Skip to content

GitLab

Commit 2e3393b0 authored by Yeqing Li's avatar Yeqing Li Committed by A. Unique TensorFlower
Browse files

Move some documents out of beta. 

PiperOrigin-RevId: 436766118
parent ac55f024
Show whitespace changes
Inline Side-by-side
Showing with 43 additions and 43 deletions
official/README.md
View file @ 2e3393b0
...@@ -41,21 +41,21 @@ In the near future, we will add: ...@@ -41,21 +41,21 @@ In the near future, we will add:
| Model | Reference (Paper) | | Model | Reference (Paper) |
|-------|-------------------| |-------|-------------------|
| [MNIST](vision/image_classification) | A basic model to classify digits from the [MNIST dataset](http://yann.lecun.com/exdb/mnist/) | | [MNIST](legacy/image_classification) | A basic model to classify digits from the [MNIST dataset](http://yann.lecun.com/exdb/mnist/) |
| [ResNet](vision/beta/MODEL_GARDEN.md) | [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385) | | [ResNet](vision/MODEL_GARDEN.md) | [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385) |
| [ResNet-RS](vision/beta/MODEL_GARDEN.md) | [Revisiting ResNets: Improved Training and Scaling Strategies](https://arxiv.org/abs/2103.07579) | | [ResNet-RS](vision/MODEL_GARDEN.md) | [Revisiting ResNets: Improved Training and Scaling Strategies](https://arxiv.org/abs/2103.07579) |
| [EfficientNet](vision/image_classification) | [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://arxiv.org/abs/1905.11946) | | [EfficientNet](legacy/image_classification) | [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://arxiv.org/abs/1905.11946) |
| [Vision Transformer](vision/beta/MODEL_GARDEN.md) | [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929) | | [Vision Transformer](vision/MODEL_GARDEN.md) | [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929) |
#### Object Detection and Segmentation #### Object Detection and Segmentation
| Model | Reference (Paper) | | Model | Reference (Paper) |
|-------|-------------------| |-------|-------------------|
| [RetinaNet](vision/beta/MODEL_GARDEN.md) | [Focal Loss for Dense Object Detection](https://arxiv.org/abs/1708.02002) | | [RetinaNet](vision/MODEL_GARDEN.md) | [Focal Loss for Dense Object Detection](https://arxiv.org/abs/1708.02002) |
| [Mask R-CNN](vision/beta/MODEL_GARDEN.md) | [Mask R-CNN](https://arxiv.org/abs/1703.06870) | | [Mask R-CNN](vision/MODEL_GARDEN.md) | [Mask R-CNN](https://arxiv.org/abs/1703.06870) |
| [ShapeMask](vision/detection) | [ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors](https://arxiv.org/abs/1904.03239) | | [ShapeMask](legacy/detection) | [ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors](https://arxiv.org/abs/1904.03239) |
| [SpineNet](vision/beta/MODEL_GARDEN.md) | [SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization](https://arxiv.org/abs/1912.05027) | | [SpineNet](vision/MODEL_GARDEN.md) | [SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization](https://arxiv.org/abs/1912.05027) |
| [Cascade RCNN-RS and RetinaNet-RS](vision/beta/MODEL_GARDEN.md) | [Simple Training Strategies and Model Scaling for Object Detection](https://arxiv.org/abs/2107.00057)| | [Cascade RCNN-RS and RetinaNet-RS](vision/MODEL_GARDEN.md) | [Simple Training Strategies and Model Scaling for Object Detection](https://arxiv.org/abs/2107.00057)|
#### Video Classification #### Video Classification
......
official/vision/beta/MODEL_GARDEN.md → official/vision/MODEL_GARDEN.md
View file @ 2e3393b0
...@@ -24,10 +24,10 @@ segmentation. ...@@ -24,10 +24,10 @@ segmentation.
