From 8f68779cc61bdf1dfbfe03cb7da636eae1bc9c27 Mon Sep 17 00:00:00 2001 From: Ma Zerun Date: Sat, 18 Sep 2021 16:32:46 +0800 Subject: [PATCH] [Docs] Update metafile and Readme (#435) * Update metafile format. * Update accuracy of checkpoints. * Add metafile and readme for tnt. * Add converted ckpts in swin-transformer. * Fix tnt ckpt link * Update swin_transformer metafile --- configs/fp16/README.md | 2 +- configs/fp16/metafile.yml | 11 +- configs/mobilenet_v2/metafile.yml | 7 +- configs/resnet/README.md | 14 +- configs/resnet/metafile.yml | 130 +++++++-------- configs/resnext/README.md | 6 +- configs/resnext/metafile.yml | 31 ++-- configs/seresnet/metafile.yml | 7 +- configs/shufflenet_v1/metafile.yml | 7 +- configs/shufflenet_v2/metafile.yml | 7 +- configs/swin_transformer/metafile.yml | 227 ++++++++++++++++++++------ configs/tnt/README.md | 16 ++ configs/tnt/metafile.yml | 29 ++++ configs/vgg/README.md | 8 +- configs/vgg/metafile.yml | 27 +-- docs/model_zoo.md | 2 +- model-index.yml | 1 + 17 files changed, 367 insertions(+), 165 deletions(-) create mode 100644 configs/tnt/metafile.yml diff --git a/configs/fp16/README.md b/configs/fp16/README.md index 7b0d9a46..2ef4ea13 100644 --- a/configs/fp16/README.md +++ b/configs/fp16/README.md @@ -17,4 +17,4 @@ | Model | Params(M) | Flops(G) | Mem (GB) | Top-1 (%) | Top-5 (%) | Config | Download | |:---------------------:|:---------:|:--------:|:---------:|:---------:|:---------:| :---------:|:--------:| -| ResNet-50 | 25.56 | 4.12 | 1.9 |76.32 | 93.04 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/fp16/resnet50_b32x8_fp16_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/fp16/resnet50_batch256_fp16_imagenet_20210320-b3964210.pth) | [log](https://download.openmmlab.com/mmclassification/v0/fp16/resnet50_batch256_fp16_imagenet_20210320-b3964210.log.json) | +| ResNet-50 | 25.56 | 4.12 | 1.9 |76.30 | 93.07 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/fp16/resnet50_b32x8_fp16_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/fp16/resnet50_batch256_fp16_imagenet_20210320-b3964210.pth) | [log](https://download.openmmlab.com/mmclassification/v0/fp16/resnet50_batch256_fp16_imagenet_20210320-b3964210.log.json) | diff --git a/configs/fp16/metafile.yml b/configs/fp16/metafile.yml index 7fad5393..d69e25e8 100644 --- a/configs/fp16/metafile.yml +++ b/configs/fp16/metafile.yml @@ -7,8 +7,13 @@ Collections: - Weight Decay - Mixed Precision Training Training Resources: 8x V100 GPUs - Paper: https://arxiv.org/abs/1710.03740 + Paper: + URL: https://arxiv.org/abs/1710.03740 + Title: Mixed Precision Training README: configs/fp16/README.md + Code: + URI: https://github.com/open-mmlab/mmclassification/blob/a41cb2fa938d957101cc446e271486206188bf5b/mmcls/core/fp16/hooks.py#L13 + Version: v0.15.0 Models: - Name: resnet50_b32x8_fp16_dynamic_imagenet @@ -24,7 +29,7 @@ Models: - Task: Image Classification Dataset: ImageNet-1k Metrics: - Top 1 Accuracy: 76.32 - Top 5 Accuracy: 93.04 + Top 1 Accuracy: 76.30 + Top 5 Accuracy: 93.07 Weights: https://download.openmmlab.com/mmclassification/v0/fp16/resnet50_batch256_fp16_imagenet_20210320-b3964210.pth Config: configs/fp16/resnet50_b32x8_fp16_dynamic_imagenet.py diff --git a/configs/mobilenet_v2/metafile.yml b/configs/mobilenet_v2/metafile.yml index c1ad0d3d..3765f0ca 100644 --- a/configs/mobilenet_v2/metafile.yml +++ b/configs/mobilenet_v2/metafile.yml @@ -10,8 +10,13 @@ Collections: Batch Size: 256 Architecture: - MobileNet V2 - Paper: https://arxiv.org/abs/1801.04381 + Paper: + URL: https://arxiv.org/abs/1801.04381 + Title: "MobileNetV2: Inverted Residuals and Linear Bottlenecks" README: configs/mobilenet_v2/README.md + Code: + URL: https://github.com/open-mmlab/mmclassification/blob/v0.15.0/mmcls/models/backbones/mobilenet_v2.py#L101 + Version: v0.15.0 Models: - Name: mobilenet_v2_b32x8_imagenet diff --git a/configs/resnet/README.md b/configs/resnet/README.md index dbd7b365..185fffd3 100644 --- a/configs/resnet/README.md +++ b/configs/resnet/README.md @@ -30,17 +30,17 @@ | Model | Params(M) | Flops(G) | Top-1 (%) | Top-5 (%) | Config | Download | |:---------------------:|:---------:|:--------:|:---------:|:---------:|:---------:|:--------:| -| ResNet-50-b16x8 | 23.71 | 1.31 | 79.9 | 95.19 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet50_b16x8_cifar100.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar100_20210528-67b58a1b.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar100_20210528-67b58a1b.log.json) | +| ResNet-50-b16x8 | 23.71 | 1.31 | 79.90 | 95.19 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet50_b16x8_cifar100.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar100_20210528-67b58a1b.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar100_20210528-67b58a1b.log.json) | ### ImageNet | Model | Params(M) | Flops(G) | Top-1 (%) | Top-5 (%) | Config | Download | |:---------------------:|:---------:|:--------:|:---------:|:---------:|:---------:|:--------:| -| ResNet-18 | 11.69 | 1.82 | 70.07 | 89.44 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet18_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_batch256_imagenet_20200708-34ab8f90.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_batch256_imagenet_20200708-34ab8f90.log.json) | -| ResNet-34 | 21.8 | 3.68 | 73.85 | 91.53 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet34_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_batch256_imagenet_20200708-32ffb4f7.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_batch256_imagenet_20200708-32ffb4f7.log.json) | -| ResNet-50 | 25.56 | 4.12 | 76.55 | 93.15 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet50_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_batch256_imagenet_20200708-cfb998bf.