**Note**: This tool is still experimental and we do not guarantee that the number is correct.
**Note**: This tool is still experimental and we do not guarantee that the number is correct.
You may well use the result for simple comparisons, but double check it before you adopt it in technical reports or papers.
(1) FLOPs are related to the input shape while parameters are not. The default input shape is (1, 3, 340, 256) for 2D recognizer, (1, 3, 32, 340, 256) for 3D recognizer.
...
...
@@ -469,7 +469,7 @@ In `mmaction/core/optimizer/my_optimizer.py`:
from.registryimportOPTIMIZERS
fromtorch.optimimportOptimizer
@OPTIMIZERS.register_module
@OPTIMIZERS.register_module()
classMyOptimizer(Optimizer):
```
...
...
@@ -495,7 +495,7 @@ In `mmaction/core/optimizer/my_optimizer_constructor.py`:
@@ -13,10 +13,10 @@ the arguments of models' forward method is returned, and it will be fed into the
> Since the data in action recognition & localization may not be the same size (image size, gt bbox size, etc.), the `DataContainer` type in MMCV is used to help collect and distribute data of different size. See [here](https://github.com/open-mmlab/mmcv/blob/master/mmcv/parallel/data_container.py) for more details.
The data preparation pipeline and the dataset is decoupled.
The data preparation pipeline and the dataset is decoupled.
Usually a dataset
defines how to process the annotations while a data pipeline defines all the steps to prepare a data dict.
A data preparation pipeline consists of a sequence of operations.
A data preparation pipeline consists of a sequence of operations.
Each operation takes a dict as input and also output a dict for the next transformation.
A typical pipeline is shown in the following figure.
...
...
@@ -202,7 +202,7 @@ in [TSM: Temporal Shift Module for Efficient Video Understanding](https://arxiv.