| Model | Resolution | Epochs | Top-1 | Top-5 | Download | | Model | Resolution | Epochs | Top-1 | Top-5 | Download |
| ------------ |:-------------:|--------:|--------:|--------:|---------:| | ------------ |:-------------:|--------:|--------:|--------:|---------:|
| ResNet-50 | 224x224 | 90 | 76.1 | 92.9 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnet50_tpu.yaml) | | ResNet-50 | 224x224 | 90 | 76.1 | 92.9 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/image_classification/imagenet_resnet50_tpu.yaml) |
| ResNet-50 | 224x224 | 200 | 77.1 | 93.5 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnet50_tpu.yaml) | | ResNet-50 | 224x224 | 200 | 77.1 | 93.5 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/image_classification/imagenet_resnet50_tpu.yaml) |
| ResNet-101 | 224x224 | 200 | 78.3 | 94.2 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnet101_tpu.yaml) | | ResNet-101 | 224x224 | 200 | 78.3 | 94.2 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/image_classification/imagenet_resnet101_tpu.yaml) |
| ResNet-152 | 224x224 | 200 | 78.7 | 94.3 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnet152_tpu.yaml) | | ResNet-152 | 224x224 | 200 | 78.7 | 94.3 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/image_classification/imagenet_resnet152_tpu.yaml) |
#### ResNet-RS models trained with various settings #### ResNet-RS models trained with various settings
...@@ -40,20 +40,20 @@ classification models with features: ...@@ -40,20 +40,20 @@ classification models with features:
depth, label smoothing and dropout. depth, label smoothing and dropout.
* New training methods including a 350-epoch schedule, cosine learning rate and * New training methods including a 350-epoch schedule, cosine learning rate and
EMA. EMA.
* Configs are in this [directory](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification). * Configs are in this [directory](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/image_classification).
| Model | Resolution | Params (M) | Top-1 | Top-5 | Download | | Model | Resolution | Params (M) | Top-1 | Top-5 | Download |
| --------- | :--------: | ---------: | ----: | ----: | --------:| | --------- | :--------: | ---------: | ----: | ----: | --------:|
| ResNet-RS-50 | 160x160 | 35.7 | 79.1 | 94.5 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs50_i160.yaml) \| [ckpt](https://storage.cloud.google.com/tf_model_garden/vision/resnet-rs/resnet-rs-50-i160.tar.gz) | | ResNet-RS-50 | 160x160 | 35.7 | 79.1 | 94.5 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/image_classification/imagenet_resnetrs50_i160.yaml) \| [ckpt](https://storage.cloud.google.com/tf_model_garden/vision/resnet-rs/resnet-rs-50-i160.tar.gz) |
| ResNet-RS-101 | 160x160 | 63.7 | 80.2 | 94.9 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs101_i160.yaml) \| [ckpt](https://storage.cloud.google.com/tf_model_garden/vision/resnet-rs/resnet-rs-101-i160.tar.gz) | | ResNet-RS-101 | 160x160 | 63.7 | 80.2 | 94.9 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/image_classification/imagenet_resnetrs101_i160.yaml) \| [ckpt](https://storage.cloud.google.com/tf_model_garden/vision/resnet-rs/resnet-rs-101-i160.tar.gz) |
| ResNet-RS-101 | 192x192 | 63.7 | 81.3 | 95.6 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs101_i192.yaml) \| [ckpt](https://storage.cloud.google.com/tf_model_garden/vision/resnet-rs/resnet-rs-101-i192.tar.gz) | | ResNet-RS-101 | 192x192 | 63.7 | 81.3 | 95.6 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/image_classification/imagenet_resnetrs101_i192.yaml) \| [ckpt](https://storage.cloud.google.com/tf_model_garden/vision/resnet-rs/resnet-rs-101-i192.tar.gz) |