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_batch256_imagenet_20200708-cfb998bf.log.json) | -| ResNet-101 | 44.55 | 7.85 | 78.18 | 94.03 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet101_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_batch256_imagenet_20200708-753f3608.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_batch256_imagenet_20200708-753f3608.log.json) | -| ResNet-152 | 60.19 | 11.58 | 78.63 | 94.16 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet152_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_batch256_imagenet_20200708-ec25b1f9.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_batch256_imagenet_20200708-ec25b1f9.log.json) | +| ResNet-18 | 11.69 | 1.82 | 69.90 | 89.43 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet18_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_8xb32_in1k_20210831-fbbb1da6.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_8xb32_in1k_20210831-fbbb1da6.log.json) | +| ResNet-34 | 21.8 | 3.68 | 73.62 | 91.59 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet34_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_8xb32_in1k_20210831-f257d4e6.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_8xb32_in1k_20210831-f257d4e6.log.json) | +| ResNet-50 | 25.56 | 4.12 | 76.55 | 93.06 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet50_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb32_in1k_20210831-ea4938fc.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb32_in1k_20210831-ea4938fc.log.json) | +| ResNet-101 | 44.55 | 7.85 | 77.97 | 94.06 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet101_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_8xb32_in1k_20210831-539c63f8.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_8xb32_in1k_20210831-539c63f8.log.json) | +| ResNet-152 | 60.19 | 11.58 | 78.48 | 94.13 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet152_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_8xb32_in1k_20210901-4d7582fa.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_8xb32_in1k_20210901-4d7582fa.log.json) | | ResNetV1D-50 | 25.58 | 4.36 | 77.54 | 93.57 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnetv1d50_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d50_b32x8_imagenet_20210531-db14775a.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d50_b32x8_imagenet_20210531-db14775a.log.json) | | ResNetV1D-101 | 44.57 | 8.09 | 78.93 | 94.48 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnetv1d101_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d101_b32x8_imagenet_20210531-6e13bcd3.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d101_b32x8_imagenet_20210531-6e13bcd3.log.json) | -| ResNetV1D-152 | 60.21 | 11.82 | 79.41 | 94.7 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnetv1d152_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d152_b32x8_imagenet_20210531-278cf22a.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d152_b32x8_imagenet_20210531-278cf22a.log.json) | +| ResNetV1D-152 | 60.21 | 11.82 | 79.41 | 94.70 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnetv1d152_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d152_b32x8_imagenet_20210531-278cf22a.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d152_b32x8_imagenet_20210531-278cf22a.log.json) | diff --git a/configs/resnet/metafile.yml b/configs/resnet/metafile.yml index e1d2a3ea..8353014d 100644 --- a/configs/resnet/metafile.yml +++ b/configs/resnet/metafile.yml @@ -10,106 +10,106 @@ Collections: Batch Size: 256 Architecture: - ResNet - Paper: https://openaccess.thecvf.com/content_cvpr_2016/html/He_Deep_Residual_Learning_CVPR_2016_paper.html + Paper: + URL: https://openaccess.thecvf.com/content_cvpr_2016/html/He_Deep_Residual_Learning_CVPR_2016_paper.html + Title: "Deep Residual Learning for Image Recognition" README: configs/resnet/README.md + Code: + URL: https://github.com/open-mmlab/mmclassification/blob/v0.15.0/mmcls/models/backbones/resnet.py#L383 + Version: v0.15.0 + - Name: ResNet-CIFAR + Metadata: + Training Data: CIFAR-10 + Training Techniques: + - SGD with Momentum + - Weight Decay + Training Resources: 8x 1080 GPUs + Epochs: 200 + Batch Size: 128 + Architecture: + - ResNet + Paper: + URL: https://openaccess.thecvf.com/content_cvpr_2016/html/He_Deep_Residual_Learning_CVPR_2016_paper.html + Title: "Deep Residual Learning for Image Recognition" + README: configs/resnet/README.md + Code: + URL: https://github.com/open-mmlab/mmclassification/blob/v0.15.0/mmcls/models/backbones/resnet_cifar.py#L10 + Version: v0.15.0 Models: - Name: resnet18_b16x8_cifar10 Metadata: FLOPs: 560000000 Parameters: 11170000 - Training Data: CIFAR-10 - Training Resources: 8x 1080 GPUs - Epochs: 200 - Batch Size: 128 - In Collection: ResNet + In Collection: ResNet-CIFAR Results: - Dataset: CIFAR-10 Metrics: - Top 1 Accuracy: 94.72 + Top 1 Accuracy: 94.82 Task: Image Classification - Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_b16x8_cifar10_20200823-f906fa4e.pth + Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_b16x8_cifar10_20210528-bd6371c8.pth Config: configs/resnet/resnet18_b16x8_cifar10.py - Name: resnet34_b16x8_cifar10 Metadata: FLOPs: 1160000000 Parameters: 21280000 - Training Data: CIFAR-10 - Training Resources: 8x 1080 GPUs - Epochs: 200 - Batch Size: 128 - In Collection: ResNet + In Collection: ResNet-CIFAR Results: - Dataset: CIFAR-10 Metrics: Top 1 Accuracy: 95.34 Task: Image Classification - Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_b16x8_cifar10_20200823-52d5d832.pth + Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_b16x8_cifar10_20210528-a8aa36a6.pth Config: configs/resnet/resnet34_b16x8_cifar10.py - Name: resnet50_b16x8_cifar10 Metadata: FLOPs: 1310000000 Parameters: 23520000 - Training Data: CIFAR-10 - Training Resources: 8x 1080 GPUs - Epochs: 200 - Batch Size: 128 - In Collection: ResNet + In Collection: ResNet-CIFAR Results: - Dataset: CIFAR-10 Metrics: - Top 1 Accuracy: 95.36 + Top 1 Accuracy: 95.55 Task: Image Classification - Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar10_20200823-882aa7b1.pth + Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar10_20210528-f54bfad9.pth Config: configs/resnet/resnet50_b16x8_cifar10.py - Name: resnet101_b16x8_cifar10 Metadata: FLOPs: 2520000000 Parameters: 42510000 - Training Data: CIFAR-10 - Training Resources: 8x 1080 GPUs - Epochs: 200 - Batch Size: 128 - In Collection: ResNet + In Collection: ResNet-CIFAR Results: - Dataset: CIFAR-10 Metrics: - Top 1 Accuracy: 95.66 + Top 1 Accuracy: 95.58 Task: Image Classification - Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_b16x8_cifar10_20200823-d9501bbc.pth + Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_b16x8_cifar10_20210528-2d29e936.pth Config: configs/resnet/resnet101_b16x8_cifar10.py - Name: resnet152_b16x8_cifar10 Metadata: FLOPs: 3740000000 Parameters: 58160000 - Training Data: CIFAR-10 - Training Resources: 8x 1080 GPUs - Epochs: 200 - Batch Size: 128 - In Collection: ResNet + In Collection: ResNet-CIFAR Results: - Dataset: CIFAR-10 Metrics: - Top 1 Accuracy: 95.96 + Top 1 Accuracy: 95.76 Task: Image Classification - Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_b16x8_cifar10_20200823-ad4d5d0c.pth + Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_b16x8_cifar10_20210528-3e8e9178.pth Config: configs/resnet/resnet152_b16x8_cifar10.py - Name: resnet50_b16x8_cifar100 Metadata: FLOPs: 1310000000 Parameters: 23710000 Training Data: CIFAR-100 - Training Resources: 8x 1080 GPUs - Epochs: 200 - Batch Size: 128 - In Collection: ResNet + In Collection: ResNet-CIFAR Results: - Dataset: CIFAR-100 Metrics: - Top 1 Accuracy: 80.51 - Top 5 Accuracy: 95.27 + Top 1 Accuracy: 79.90 + Top 5 Accuracy: 95.19 Task: Image Classification - Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_batch256_cifar100_20210410-37f13c16.pth + Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar100_20210528-67b58a1b.pth Config: configs/resnet/resnet50_b16x8_cifar100.py - Name: resnet18_b32x8_imagenet Metadata: @@ -119,10 +119,10 @@ Models: Results: - Dataset: ImageNet-1k Metrics: - Top 1 Accuracy: 70.07 - Top 5 Accuracy: 89.44 + Top 1 Accuracy: 69.90 + Top 5 Accuracy: 89.43 Task: Image Classification - Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_batch256_imagenet_20200708-34ab8f90.pth + Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_8xb32_in1k_20210831-fbbb1da6.pth Config: configs/resnet/resnet18_b32x8_imagenet.py - Name: resnet34_b32x8_imagenet Metadata: @@ -132,10 +132,10 @@ Models: Results: - Dataset: ImageNet-1k Metrics: - Top 1 Accuracy: 73.85 - Top 5 Accuracy: 91.53 + Top 1 Accuracy: 73.62 + Top 5 Accuracy: 91.59 Task: Image Classification - Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_batch256_imagenet_20200708-32ffb4f7.pth + Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_8xb32_in1k_20210831-f257d4e6.pth Config: configs/resnet/resnet34_b32x8_imagenet.py - Name: resnet50_b32x8_imagenet Metadata: @@ -146,9 +146,9 @@ Models: - Dataset: ImageNet-1k Metrics: Top 1 Accuracy: 76.55 - Top 5 Accuracy: 93.15 + Top 5 Accuracy: 93.06 Task: Image Classification - Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_batch256_imagenet_20200708-cfb998bf.pth + Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb32_in1k_20210831-ea4938fc.pth Config: configs/resnet/resnet50_b32x8_imagenet.py - Name: resnet101_b32x8_imagenet Metadata: @@ -158,10 +158,10 @@ Models: Results: - Dataset: ImageNet-1k Metrics: - Top 1 Accuracy: 78.18 - Top 5 Accuracy: 94.03 + Top 1 Accuracy: 77.97 + Top 5 Accuracy: 94.06 Task: Image Classification - Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_batch256_imagenet_20200708-753f3608.pth + Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_8xb32_in1k_20210831-539c63f8.pth Config: configs/resnet/resnet101_b32x8_imagenet.py - Name: resnet152_b32x8_imagenet Metadata: @@ -171,10 +171,10 @@ Models: Results: - Dataset: ImageNet-1k Metrics: - Top 1 Accuracy: 78.63 - Top 5 Accuracy: 94.16 + Top 1 Accuracy: 78.48 + Top 5 Accuracy: 94.13 Task: Image Classification - Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_batch256_imagenet_20200708-ec25b1f9.pth + Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_8xb32_in1k_20210901-4d7582fa.pth Config: configs/resnet/resnet152_b32x8_imagenet.py - Name: resnetv1d50_b32x8_imagenet Metadata: @@ -184,10 +184,10 @@ Models: Results: - Dataset: ImageNet-1k Metrics: - Top 1 Accuracy: 77.4 - Top 5 Accuracy: 93.66 + Top 1 Accuracy: 77.54 + Top 5 Accuracy: 93.57 Task: Image Classification - Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d50_batch256_imagenet_20200708-1ad0ce94.pth + Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d50_b32x8_imagenet_20210531-db14775a.pth Config: configs/resnet/resnetv1d50_b32x8_imagenet.py - Name: resnetv1d101_b32x8_imagenet Metadata: @@ -197,10 +197,10 @@ Models: Results: - Dataset: ImageNet-1k Metrics: - Top 1 Accuracy: 78.85 - Top 5 Accuracy: 94.38 + Top 1 Accuracy: 78.93 + Top 5 Accuracy: 94.48 Task: Image Classification - Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d101_batch256_imagenet_20200708-9cb302ef.pth + Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d101_b32x8_imagenet_20210531-6e13bcd3.pth Config: configs/resnet/resnetv1d101_b32x8_imagenet.py - Name: resnetv1d152_b32x8_imagenet Metadata: @@ -210,8 +210,8 @@ Models: Results: - Dataset: ImageNet-1k Metrics: - Top 1 Accuracy: 79.35 - Top 5 Accuracy: 94.61 + Top 1 Accuracy: 79.41 + Top 5 Accuracy: 94.70 Task: Image Classification - Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d152_batch256_imagenet_20200708-e79cb6a2.pth + Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d152_b32x8_imagenet_20210531-278cf22a.pth Config: configs/resnet/resnetv1d152_b32x8_imagenet.py diff --git a/configs/resnext/README.md b/configs/resnext/README.md index 69c12952..5f80978c 100644 --- a/configs/resnext/README.md +++ b/configs/resnext/README.md @@ -21,6 +21,6 @@ | Model | Params(M) | Flops(G) | Top-1 (%) | Top-5 (%) | Config | Download | |:---------------------:|:---------:|:--------:|:---------:|:---------:|:---------:|:--------:| | ResNeXt-32x4d-50 | 25.03 | 4.27 | 77.90 | 93.66 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnext/resnext50_32x4d_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnext/resnext50_32x4d_b32x8_imagenet_20210429-56066e27.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnext/resnext50_32x4d_b32x8_imagenet_20210429-56066e27.log.json) | -| ResNeXt-32x4d-101 | 44.18 | 8.03 | 78.71 | 94.12 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnext/resnext101_32x4d_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnext/resnext101_32x4d_b32x8_imagenet_20210506-e0fa3dd5.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnext/resnext101_32x4d_b32x8_imagenet_20210506-e0fa3dd5.log.json) | -| ResNeXt-32x8d-101 | 88.79 | 16.5 | 79.23 | 94.58 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnext/resnext101_32x8d_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnext/resnext101_32x8d_b32x8_imagenet_20210506-23a247d5.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnext/resnext101_32x8d_b32x8_imagenet_20210506-23a247d5.log.json) | -| ResNeXt-32x4d-152 | 59.95 | 11.8 | 78.93 | 94.41 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnext/resnext152_32x4d_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnext/resnext152_32x4d_b32x8_imagenet_20210524-927787be.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnext/resnext152_32x4d_b32x8_imagenet_20210524-927787be.log.json) | +| ResNeXt-32x4d-101 | 44.18 | 8.03 | 78.61 | 94.17 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnext/resnext101_32x4d_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnext/resnext101_32x4d_b32x8_imagenet_20210506-e0fa3dd5.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnext/resnext101_32x4d_b32x8_imagenet_20210506-e0fa3dd5.log.json) | +| ResNeXt-32x8d-101 | 88.79 | 16.5 | 79.27 | 94.58 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnext/resnext101_32x8d_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnext/resnext101_32x8d_b32x8_imagenet_20210506-23a247d5.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnext/resnext101_32x8d_b32x8_imagenet_20210506-23a247d5.log.json) | +| ResNeXt-32x4d-152 | 59.95 | 11.8 | 78.88 | 94.33 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnext/resnext152_32x4d_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnext/resnext152_32x4d_b32x8_imagenet_20210524-927787be.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnext/resnext152_32x4d_b32x8_imagenet_20210524-927787be.log.json) | diff --git a/configs/resnext/metafile.yml b/configs/resnext/metafile.yml index 9a2efde9..841bad4c 100644 --- a/configs/resnext/metafile.yml +++ b/configs/resnext/metafile.yml @@ -10,8 +10,13 @@ Collections: Batch Size: 256 Architecture: - ResNeXt - Paper: https://openaccess.thecvf.com/content_cvpr_2017/html/Xie_Aggregated_Residual_Transformations_CVPR_2017_paper.html + Paper: + URL: https://openaccess.thecvf.com/content_cvpr_2017/html/Xie_Aggregated_Residual_Transformations_CVPR_2017_paper.html + Title: "Aggregated Residual Transformations for Deep Neural Networks" README: configs/resnext/README.md + Code: + URL: https://github.com/open-mmlab/mmclassification/blob/v0.15.0/mmcls/models/backbones/resnext.py#L90 + Version: v0.15.0 Models: - Name: resnext50_32x4d_b32x8_imagenet @@ -22,10 +27,10 @@ Models: Results: - Dataset: ImageNet-1k Metrics: - Top 1 Accuracy: 77.92 - Top 5 Accuracy: 93.74 + Top 1 Accuracy: 77.90 + Top 5 Accuracy: 93.66 Task: Image Classification - Weights: https://download.openmmlab.com/mmclassification/v0/resnext/resnext50_32x4d_batch256_imagenet_20200708-c07adbb7.pth + Weights: https://download.openmmlab.com/mmclassification/v0/resnext/resnext50_32x4d_b32x8_imagenet_20210429-56066e27.pth Config: configs/resnext/resnext50_32x4d_b32x8_imagenet.py - Name: resnext101_32x4d_b32x8_imagenet Metadata: @@ -35,10 +40,10 @@ Models: Results: - Dataset: ImageNet-1k Metrics: - Top 1 Accuracy: 78.7 - Top 5 Accuracy: 94.34 + Top 1 Accuracy: 78.61 + Top 5 Accuracy: 94.17 Task: Image Classification - Weights: https://download.openmmlab.com/mmclassification/v0/resnext/resnext101_32x4d_batch256_imagenet_20200708-87f2d1c9.pth + Weights: https://download.openmmlab.com/mmclassification/v0/resnext/resnext101_32x4d_b32x8_imagenet_20210506-e0fa3dd5.pth Config: configs/resnext/resnext101_32x4d_b32x8_imagenet.py - Name: resnext101_32x8d_b32x8_imagenet Metadata: @@ -48,10 +53,10 @@ Models: Results: - Dataset: ImageNet-1k Metrics: - Top 1 Accuracy: 79.22 - Top 5 Accuracy: 94.52 + Top 1 Accuracy: 79.27 + Top 5 Accuracy: 94.58 Task: Image Classification - Weights: https://download.openmmlab.com/mmclassification/v0/resnext/resnext101_32x8d_batch256_imagenet_20200708-1ec34aa7.pth + Weights: https://download.openmmlab.com/mmclassification/v0/resnext/resnext101_32x8d_b32x8_imagenet_20210506-23a247d5.pth