berard, deepsghimire, Erjia Guan, F-G Fernandez, Jithun Nair, Joao Gomes, John Detloff, Justin Chu, Karan Desai, lezcano, mpearce25, Nghia, Nicolas Hug, Nikita Shulga, nps1ngh, Omkar Salpekar, Philip Meier, Robert Perrotta, RoiEX, Samantha Andow, Sergii Dymchenko, shunsuke yokokawa, Sim Sun, Toni Blaslov, toni057, Vasilis Vryniotis, vfdev-5, Vladislav Sovrasov, vsuryamurthy, Yosua Michael Maranatha, Yuxin Wu

TorchVision 0.14.1 Release

This is a minor release, which is compatible with PyTorch 1.13.1. There are no new features added.

TorchVision 0.14, including new model registration API, new models, weights, augmentations, and more

Highlights

[BETA] New Model Registration API

Following up on the multi-weight support API that was released on the previous version, we have added a new model registration API to help users retrieve models and weights. There are now 4 new methods under the torchvision.models module: get_model, get_model_weights, get_weight, and list_models. Here are examples of how we can use them:

import torchvision
from torchvision.models import get_model, get_model_weights, list_models


max_params = 5000000

tiny_models = []
for model_name in list_models(module=torchvision.models):
    weights_enum = get_model_weights(model_name)
    if len([w for w in weights_enum if w.meta["num_params"] <= max_params]) > 0:
        tiny_models.append(model_name)

print(tiny_models)
# ['mnasnet0_5', 'mnasnet0_75', 'mnasnet1_0', 'mobilenet_v2', ...]

model = get_model(tiny_models[0], weights="DEFAULT")
print(sum(x.numel() for x in model.state_dict().values()))
# 2239188

As of now, this API is still beta and there might be changes in the future in order to improve its usability based on your feedback.

New Architecture and Model Variants

Classification Models

We’ve added the Swin Transformer V2 architecture along with pre-trained weights for its tiny/small/base variants. In addition, we have added support for the MaxViT transformer. Here is an example on how to use the models:

import torch
from torchvision.models import *

image = torch.rand(1, 3, 224, 224)
model = swin_v2_t(weights="DEFAULT").eval()
# model = maxvit_t(weights="DEFAULT").eval()
prediction = model(image)

Here is the table showing the accuracy of the models tested on ImageNet1K dataset.

Model	Acc@1	Acc@1 change over V1	Acc@5	Acc@5 change over V1
swin_v2_t	82.072	+0.598	96.132	+0.356
swin_v2_s	83.712	+0.516	96.816	+0.456
swin_v2_b	84.112	+0.530	96.864	+0.224
maxvit_t	83.700	-	96.722	-

We would like to thank Ren Pang and Teodor Poncu for contributing the 2 models to torchvision.

[BETA] Video Classification Model

We added two new video classification models, MViT and S3D. MViT is a state of the art video classification transformer model which has 80.757% accuracy on Kinetics400 dataset, while S3D is a relatively small model with good accuracy for its size. These models can be used as follows:

import torch
from torchvision.models.video import *

video = torch.rand(3, 32, 800, 600)
model = mvit_v2_s(weights="DEFAULT")
# model = s3d(weights="DEFAULT")
model.eval()
prediction = model(images)

Here is the table showing the accuracy of the new video classification models tested in the Kinetics400 dataset.

Model	Acc@1	Acc@5
mvit_v1_b	81.474	95.776
mvit_v2_s	83.196	96.36
s3d	83.582	96.64

We would like to thank Haoqi Fan, Yanghao Li, Christoph Feichtenhofer and Wan-Yen Lo for their work on PyTorchVideo and their support during the development of the MViT model. We would like to thank Sophia Zhi for her contribution implementing the S3D model in torchvision.

New Primitives & Augmentations

In this release we’ve added the SimpleCopyPaste augmentation in our reference scripts and we up-streamed the PolynomialLR scheduler to PyTorch Core. We would like to thank Lezwon Castelino and Federico Pozzi for their contributions. We are continuing our efforts to modernize TorchVision by adding more SoTA primitives, Augmentations and architectures with the help of our community. If you are interested in contributing, have a look at the following issue.