| ResNet-RS-152 | 192x192 | 86.8 | 81.9 | 95.8 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs152_i192.yaml) \| [ckpt](https://storage.cloud.google.com/tf_model_garden/vision/resnet-rs/resnet-rs-152-i192.tar.gz) | | ResNet-RS-152 | 192x192 | 86.8 | 81.9 | 95.8 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/image_classification/imagenet_resnetrs152_i192.yaml) \| [ckpt](https://storage.cloud.google.com/tf_model_garden/vision/resnet-rs/resnet-rs-152-i192.tar.gz) |
| ResNet-RS-152 | 224x224 | 86.8 | 82.5 | 96.1 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs152_i224.yaml) \| [ckpt](https://storage.cloud.google.com/tf_model_garden/vision/resnet-rs/resnet-rs-152-i224.tar.gz) | | ResNet-RS-152 | 224x224 | 86.8 | 82.5 | 96.1 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/image_classification/imagenet_resnetrs152_i224.yaml) \| [ckpt](https://storage.cloud.google.com/tf_model_garden/vision/resnet-rs/resnet-rs-152-i224.tar.gz) |
| ResNet-RS-152 | 256x256 | 86.8 | 83.1 | 96.3 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs152_i256.yaml) \| [ckpt](https://storage.cloud.google.com/tf_model_garden/vision/resnet-rs/resnet-rs-152-i256.tar.gz) | | ResNet-RS-152 | 256x256 | 86.8 | 83.1 | 96.3 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/image_classification/imagenet_resnetrs152_i256.yaml) \| [ckpt](https://storage.cloud.google.com/tf_model_garden/vision/resnet-rs/resnet-rs-152-i256.tar.gz) |
| ResNet-RS-200 | 256x256 | 93.4 | 83.5 | 96.6 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs200_i256.yaml) \| [ckpt](https://storage.cloud.google.com/tf_model_garden/vision/resnet-rs/resnet-rs-200-i256.tar.gz) | | ResNet-RS-200 | 256x256 | 93.4 | 83.5 | 96.6 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/image_classification/imagenet_resnetrs200_i256.yaml) \| [ckpt](https://storage.cloud.google.com/tf_model_garden/vision/resnet-rs/resnet-rs-200-i256.tar.gz) |
| ResNet-RS-270 | 256x256 | 130.1 | 83.6 | 96.6 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs270_i256.yaml) \| [ckpt](https://storage.cloud.google.com/tf_model_garden/vision/resnet-rs/resnet-rs-270-i256.tar.gz) | | ResNet-RS-270 | 256x256 | 130.1 | 83.6 | 96.6 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/image_classification/imagenet_resnetrs270_i256.yaml) \| [ckpt](https://storage.cloud.google.com/tf_model_garden/vision/resnet-rs/resnet-rs-270-i256.tar.gz) |
| ResNet-RS-350 | 256x256 | 164.3 | 83.7 | 96.7 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs350_i256.yaml) \| [ckpt](https://storage.cloud.google.com/tf_model_garden/vision/resnet-rs/resnet-rs-350-i256.tar.gz) | | ResNet-RS-350 | 256x256 | 164.3 | 83.7 | 96.7 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/image_classification/imagenet_resnetrs350_i256.yaml) \| [ckpt](https://storage.cloud.google.com/tf_model_garden/vision/resnet-rs/resnet-rs-350-i256.tar.gz) |
| ResNet-RS-350 | 320x320 | 164.3 | 84.2 | 96.9 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs420_i256.yaml) \| [ckpt](https://storage.cloud.google.com/tf_model_garden/vision/resnet-rs/resnet-rs-350-i320.tar.gz) | | ResNet-RS-350 | 320x320 | 164.3 | 84.2 | 96.9 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/image_classification/imagenet_resnetrs420_i256.yaml) \| [ckpt](https://storage.cloud.google.com/tf_model_garden/vision/resnet-rs/resnet-rs-350-i320.tar.gz) |
#### Vision Transformer (ViT) #### Vision Transformer (ViT)
...@@ -109,16 +109,16 @@ evaluated on [COCO](https://cocodataset.org/) val2017. ...@@ -109,16 +109,16 @@ evaluated on [COCO](https://cocodataset.org/) val2017.