Config: configs/resnext/resnext101_32x8d_b32x8_imagenet.py - Name: resnext152_32x4d_b32x8_imagenet Metadata: @@ -61,8 +66,8 @@ Models: Results: - Dataset: ImageNet-1k Metrics: - Top 1 Accuracy: 79.06 - Top 5 Accuracy: 94.47 + Top 1 Accuracy: 78.88 + Top 5 Accuracy: 94.33 Task: Image Classification - Weights: https://download.openmmlab.com/mmclassification/v0/resnext/resnext152_32x4d_batch256_imagenet_20200708-aab5034c.pth + Weights: https://download.openmmlab.com/mmclassification/v0/resnext/resnext152_32x4d_b32x8_imagenet_20210524-927787be.pth Config: configs/resnext/resnext152_32x4d_b32x8_imagenet.py diff --git a/configs/seresnet/metafile.yml b/configs/seresnet/metafile.yml index 1865aa9a..419425dc 100644 --- a/configs/seresnet/metafile.yml +++ b/configs/seresnet/metafile.yml @@ -10,8 +10,13 @@ Collections: Batch Size: 256 Architecture: - ResNet - Paper: https://openaccess.thecvf.com/content_cvpr_2018/html/Hu_Squeeze-and-Excitation_Networks_CVPR_2018_paper.html + Paper: + URL: https://openaccess.thecvf.com/content_cvpr_2018/html/Hu_Squeeze-and-Excitation_Networks_CVPR_2018_paper.html + Title: "Squeeze-and-Excitation Networks" README: configs/seresnet/README.md + Code: + URL: https://github.com/open-mmlab/mmclassification/blob/v0.15.0/mmcls/models/backbones/seresnet.py#L58 + Version: v0.15.0 Models: - Name: seresnet50_b32x8_imagenet diff --git a/configs/shufflenet_v1/metafile.yml b/configs/shufflenet_v1/metafile.yml index 4e7720fa..04e7e464 100644 --- a/configs/shufflenet_v1/metafile.yml +++ b/configs/shufflenet_v1/metafile.yml @@ -11,8 +11,13 @@ Collections: Batch Size: 1024 Architecture: - Shufflenet V1 - Paper: https://openaccess.thecvf.com/content_cvpr_2018/html/Zhang_ShuffleNet_An_Extremely_CVPR_2018_paper.html + Paper: + URL: https://openaccess.thecvf.com/content_cvpr_2018/html/Zhang_ShuffleNet_An_Extremely_CVPR_2018_paper.html + Title: "ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices" README: configs/shufflenet_v1/README.md + Code: + URL: https://github.com/open-mmlab/mmclassification/blob/v0.15.0/mmcls/models/backbones/shufflenet_v1.py#L152 + Version: v0.15.0 Models: - Name: shufflenet_v1_1x_b64x16_linearlr_bn_nowd_imagenet diff --git a/configs/shufflenet_v2/metafile.yml b/configs/shufflenet_v2/metafile.yml index 66f857ef..a1aa95da 100644 --- a/configs/shufflenet_v2/metafile.yml +++ b/configs/shufflenet_v2/metafile.yml @@ -11,8 +11,13 @@ Collections: Batch Size: 1024 Architecture: - Shufflenet V2 - Paper: https://openaccess.thecvf.com/content_ECCV_2018/papers/Ningning_Light-weight_CNN_Architecture_ECCV_2018_paper.pdf + Paper: + URL: https://openaccess.thecvf.com/content_ECCV_2018/papers/Ningning_Light-weight_CNN_Architecture_ECCV_2018_paper.pdf + Title: "ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design" README: configs/shufflenet_v2/README.md + Code: + URL: https://github.com/open-mmlab/mmclassification/blob/v0.15.0/mmcls/models/backbones/shufflenet_v2.py#L134 + Version: v0.15.0 Models: - Name: shufflenet_v2_1x_b64x16_linearlr_bn_nowd_imagenet diff --git a/configs/swin_transformer/metafile.yml b/configs/swin_transformer/metafile.yml index e8a12635..46ea185d 100644 --- a/configs/swin_transformer/metafile.yml +++ b/configs/swin_transformer/metafile.yml @@ -1,7 +1,7 @@ Collections: - Name: Swin-Transformer Metadata: - Training Data: ImageNet + Training Data: ImageNet-1k Training Techniques: - AdamW - Weight Decay @@ -10,58 +10,179 @@ Collections: Batch Size: 1024 Architecture: - Shift Window Multihead Self Attention - Paper: https://arxiv.org/pdf/2103.14030.pdf + Paper: + URL: https://arxiv.org/pdf/2103.14030.pdf + Title: "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" README: configs/swin_transformer/README.md + Code: + URL: https://github.com/open-mmlab/mmclassification/blob/v0.15.0/mmcls/models/backbones/swin_transformer.py#L176 + Version: v0.15.0 Models: -- Config: configs/swin_transformer/swin_tiny_224_b16x64_300e_imagenet.py - In Collection: Swin-Transformer - Metadata: - FLOPs: 4360000000 - Parameters: 28290000 - Training Data: ImageNet - Training Resources: 16x 1080 GPUs - Epochs: 300 - Batch Size: 1024 - Name: swin_tiny_224_imagenet - Results: - - Dataset: ImageNet - Metrics: - Top 1 Accuracy: 81.18 - Top 5 Accuracy: 95.61 - Task: Image Classification - Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_tiny_224_b16x64_300e_imagenet_20210616_090925-66df6be6.pth -- Config: configs/swin_transformer/swin_small_224_b16x64_300e_imagenet.py - In Collection: Swin-Transformer - Metadata: - FLOPs: 8520000000 - Parameters: 48610000 - Training Data: ImageNet - Training Resources: 16x 1080 GPUs - Epochs: 300 - Batch Size: 1024 - Name: swin_small_224_imagenet - Results: - - Dataset: ImageNet - Metrics: - Top 1 Accuracy: 83.02 - Top 5 Accuracy: 96.29 - Task: Image Classification - Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_small_224_b16x64_300e_imagenet_20210615_110219-7f9d988b.pth -- Config: configs/swin_transformer/swin_base_224_b16x64_300e_imagenet.py - In Collection: Swin-Transformer - Metadata: - FLOPs: 15140000000 - Parameters: 87770000 - Training Data: ImageNet - Training Resources: 16x 1080 GPUs - Epochs: 300 - Batch Size: 1024 - Name: swin_base_224_imagenet - Results: - - Dataset: ImageNet - Metrics: - Top 1 Accuracy: 83.36 - Top 5 Accuracy: 96.44 - Task: Image Classification - Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_base_224_b16x64_300e_imagenet_20210616_190742-93230b0d.pth + - Name: swin-tiny_64xb16_in1k + Metadata: + FLOPs: 4360000000 + Parameters: 28290000 + In Collection: Swin-Transformer + Results: + - Dataset: ImageNet-1k + Metrics: + Top 1 