Upcoming Prototype APIs

We are currently working on extending our existing Transforms and Functional API to provide native support for Video, Object Detection, Semantic and Instance Segmentation. This will enable us to offer better support to the existing Computer Vision tasks and make importable from the TorchVision binary SoTA augmentations such as MixUp, CutMix, Large Scale Jitter and SimpleCopyPaste. The API is still under development and thus was not included in the release but you can read more about it on our blogpost and provide your feedback on the dedicated Github issue.

Backward Incompatible Changes

We’ve removed some APIs that have been deprecated since version 0.12 (or before). Here is the list of things that we removed and their replacement:

• The Kinetics400 class has been removed. Users must now use the newer Kinetics class which is a direct replacement.
• The class _DeprecatedConvBNAct, ConvBNReLU, and ConvBNActivation were removed from torchvision.models.mobilenetv2 and are replaced with the more generic Conv2dNormActivation class.
• The torchvision.models.mobilenetv3.SqueezeExcitation has been removed in favor of torchvision.ops.SqueezeExcitation.
• The class methods convert_to_roi_format, infer_scale, setup_scales from torchvision.ops.MultiScaleRoiAlign have been removed.
• We have removed the resample and fillcolor parameters from the Transforms API. They have been replaced with interpolation and fill respectively.
• We’ve removed the range parameter from torchvision.utils.make_grid as it was replaced by the value_range parameter to avoid shadowing the Python built-in method.

Detailed Changes (PRs)

Deprecations

[models] Remove cpp model in v0.14 due to deprecation (#6632)
[utils, ops, transforms, models, datasets] Remove deprecated APIs for 0.14 (#6258)

New Features

[datasets] Add various Stereo Matching datasets (#6345, #6346, #6311, #6347, #6349, #6348, #6350, #6351)
[models] Add the S3D architecture to TorchVision (#6412, #6537)
[models] add crestereo implementation (#6310, #6629)
[models] MaxVit model (#6342)
[models] Make get_model_builder public (#6560)
[models] Add registration mechanism for models (#6333, #6369)
[models] Add MViT architecture in TorchVision for both V1 and V2 (#6198, #6373)
[models] Add SwinV2 mode variant (#6246, #6266)
[reference scripts] Add stereo matching reference scripts (#6549, #6554, #6605)
[transforms] Added elastic transform in torchvision.transforms (#4938)
[build] Add M1 binary builds (#5948, #6135, #6140, #6110, #6132, #6324, #6122, #6409)

Improvements

[build] Various torchvision binary build improvements (#6396, #6201, #6230, #6199)
[build] Install NVJPEG on Windows for 11.6 and 11.7 CUDA (#6578)
[models] Change weights return type to Mapping in models api (#6097)
[models] Vectorize box decoding and encoding in FCOS (#6203, #6278)
[ci] Add CUDA 11.7 builds (#6425)
[ci] Various CI improvements (#6590, #6290, #6170, #6218)
[documentation] Various documentations improvements (#6276, #6163, #6450, #6294, #6572, #6176, #6340, #6314, #6427, #6536, #6215, #6150)
[documentation] Add new .. betastatus:: directive and document Beta APIs (#6115)
[hub] Expose on Hub the public methods of the registration API (#6364)
[io, documentation] DOC: add limitation of decode_jpeg in the function docstring (#6637)
[models] Make the assert message more verbose in vision transformer (#6583)
[ops] Generalize ConvNormActivation function to accept tuple for some parameters (#6251)
[reference scripts] Update the datase...

Minor release

This minor release bumps the pinned PyTorch version to v1.12.1 and contains some minor bug fixes.

Highlights

Bug Fixes

• Small Patch SwinTransformer for FX compatibility #6252
• Indicate strings can be used to specify weights parameter #6314
• Fix d/c IoU for different batch sizes #6338

TorchVision 0.13, including new Multi-weights API, new pre-trained weights, and more

Highlights

Models

Multi-weight support API

TorchVision v0.13 offers a new Multi-weight support API for loading different weights to the existing model builder methods:

from torchvision.models import *

# Old weights with accuracy 76.130%
resnet50(weights=ResNet50_Weights.IMAGENET1K_V1)

# New weights with accuracy 80.858%
resnet50(weights=ResNet50_Weights.IMAGENET1K_V2)

# Best available weights (currently alias for IMAGENET1K_V2)
# Note that these weights may change across versions
resnet50(weights=ResNet50_Weights.DEFAULT)