| Backbone | Resolution | Epochs | FLOPs (B) | Params (M) | Box AP | Download | | Backbone | Resolution | Epochs | FLOPs (B) | Params (M) | Box AP | Download |
| ------------ |:-------------:| -------:|--------------:|-----------:|--------:|---------:| | ------------ |:-------------:| -------:|--------------:|-----------:|--------:|---------:|
| SpineNet-49 | 640x640 | 500 | 85.4| 28.5 | 44.2 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/retinanet/coco_spinenet49_tpu.yaml) \| [TB.dev](https://tensorboard.dev/experiment/n2UN83TkTdyKZn3slCWulg/#scalars&_smoothingWeight=0)| | SpineNet-49 | 640x640 | 500 | 85.4| 28.5 | 44.2 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/retinanet/coco_spinenet49_tpu.yaml) \| [TB.dev](https://tensorboard.dev/experiment/n2UN83TkTdyKZn3slCWulg/#scalars&_smoothingWeight=0)|
| SpineNet-96 | 1024x1024 | 500 | 265.4 | 43.0 | 48.5 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/retinanet/coco_spinenet96_tpu.yaml) \| [TB.dev](https://tensorboard.dev/experiment/n2UN83TkTdyKZn3slCWulg/#scalars&_smoothingWeight=0)| | SpineNet-96 | 1024x1024 | 500 | 265.4 | 43.0 | 48.5 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/retinanet/coco_spinenet96_tpu.yaml) \| [TB.dev](https://tensorboard.dev/experiment/n2UN83TkTdyKZn3slCWulg/#scalars&_smoothingWeight=0)|
| SpineNet-143 | 1280x1280 | 500 | 524.0 | 67.0 | 50.0 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/retinanet/coco_spinenet143_tpu.yaml) \| [TB.dev](https://tensorboard.dev/experiment/n2UN83TkTdyKZn3slCWulg/#scalars&_smoothingWeight=0)| | SpineNet-143 | 1280x1280 | 500 | 524.0 | 67.0 | 50.0 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/retinanet/coco_spinenet143_tpu.yaml) \| [TB.dev](https://tensorboard.dev/experiment/n2UN83TkTdyKZn3slCWulg/#scalars&_smoothingWeight=0)|
#### Mobile-size RetinaNet (Trained from scratch): #### Mobile-size RetinaNet (Trained from scratch):
| Backbone | Resolution | Epochs | FLOPs (B) | Params (M) | Box AP | Download | | Backbone | Resolution | Epochs | FLOPs (B) | Params (M) | Box AP | Download |
| ----------- | :--------: | -----: | --------: | ---------: | -----: | --------:| | ----------- | :--------: | -----: | --------: | ---------: | -----: | --------:|
| MobileNetv2 | 256x256 | 600 | - | 2.27 | 23.5 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/retinanet/coco_mobilenetv2_tpu.yaml) | | MobileNetv2 | 256x256 | 600 | - | 2.27 | 23.5 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/retinanet/coco_mobilenetv2_tpu.yaml) |
| Mobile SpineNet-49 | 384x384 | 600 | 1.0 | 2.32 | 28.1 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/retinanet/coco_spinenet49_mobile_tpu.yaml) \| [ckpt](https://storage.cloud.google.com/tf_model_garden/vision/retinanet/spinenet49mobile.tar.gz) | | Mobile SpineNet-49 | 384x384 | 600 | 1.0 | 2.32 | 28.1 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/retinanet/coco_spinenet49_mobile_tpu.yaml) \| [ckpt](https://storage.cloud.google.com/tf_model_garden/vision/retinanet/spinenet49mobile.tar.gz) |
### Instance Segmentation Baselines ### Instance Segmentation Baselines
...@@ -126,19 +126,19 @@ evaluated on [COCO](https://cocodataset.org/) val2017. ...@@ -126,19 +126,19 @@ evaluated on [COCO](https://cocodataset.org/) val2017.