Accuracy: 81.18 + Top 5 Accuracy: 95.61 + Task: Image Classification + Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_tiny_224_b16x64_300e_imagenet_20210616_090925-66df6be6.pth + Config: configs/swin_transformer/swin_tiny_224_b16x64_300e_imagenet.py + - Name: swin-small_64xb16_in1k + Metadata: + FLOPs: 8520000000 + Parameters: 49610000 + In Collection: Swin-Transformer + Results: + - Dataset: ImageNet-1k + Metrics: + Top 1 Accuracy: 83.02 + Top 5 Accuracy: 96.29 + Task: Image Classification + Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_small_224_b16x64_300e_imagenet_20210615_110219-7f9d988b.pth + Config: configs/swin_transformer/swin_small_224_b16x64_300e_imagenet.py + - Name: swin-base_64xb16_in1k + Metadata: + FLOPs: 15140000000 + Parameters: 87770000 + In Collection: Swin-Transformer + Results: + - Dataset: ImageNet-1k + Metrics: + Top 1 Accuracy: 83.36 + Top 5 Accuracy: 96.44 + Task: Image Classification + Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_base_224_b16x64_300e_imagenet_20210616_190742-93230b0d.pth + Config: configs/swin_transformer/swin_base_224_b16x64_300e_imagenet.py + - Name: swin-tiny_3rdparty_in1k + Metadata: + FLOPs: 4360000000 + Parameters: 28290000 + In Collection: Swin-Transformer + Results: + - Dataset: ImageNet-1k + Metrics: + Top 1 Accuracy: 81.18 + Top 5 Accuracy: 95.52 + Task: Image Classification + Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_tiny_patch4_window7_224-160bb0a5.pth + Converted From: + Weights: https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_tiny_patch4_window7_224.pth + Code: https://github.com/microsoft/Swin-Transformer/blob/777f6c66604bb5579086c4447efe3620344d95a9/models/swin_transformer.py#L458 + Config: configs/swin_transformer/swin_tiny_224_b16x64_300e_imagenet.py + - Name: swin-small_3rdparty_in1k + Metadata: + FLOPs: 8520000000 + Parameters: 49610000 + In Collection: Swin-Transformer + Results: + - Dataset: ImageNet-1k + Metrics: + Top 1 Accuracy: 83.21 + Top 5 Accuracy: 96.25 + Task: Image Classification + Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_small_patch4_window7_224-cc7a01c9.pth + Converted From: + Weights: https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_small_patch4_window7_224.pth + Code: https://github.com/microsoft/Swin-Transformer/blob/777f6c66604bb5579086c4447efe3620344d95a9/models/swin_transformer.py#L458 + Config: configs/swin_transformer/swin_small_224_b16x64_300e_imagenet.py + - Name: swin-base_3rdparty_in1k + Metadata: + FLOPs: 15140000000 + Parameters: 87770000 + In Collection: Swin-Transformer + Results: + - Dataset: ImageNet-1k + Metrics: + Top 1 Accuracy: 83.42 + Top 5 Accuracy: 96.44 + Task: Image Classification + Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_base_patch4_window7_224-4670dd19.pth + Converted From: + Weights: https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window7_224.pth + Code: https://github.com/microsoft/Swin-Transformer/blob/777f6c66604bb5579086c4447efe3620344d95a9/models/swin_transformer.py#L458 + Config: configs/swin_transformer/swin_base_224_b16x64_300e_imagenet.py + - Name: swin-base_3rdparty_in1k-384 + Metadata: + FLOPs: 44490000000 + Parameters: 87900000 + In Collection: Swin-Transformer + Results: + - Dataset: ImageNet-1k + Metrics: + Top 1 Accuracy: 84.49 + Top 5 Accuracy: 96.95 + Task: Image Classification + Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_base_patch4_window12_384-02c598a4.pth + Converted From: + Weights: https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window12_384.pth + Code: https://github.com/microsoft/Swin-Transformer/blob/777f6c66604bb5579086c4447efe3620344d95a9/models/swin_transformer.py#L458 + Config: configs/swin_transformer/swin_base_384_evalonly_imagenet.py + - Name: swin-base_in21k-pre-3rdparty_in1k + Metadata: + FLOPs: 15140000000 + Parameters: 87770000 + In Collection: Swin-Transformer + Results: + - Dataset: ImageNet-1k + Metrics: + Top 1 Accuracy: 85.16 + Top 5 Accuracy: 97.50 + Task: Image Classification + Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_base_patch4_window7_224_22kto1k-f967f799.pth + Converted From: + Weights: https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window7_224_22kto1k.pth + Code: https://github.com/microsoft/Swin-Transformer/blob/777f6c66604bb5579086c4447efe3620344d95a9/models/swin_transformer.py#L458 + Config: configs/swin_transformer/swin_base_224_b16x64_300e_imagenet.py + - Name: swin-base_in21k-pre-3rdparty_in1k-384 + Metadata: + FLOPs: 44490000000 + Parameters: 87900000 + In Collection: Swin-Transformer + Results: + - Dataset: ImageNet-1k + Metrics: + Top 1 Accuracy: 86.44 + Top 5 Accuracy: 98.05 + Task: Image Classification + Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_base_patch4_window12_384_22kto1k-d59b0d1d.pth + Converted From: + Weights: https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window12_384_22kto1k.pth + Code: https://github.com/microsoft/Swin-Transformer/blob/777f6c66604bb5579086c4447efe3620344d95a9/models/swin_transformer.py#L458 + Config: configs/swin_transformer/swin_base_384_evalonly_imagenet.py + - Name: swin-large_in21k-pre-3rdparty_in1k + Metadata: + FLOPs: 34040000000 + Parameters: 196530000 + In Collection: Swin-Transformer + Results: + - Dataset: ImageNet-1k + Metrics: + Top 1 Accuracy: 86.24 + Top 5 Accuracy: 97.88 + Task: Image Classification + Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_large_patch4_window7_224_22kto1k-5f0996db.pth + Converted From: + Weights: https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_large_patch4_window7_224_22kto1k.pth + Code: https://github.com/microsoft/Swin-Transformer/blob/777f6c66604bb5579086c4447efe3620344d95a9/models/swin_transformer.py#L458 + Config: configs/swin_transformer/swin_large_224_evalonly_imagenet.py + - Name: swin-large_in21k-pre-3rdparty_in1k-384 + Metadata: + FLOPs: 100040000000 + Parameters: 196740000 + In Collection: Swin-Transformer + Results: + - Dataset: ImageNet-1k + Metrics: + Top 1 Accuracy: 87.25 + Top 5 Accuracy: 98.25 + Task: Image Classification + Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_large_patch4_window12_384_22kto1k-0a40944b.pth + Converted From: + Weights: https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_large_patch4_window12_384_22kto1k.pth + Code: https://github.com/microsoft/Swin-Transformer/blob/777f6c66604bb5579086c4447efe3620344d95a9/models/swin_transformer.py#L458 + Config: configs/swin_transformer/swin_large_384_evalonly_imagenet.py diff --git a/configs/tnt/README.md b/configs/tnt/README.md index 7617c998..5e4bd38c 100644 --- a/configs/tnt/README.md +++ b/configs/tnt/README.md @@ -14,3 +14,19 @@ primaryClass={cs.CV} } ``` + +## Pretrain model + +The pre-trained modles are converted from [timm](https://github.com/rwightman/pytorch-image-models/). + +### ImageNet + +| Model | Params(M) | Flops(G) | Top-1 (%) | Top-5 (%) | Download | +|:---------------------:|:---------:|:--------:|:---------:|:---------:|:--------:| +| Transformer in Transformer small\* | 23.76 | 3.36 | 81.52 | 95.73 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/tnt/tnt_s_patch16_224_evalonly_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/tnt/tnt-small-p16_3rdparty_in1k_20210903-c56ee7df.pth) | [log]()| + +*Models with \* are converted from other repos.* + +## Results and models + +Waiting for adding. diff --git a/configs/tnt/metafile.yml b/configs/tnt/metafile.yml new file mode 100644 index 00000000..ff8558b3 --- /dev/null +++ b/configs/tnt/metafile.yml @@ -0,0 +1,29 @@ +Collections: + - Name: Transformer in Transformer + Metadata: + Training Data: ImageNet-1k + Paper: + URL: https://arxiv.org/abs/2103.00112 + Title: "Transformer in Transformer" + README: configs/tnt/README.md + Code: + URL: https://github.com/open-mmlab/mmclassification/blob/v0.15.0/mmcls/models/backbones/tnt.py#L203 + Version: v0.15.0 + +Models: + - Name: tnt-small-p16_3rdparty_in1k + Metadata: + FLOPs: 3360000000 + Parameters: 23760000 + In Collection: Transformer in Transformer + Results: + - Dataset: ImageNet-1k + Metrics: + Top 1 Accuracy: 81.52 + Top 5 Accuracy: 95.73 + Task: Image Classification + Weights: https://download.openmmlab.com/mmclassification/v0/tnt/tnt-small-p16_3rdparty_in1k_20210903-c56ee7df.pth + Config: configs/tnt/tnt_s_patch16_224_evalonly_imagenet.py + Converted From: + Weights: https://github.com/contrastive/pytorch-image-models/releases/download/TNT/tnt_s_patch16_224.pth.tar + Code: https://github.com/contrastive/pytorch-image-models/blob/809271b0f3e5d9be4e11c0c5cec1dbba8b5e2c60/timm/models/tnt.py#L144 diff --git a/configs/vgg/README.md b/configs/vgg/README.md index 6bda72f9..f1f59255 100644 --- a/configs/vgg/README.md +++ b/configs/vgg/README.md @@ -24,7 +24,7 @@ | VGG-13 | 133.05 | 11.34 | 70.02 | 89.46 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/vgg/vgg13_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/vgg/vgg13_batch256_imagenet_20210208-4d1d6080.pth) | [log](https://download.openmmlab.com/mmclassification/v0/vgg/vgg13_batch256_imagenet_20210208-4d1d6080.log.json) | | VGG-16 | 138.36 | 15.5 | 71.62 | 90.49 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/vgg/vgg16_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/vgg/vgg16_batch256_imagenet_20210208-db26f1a5.pth) | [log](https://download.openmmlab.com/mmclassification/v0/vgg/vgg16_batch256_imagenet_20210208-db26f1a5.log.json) | | VGG-19 | 143.67 | 19.67 | 72.41 | 90.80 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/vgg/vgg19_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/vgg/vgg19_batch256_imagenet_20210208-e6920e4a.pth) | [log](https://download.openmmlab.com/mmclassification/v0/vgg/vgg19_batch256_imagenet_20210208-e6920e4a.log.json)| -| VGG-11-BN | 132.87 | 7.64 | 70.75 | 90.12 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/vgg/vgg11bn_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/vgg/vgg11_bn_batch256_imagenet_20210207-f244902c.pth) | [log](https://download.openmmlab.com/mmclassification/v0/vgg/vgg11_bn_batch256_imagenet_20210207-f244902c.log.json) | -| VGG-13-BN | 133.05 | 11.36 | 72.15 | 90.71 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/vgg/vgg13bn_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/vgg/vgg13_bn_batch256_imagenet_20210207-1a8b7864.pth) | [log](https://download.openmmlab.com/mmclassification/v0/vgg/vgg13_bn_batch256_imagenet_20210207-1a8b7864.log.json) | -| VGG-16-BN | 138.37 | 15.53 | 73.72 | 91.68 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/vgg/vgg16_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/vgg/vgg16_bn_batch256_imagenet_20210208-7e55cd29.pth) | [log](https://download.openmmlab.com/mmclassification/v0/vgg/vgg16_bn_batch256_imagenet_20210208-7e55cd29.log.json) | -| VGG-19-BN | 143.68 | 19.7 | 74.70 | 92.24 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/vgg/vgg19bn_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/vgg/vgg19_bn_batch256_imagenet_20210208-da620c4f.pth) | [log](https://download.openmmlab.com/mmclassification/v0/vgg/vgg19_bn_batch256_imagenet_20210208-da620c4f.log.json)| +| VGG-11-BN | 132.87 | 7.64 | 70.67 | 90.16 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/vgg/vgg11bn_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/vgg/vgg11_bn_batch256_imagenet_20210207-f244902c.pth) | [log](https://download.openmmlab.com/mmclassification/v0/vgg/vgg11_bn_batch256_imagenet_20210207-f244902c.log.json) | +| VGG-13-BN | 133.05 | 11.36 | 72.12 | 90.66 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/vgg/vgg13bn_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/vgg/vgg13_bn_batch256_imagenet_20210207-1a8b7864.pth) | [log](https://download.openmmlab.com/mmclassification/v0/vgg/vgg13_bn_batch256_imagenet_20210207-1a8b7864.log.json) | +| VGG-16-BN | 138.37 | 15.53 | 73.74 | 91.66 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/vgg/vgg16_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/vgg/vgg16_bn_batch256_imagenet_20210208-7e55cd29.pth) | [log](https://download.openmmlab.com/mmclassification/v0/vgg/vgg16_bn_batch256_imagenet_20210208-7e55cd29.log.json) | +| VGG-19-BN | 143.68 | 19.7 | 74.68 | 92.27 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/vgg/vgg19bn_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/vgg/vgg19_bn_batch256_imagenet_20210208-da620c4f.pth) | [log](https://download.openmmlab.com/mmclassification/v0/vgg/vgg19_bn_batch256_imagenet_20210208-da620c4f.log.json)| diff --git a/configs/vgg/metafile.yml b/configs/vgg/metafile.yml index a055d9ea..0c944812 100644 --- a/configs/vgg/metafile.yml +++ b/configs/vgg/metafile.yml @@ -10,8 +10,13 @@ Collections: Batch Size: 256 Architecture: - VGG - Paper: https://arxiv.org/abs/1409.1556 + Paper: + URL: https://arxiv.org/abs/1409.1556 + Title: "Very Deep Convolutional Networks for Large-Scale Image" README: configs/vgg/README.md + Code: + URL: https://github.com/open-mmlab/mmclassification/blob/v0.15.0/mmcls/models/backbones/vgg.py#L39 + Version: v0.15.0 Models: - Name: vgg11_b32x8_imagenet @@ -74,8 +79,8 @@ Models: Results: - Dataset: ImageNet-1k Metrics: - Top 1 Accuracy: 70.75 - Top 5 Accuracy: 90.12 + Top 1 Accuracy: 70.67 + Top 5 Accuracy: 90.16 Task: Image Classification Weights: https://download.openmmlab.com/mmclassification/v0/vgg/vgg11_bn_batch256_imagenet_20210207-f244902c.pth Config: configs/vgg/vgg11bn_b32x8_imagenet.py @@ -87,12 +92,12 @@ Models: Results: - Dataset: ImageNet-1k Metrics: - Top 1 Accuracy: 72.15 - Top 5 Accuracy: 90.71 + Top 1 Accuracy: 72.12 + Top 5 Accuracy: 90.66 Task: Image Classification Weights: https://download.openmmlab.com/mmclassification/v0/vgg/vgg13_bn_batch256_imagenet_20210207-1a8b7864.pth Config: configs/vgg/vgg13bn_b32x8_imagenet.py - - Name: vgg16_b32x8_imagenet + - Name: vgg16bn_b32x8_imagenet Metadata: FLOPs: 15530000000 Parameters: 138370000 @@ -100,11 +105,11 @@ Models: Results: - Dataset: ImageNet-1k Metrics: - Top 1 Accuracy: 73.72 - Top 5 Accuracy: 91.68 + Top 1 Accuracy: 73.74 + Top 5 Accuracy: 91.66 Task: Image Classification Weights: https://download.openmmlab.com/mmclassification/v0/vgg/vgg16_bn_batch256_imagenet_20210208-7e55cd29.pth - Config: configs/vgg/vgg16_b32x8_imagenet.py + Config: configs/vgg/vgg16bn_b32x8_imagenet.py - Name: vgg19bn_b32x8_imagenet Metadata: FLOPs: 19700000000 @@ -113,8 +118,8 @@ Models: Results: - Dataset: ImageNet-1k Metrics: - Top 1 Accuracy: 74.7 - Top 5 Accuracy: 92.24 + Top 1 Accuracy: 74.68 + Top 5 Accuracy: 92.27 Task: Image Classification Weights: https://download.openmmlab.com/mmclassification/v0/vgg/vgg19_bn_batch256_imagenet_20210208-da620c4f.pth Config: configs/vgg/vgg19bn_b32x8_imagenet.py diff --git a/docs/model_zoo.md b/docs/model_zoo.md index 6fb0ccb1..ab9f25fb 100644 --- a/docs/model_zoo.md +++ b/docs/model_zoo.md @@ -43,7 +43,7 @@ The ResNet family models below are trained by standard data augmentations, i.e., | Swin-Transformer tiny | 28.29 | 4.36 | 81.18 | 95.61 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/swin_transformer/swin_tiny_224_b16x64_300e_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_tiny_224_b16x64_300e_imagenet_20210616_090925-66df6be6.pth) | [log](https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_tiny_224_b16x64_300e_imagenet_20210616_090925.log.json)| | Swin-Transformer small| 49.61 | 8.52 | 83.02 | 96.29 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/swin_transformer/swin_small_224_b16x64_300e_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_small_224_b16x64_300e_imagenet_20210615_110219-7f9d988b.pth) | [log](https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_small_224_b16x64_300e_imagenet_20210615_110219.log.json)| | Swin-Transformer base | 87.77 | 15.14 | 83.36 | 96.44 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/swin_transformer/swin_base_224_b16x64_300e_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_base_224_b16x64_300e_imagenet_20210616_190742-93230b0d.pth) | [log](https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_base_224_b16x64_300e_imagenet_20210616_190742.log.json)| -| Transformer in Transformer small* | 23.76 | 3.36 | 81.52 | 95.73 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/tnt/tnt_s_patch16_224_evalonly_imagenet) | [model](http://download.openmmlab.com/mmclassification/v0/transformer-in-transformer/convert/tnt_s_patch16_224_evalonly_imagenet.pth) | [log]()| +| Transformer in Transformer small\* | 23.76 | 3.36 | 81.52 | 95.73 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/tnt/tnt_s_patch16_224_evalonly_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/tnt/tnt-small-p16_3rdparty_in1k_20210903-c56ee7df.pth) | [log]()| Models with * are converted from other repos, others are trained by ourselves. diff --git a/model-index.yml b/model-index.yml index 5737454e..4d873f94 100644 --- a/model-index.yml +++ b/model-index.yml @@ -8,3 +8,4 @@ Import: - configs/shufflenet_v2/metafile.yml - configs/swin_transformer/metafile.yml - configs/vgg/metafile.yml + - configs/tnt/metafile.yml