# Strings are also supported
resnet50(weights="IMAGENET1K_V2")

# No weights - random initialization
resnet50(weights=None)

The new API bundles along with the weights important details such as the preprocessing transforms and meta-data such as labels. Here is how to make the most out of it:

from torchvision.io import read_image
from torchvision.models import resnet50, ResNet50_Weights

img = read_image("test/assets/encode_jpeg/grace_hopper_517x606.jpg")

# Step 1: Initialize model with the best available weights
weights = ResNet50_Weights.DEFAULT
model = resnet50(weights=weights)
model.eval()

# Step 2: Initialize the inference transforms
preprocess = weights.transforms()

# Step 3: Apply inference preprocessing transforms
batch = preprocess(img).unsqueeze(0)

# Step 4: Use the model and print the predicted category
prediction = model(batch).squeeze(0).softmax(0)
class_id = prediction.argmax().item()
score = prediction[class_id].item()
category_name = weights.meta["categories"][class_id]
print(f"{category_name}: {100 * score:.1f}%")

You can read more about the new API in the docs. To provide your feedback, please use this dedicated Github issue.

New architectures and model variants

Classification

The Swin Transformer and EfficienetNetV2 are two popular classification models which are often used for downstream vision tasks. This release includes 6 pre-trained weights for their classification variants. Here is how to use the new models:

import torch
from torchvision.models import *

image = torch.rand(1, 3, 224, 224)
model = swin_t(weights="DEFAULT").eval()
prediction = model(image)

image = torch.rand(1, 3, 384, 384)
model = efficientnet_v2_s(weights="DEFAULT").eval()
prediction = model(image)

In addition to the above, we also provide new variants for existing architectures such as ShuffleNetV2, ResNeXt and MNASNet. The accuracies of all the new pre-trained models obtained on ImageNet-1K are seen below:

Model	Acc@1	Acc@5
swin_t	81.474	95.776
swin_s	83.196	96.36
swin_b	83.582	96.64
efficientnet_v2_s	84.228	96.878
efficientnet_v2_m	85.112	97.156
efficientnet_v2_l	85.808	97.788
resnext101_64x4d	83.246	96.454
resnext101_64x4d (quantized)	82.898	96.326
shufflenet_v2_x1_5	72.996	91.086
shufflenet_v2_x1_5 (quantized)	72.052	90.700
shufflenet_v2_x2_0	76.230	93.006
shufflenet_v2_x2_0 (quantized)	75.354	92.488
mnasnet0_75	71.180	90.496
mnas1_3	76.506	93.522

We would like to thank Hu Ye for contributing to TorchVision the Swin Transformer implementation.

[BETA] Object Detection and Instance Segmentation

We have introduced 3 new model variants for RetinaNet, FasterRCNN and MaskRCNN that include several post-paper architectural optimizations and improved training recipes. All models can be used similarly:

import torch
from torchvision.models.detection import *

images = [torch.rand(3, 800, 600)]
model = retinanet_resnet50_fpn_v2(weights="DEFAULT")
# model = fasterrcnn_resnet50_fpn_v2(weights="DEFAULT")
# model = maskrcnn_resnet50_fpn_v2(weights="DEFAULT")
model.eval()
prediction = model(images)

Below we present the metrics of the new variants on COCO val2017. In parenthesis we denote the improvement over the old variants:

Model	Box mAP	Mask mAP
retinanet_resnet50_fpn_v2	41.5 (+5.1)	-
fasterrcnn_resnet50_fpn_v2	46.7 (+9.7)	-
maskrcnn_resnet50_fpn_v2	47.4 (+9.5)	41.8 (+7.2)

We would like to thank Ross Girshick, Piotr Dollar, Vaibhav Aggarwal, Francisco Massa and Hu Ye for their past research and contributions to this work.

New pre-trained weights

SWAG weights

The ViT and RegNet model variants offer new pre-trained SWAG (Supervised Weakly from hashtAGs) weights. One of the biggest of these models achieves a whopping 88.6% accuracy on ImageNet-1K. We currently offer two versions of the weights: 1) fine-tuned end-to-end weights on ImageNet-1K (highest accuracy) and 2) frozen trunk weights with a linear classifier fit on ImageNet-1K (great for transfer learning). Below we see the detailed accuracies of each model variant:

Model Weights	Acc@1	Acc@5
RegNet_Y_16GF_Weights.IMAGENET1K_SWAG_E2E_V1	86.012	98.054
RegNet_Y_16GF_Weights.IMAGENET1K_SWAG_LINEAR_V1	83.976	97.244
RegNet_Y_32GF_Weights.IMAGENET1K_SWAG_E2E_V1	86.838	98.362
RegNet_Y_32GF_Weights.IMAGENET1K_SWAG_LINEAR_V1	84.622	97.48
RegNet_Y_128GF_Weights.IMAGENET1K_SWAG_E2E_V1	88.228	98.682
RegNet_Y_128GF_Weights.IMAGENET1K_SWAG_LINEAR_V1	86.068	97.844
ViT_B_16_Weights.IMAGENET1K_SWAG_E2E_V1	85.304	97.65
ViT_B_16_Weights.IMAGENET1K_SWAG_LINEAR_V1	81.886	96.18
ViT_L_16_Weights.IMAGENET1K_SWAG_E2E_V1	88.064	98.512
ViT_L_16_Weights.IMAGENET1K_SWAG_LINEAR_V1	85.146	97.422
ViT_H_14_Weights.IMAGENET1K_SWAG_E2E_V1	88.552	98.694
ViT_H_14_Weights.IMAGENET1K_SWAG_LINEAR_V1	85.708	97.73

The weights can be loaded normally as follows:

from torchvision.models import *

model1 = vit_h_14(weights="IMAGENET1K_SWAG_E2E_V1")
model2 = vit_h_14(weights="IMAGENET1K_SWAG_LINEAR_V1")

The SWAG weights are released under the Attribution-NonCommercial 4.0 International license. We would like to thank Laura Gustafson, Mannat Singh and Aaron Adcock for their work and support in making the weights available to TorchVision.

Model Refresh

The release of the Multi-weight support API enabled us to refresh the most popular models and offer more accurate weights. We improved on average each model by ~3 points. The new recipe used was learned on top of ResNet50 and its details were covered on a previous blogpost.

Model	Old weights	New weights
efficientnet_b1	78.642	79.838
mobilenet_v2	71.878	72.154
mobilenet_v3_large	74.042	75.274
regnet_y_400mf	74.046	75.804
regnet_y_800mf	76.42	78.828
regnet_y_1_6gf	77.95	80.876
regnet_y_3_2gf	78.948	81.982
regnet_y_8gf	80.032	82.828
regnet_y_16gf	80.424	82.886
regnet_y_32gf	80.878	83.368
regnet_x_400mf	72.834	74.864
regnet_x_800mf	75.212	77.522
regnet_x_1_6gf	77.04	79.668
regnet_x_3_2gf	78.364	81.196
regnet_x_8gf	79.344	81.682
regnet_x_16gf	80.058	82.716
regnet_x_32gf	80.622	83.014
resnet50	76.13	80.858
resnet50 (quantized)	75.92	80.282
resnet101	77.374	81.886
resnet152	78.312	82.284
resnext50_32x4d	77.618	81.198
resnext101_32x8d	79.312	82.834
resnext101_32x8d (quantized)	78.986	82.574
wide_resnet50_2	78.468	81.602
wide_resnet101_2	78.848	82.51

We would like to thank Piotr Dollar, Mannat Singh and Hugo Touvron for their past research and contributions to this work.

Ops and Transforms

New Augmentations, Layers and Losses

This release brings a bunch of new primitives which can be used to produce SOTA models. Some highlights include the addition of AugMix data-augmentation method, the DropBlock layer, the cIoU/dIoU loss and many more. We would like to thank Aditya Oke, Abhijit Deo, Yassine Alouini and Hu Ye for contributing to the project and for helping us maintain TorchVision relevant and fresh.

Documentation

We completely revamped our models documentation to make them easier to browse, and added various key information such as supported image sizes, or image pre-processing steps of pre-trained weights. We now have a main model page with various summary tables of available weights, and each model has a dedicated page. Each model builder is also documented in their own page, with more details about the available weights, including accuracy, minimal image size, lin...

TorchVision 0.12, including new Models, Datasets, GPU Video Decoding, and more

Highlights

New Models

Four new model families have been released in the latest version along with pre-trained weights for their variants: FCOS, RAFT, Vision Transformer (ViT) and ConvNeXt.

Object Detection

FCOS is a popular, fully convolutional, anchor-free model for object detection. In this release we include a community-contributed model implementation as well as pre-trained weights. The model was trained on COCO train2017 and can be used as follows:

import torch
from torchvision import models

x = [torch.rand(3, 224, 224)]
fcos = models.detection.fcos_resnet50_fpn(pretrained=True).eval()
predictions =  fcos(x)

The box AP of the pre-trained model on COCO val2017 is 39.2 (see #4961 for more details).

We would like to thank Hu Ye and Zhiqiang Wang for contributing to the model implementation and initial training. This was the first community-contributed model in a long while, and given its success, we decided to use the learnings from this process and create a new model contribution guidelines.

Optical Flow support and RAFT model

Torchvision now supports optical flow! Optical flow models try to predict movement in a video: given two consecutive frames, the model predicts where each pixel of the first frame ends up in the second frame. Check out our new tutorial on Optical Flow!

We implemented a torchscript-compatible RAFT model with pre-trained weights (both normal and “small” versions), and added support for training and evaluating optical flow models. Our training scripts support distributed training across processes and nodes, leading to much faster training time than the original implementation. We also added 5 new optical flow datasets: Flying Chairs, Flying Things, Sintel, Kitti, and HD1K.

Image Classification

Vision Transformer (ViT) and ConvNeXt are two popular architectures which can be used as image classifiers or as backbones for downstream vision tasks. In this release we include 8 pre-trained weights for their classification variants. The models were trained on ImageNet and can be used as follows:

import torch
from torchvision import models

x = torch.rand(1, 3, 224, 224)
vit = models.vit_b_16(pretrained=True).eval()
convnext = models.convnext_tiny(pretrained=True).eval()
predictions1 = vit(x)
predictions2 = convnext(x)

The accuracies of the pre-trained models obtained on ImageNet val are seen below:

Model	Acc@1	Acc@5
vit_b_16	81.072	95.318
vit_b_32	75.912	92.466
vit_l_16	79.662	94.638
vit_l_32	76.972	93.07
convnext_tiny	82.52	96.146
convnext_small	83.616	96.65
convnext_base	84.062	96.87
convnext_large	84.414	96.976

The above models have been trained using an adjusted version of our new training recipe and this allows us to offer models with accuracies significantly higher than the ones on the original papers.

GPU Video Decoding

In this release, we add support for GPU video decoding in the video reading API. To use hardware-accelerated decoding, we just need to pass a cuda device to the video reading API as shown below:

import torchvision

reader = torchvision.io.VideoReader(file_name, device='cuda:0')
for frame in reader:
    print(frame)

We also support seeking to anyframe or a keyframe in the video before reading, as shown below:

reader.seek(seek_time)

New Datasets

We have implemented 14 new classification datasets: CLEVR, GTSRB, FER2013, SUN397, Country211, Flowers102, fvgc_aircraft, OxfordIIITPet, DTD, Food 101, Rendered SST2, Stanford cars, PCAM, and EuroSAT.

As part of our work on Optical Flow support (see above for more details), we also added 5 new optical flow datasets: Flying Chairs, Flying Things, Sintel, Kitti, and HD1K.

Documentation

New documentation layout

We have updated our documentation pages to be more compact and easier to browse. Each function / class is now documented in a separate page, clearing up some space in the per-module pages, and easing the discovery of the proposed APIs. Compare e.g. our previous docs vs the new ones. Please let us know if you have any feedback!

Model contribution guidelines

New model contribution guidelines have been published following the success of the FCOS model which was contributed by the community. These guidelines aim to be an overview of the model contribution process for anyone who would like to suggest, implement and train a new model.

Upcoming Prototype APIs

We are currently working on a prototype API which adds Multi-weight support on all of our model builder methods. This will enable us to offer multiple pre-trained weights, associated with their meta-data and inference transforms. The API is still under review and thus was not included in the release but you can read more about it on our blogpost and provide your feedback on the dedicated Github issue.

Changes in our deprecation policy

Up until now, torchvision would almost never remove deprecated APIs. In order to be more aligned and consistent with pytorch core, we are updating our deprecation policy. We are now following a 2-release deprecation cycle: deprecated APIs will raise a warning for 2 versions, and will be removed after that. To reflect these changes and to smooth the transition, we have decided to:

• Remove all APIs that had been deprecated before or on v0.8, released 1.5 years ago.
• Update the removal timeline of all other deprecated APIs to v0.14, to reflect the new 2-cycle policy starting now in v0.12.

Backward-incompatible changes

[models.quantization] Removed the Quantized shufflenet_v2_x1_5 and shufflenet_v2_x2_0 model builders which had no associated weights, rendering them useless. Additionally we added pre-trained weights for the shufflenet_v2_x0_5 quantized variant.. (#4854)
[ops] Change to stable sort in nms implementations - this change can lead to different behavior in rare cases therefore it has been flagged as backwards-incompatible (#4767)
[transforms] Changed the center and the parametrization of shear X/Y in Auto Augment transforms to align with the original papers (#5285) (#5384)

Deprecations

Note: in order to be more aligned with pytorch core, we are updating our deprecation policy. Please read more above in the “Highlights” section.

[ops] The ops.poolers.MultiScaleRoIAlign public methods setup_setup_scales, convert_to_roi_format, and infer_scale have been deprecated and will be removed in 0.14 (#4951) (#4810)

New Features

[datasets] New optical flow datasets added: FlyingChairs, Kitti, Sintel, FlyingThings3D, and HD1K (#4860) (#4845) (#4858) (#4890) (#5004) (#4889) (#4888) (#4870)
[datasets] New classification datasets support for FLAVA: CLEVR, GTSRB, FER2013, SUN397, Country211, Flowers102, fvgc_aircraft, OxfordIIITPet, DTD, Food 101, Rendered SST2, Stanford cars, PCAM, and EuroSAT (#5120) (#5130) (#5117) (#5132) (#5138) (#5177) (#5178) (#5116) (#5115) (#5119) (#5220) (#5166) (#5203) (#5114) (#5164) (#5280)
[models] Add VisionTransformer model (#5173) (#5210) (#5172) (#5085) (#5226) (#5025) (#5086) (#5159)
[models] Add ConvNeXt model (#5330) (#5253)
[models] Add RAFT models and support for optical flow model training (#5022) (#5070) (#5174) (#5381) (#5078) (#5076) (#5081) (#5079) (#5026) (#5027) (#5082) (#5060) (#4868) (#4657) (#4732)
[models] Add FCOS model (#4961) (#5267)
[utils] Add utility to convert optical flow to an image (#5134) (#5308)
[utils] Add utility to draw keypoints (#4216)
[video] Add video GPU decoder (#5019) (#5191) (#5215) (#5256) (#4474) (#3179) (#4878) (#5328) (#5327) (#5183) (#4947) (#5192)

Improvements

[datasets] Migrate mnist dataset from np.frombuffer (#4598)
[io, tests] Switch from np.frombuffer to torch.frombuffer (#4578)
[models] Update ResNet-50 accuracy with Repeated Augmentation (#5201)
[models] Add regnet_y_128gf factory function, and several regnet model weights (#5176) (#4530)
[models] Adding min_size to classification and video models (#5223)
[models] Remove in-place mutation in DefaultBoxGenerator (#5279)
[models] Added Dropout parameter to Models Constructors (#4580)
[models] Allow to use custom norm_layer (#4621)
[models] Add In...

Minor release

This is a minor release compatible with PyTorch 1.10.2 and a minor bug fix.

Highlights

Bug Fixes

• [CI] Skip jpeg comparison tests with PIL (#5232)

Minor bugfix release

This minor release bumps the pinned PyTorch version to v1.10.1 and contains some minor bug fixes.

Highlights

Bug Fixes

• [CI] Fix clang_format issue (#5061)
• [CI, MOBILE] Fix binary_libtorchvision_ops_android job (#5062)
• [CI] Add numpy as explicit dependency to build_cmake.sh (#5065)
• [MODELS] Amend the weights only if quantize=True. (#5066)
• [TRANSFORMS] Fix augmentation space to be uint8 compatible (#5067)
• [DATASETS] Fix WIDERFace download links (#5068)
• [BUILD, WINDOWS] Workaround for loading bundled DLLs (#5094)

Update dependency on wheels to match version in PyPI

Users were reporting issues installing torchvision on PyPI, this release contains an update to the dependencies for wheels to point directly to torch==0.10.0