| Backbone | Resolution | Epochs | FLOPs (B) | Params (M) | Box AP | Mask AP | Download | | Backbone | Resolution | Epochs | FLOPs (B) | Params (M) | Box AP | Mask AP | Download |
| ------------ |:-------------:| -------:|-----------:|-----------:|-------:|--------:|---------:| | ------------ |:-------------:| -------:|-----------:|-----------:|-------:|--------:|---------:|
| ResNet50-FPN | 640x640 | 350 | 227.7 | 46.3 | 42.3 | 37.6 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/maskrcnn/r50fpn_640_coco_scratch_tpu4x4.yaml) | | ResNet50-FPN | 640x640 | 350 | 227.7 | 46.3 | 42.3 | 37.6 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/maskrcnn/r50fpn_640_coco_scratch_tpu4x4.yaml) |
| SpineNet-49 | 640x640 | 350 | 215.7 | 40.8 | 42.6 | 37.9 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/maskrcnn/coco_spinenet49_mrcnn_tpu.yaml) | | SpineNet-49 | 640x640 | 350 | 215.7 | 40.8 | 42.6 | 37.9 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/maskrcnn/coco_spinenet49_mrcnn_tpu.yaml) |
| SpineNet-96 | 1024x1024 | 500 | 315.0 | 55.2 | 48.1 | 42.4 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/maskrcnn/coco_spinenet96_mrcnn_tpu.yaml) | | SpineNet-96 | 1024x1024 | 500 | 315.0 | 55.2 | 48.1 | 42.4 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/maskrcnn/coco_spinenet96_mrcnn_tpu.yaml) |
| SpineNet-143 | 1280x1280 | 500 | 498.8 | 79.2 | 49.3 | 43.4 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/maskrcnn/coco_spinenet143_mrcnn_tpu.yaml) | | SpineNet-143 | 1280x1280 | 500 | 498.8 | 79.2 | 49.3 | 43.4 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/maskrcnn/coco_spinenet143_mrcnn_tpu.yaml) |
#### Cascade RCNN-RS (Trained from scratch) #### Cascade RCNN-RS (Trained from scratch)
| Backbone | Resolution | Epochs | Params (M) | Box AP | Mask AP | Download | Backbone | Resolution | Epochs | Params (M) | Box AP | Mask AP | Download
------------ | :--------: | -----: | ---------: | -----: | ------: | -------: ------------ | :--------: | -----: | ---------: | -----: | ------: | -------:
| SpineNet-49 | 640x640 | 500 | 56.4 | 46.4 | 40.0 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/maskrcnn/coco_spinenet49_cascadercnn_tpu.yaml)| | SpineNet-49 | 640x640 | 500 | 56.4 | 46.4 | 40.0 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/maskrcnn/coco_spinenet49_cascadercnn_tpu.yaml)|
| SpineNet-96 | 1024x1024 | 500 | 70.8 | 50.9 | 43.8 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/maskrcnn/coco_spinenet96_cascadercnn_tpu.yaml)| | SpineNet-96 | 1024x1024 | 500 | 70.8 | 50.9 | 43.8 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/maskrcnn/coco_spinenet96_cascadercnn_tpu.yaml)|
| SpineNet-143 | 1280x1280 | 500 | 94.9 | 51.9 | 45.0 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/maskrcnn/coco_spinenet143_cascadercnn_tpu.yaml)| | SpineNet-143 | 1280x1280 | 500 | 94.9 | 51.9 | 45.0 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/maskrcnn/coco_spinenet143_cascadercnn_tpu.yaml)|
## Semantic Segmentation ## Semantic Segmentation
...@@ -186,10 +186,10 @@ evaluated on [COCO](https://cocodataset.org/) val2017. ...@@ -186,10 +186,10 @@ evaluated on [COCO](https://cocodataset.org/) val2017.
| Model | Input (frame x stride) | Top-1 | Top-5 | Download | | Model | Input (frame x stride) | Top-1 | Top-5 | Download |
| -------- |:----------------------:|--------:|--------:|---------:| | -------- |:----------------------:|--------:|--------:|---------:|
| SlowOnly | 8 x 8 | 74.1 | 91.4 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/video_classification/k400_slowonly8x8_tpu.yaml) | | SlowOnly | 8 x 8 | 74.1 | 91.4 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/video_classification/k400_slowonly8x8_tpu.yaml) |
| SlowOnly | 16 x 4 | 75.6 | 92.1 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/video_classification/k400_slowonly16x4_tpu.yaml) | | SlowOnly | 16 x 4 | 75.6 | 92.1 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/video_classification/k400_slowonly16x4_tpu.yaml) |
| R3D-50 | 32 x 2 | 77.0 | 93.0 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/video_classification/k400_3d-resnet50_tpu.yaml) | | R3D-50 | 32 x 2 | 77.0 | 93.0 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/video_classification/k400_3d-resnet50_tpu.yaml) |
| R3D-RS-50 | 32 x 2 | 78.2 | 93.7 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/video_classification/k400_resnet3drs_50_tpu.yaml) | | R3D-RS-50 | 32 x 2 | 78.2 | 93.7 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/video_classification/k400_resnet3drs_50_tpu.yaml) |
| R3D-RS-101 | 32 x 2 | 79.5 | 94.2 | - | R3D-RS-101 | 32 x 2 | 79.5 | 94.2 | -
| R3D-RS-152 | 32 x 2 | 79.9 | 94.3 | - | R3D-RS-152 | 32 x 2 | 79.9 | 94.3 | -
| R3D-RS-200 | 32 x 2 | 80.4 | 94.4 | - | R3D-RS-200 | 32 x 2 | 80.4 | 94.4 | -
...@@ -205,8 +205,8 @@ evaluated on [COCO](https://cocodataset.org/) val2017. ...@@ -205,8 +205,8 @@ evaluated on [COCO](https://cocodataset.org/) val2017.
| Model | Input (frame x stride) | Top-1 | Top-5 | Download | | Model | Input (frame x stride) | Top-1 | Top-5 | Download |
| -------- |:----------------------:|--------:|--------:|---------:| | -------- |:----------------------:|--------:|--------:|---------:|
| SlowOnly | 8 x 8 | 77.3 | 93.6 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/video_classification/k600_slowonly8x8_tpu.yaml) | | SlowOnly | 8 x 8 | 77.3 | 93.6 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/video_classification/k600_slowonly8x8_tpu.yaml) |
| R3D-50 | 32 x 2 | 79.5 | 94.8 | [config](https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/video_classification/k600_3d-resnet50_tpu.yaml) | | R3D-50 | 32 x 2 | 79.5 | 94.8 | [config](https://github.com/tensorflow/models/blob/master/official/vision/configs/experiments/video_classification/k600_3d-resnet50_tpu.yaml) |
| R3D-RS-200 | 32 x 2 | 83.1 | - | - | R3D-RS-200 | 32 x 2 | 83.1 | - | -
| R3D-RS-200 | 48 x 2 | 83.8 | - | - | R3D-RS-200 | 48 x 2 | 83.8 | - | -
| MoViNet-A0-Base | 50 x 5 | 72.05 | 90.92 | [config](https://github.com/tensorflow/models/blob/master/official/projects/movinet/configs/yaml/movinet_a0_k600_8x8.yaml) | | MoViNet-A0-Base | 50 x 5 | 72.05 | 90.92 | [config](https://github.com/tensorflow/models/blob/master/official/projects/movinet/configs/yaml/movinet_a0_k600_8x8.yaml) |
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment