You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
OpenVINO™ Training Extensions provides "model template" for every supported task type, which consolidates neccesary information to build a model.
36
36
Model templates are validated on various datasets and serve one-stop shop for obtaining best models in general.
37
-
If you are an experienced user, you can configure your own model based on [torchvision](https://pytorch.org/vision/stable/index.html), [pytorchcv](https://github.com/osmr/imgclsmob), [mmcv](https://github.com/open-mmlab/mmcv) and [OpenVINO Model Zoo (OMZ)](https://github.com/openvinotoolkit/open_model_zoo).
37
+
If you are an experienced user, you can configure your own model based on [torchvision](https://pytorch.org/vision/releases/v1.0.0/index.html), [pytorchcv](https://github.com/osmr/imgclsmob), [mmcv](https://github.com/open-mmlab/mmcv) and [OpenVINO Model Zoo (OMZ)](https://github.com/openvinotoolkit/open_model_zoo).
38
38
39
39
Moreover, OpenVINO™ Training Extensions provides automatic configuration of task types and hyperparameters.
40
40
The framework will identify the most suitable model template based on your dataset, and choose the best hyperparameter configuration.
@@ -51,7 +51,7 @@ OpenVINO™ Training Extensions supports the following computer vision tasks:
51
51
-**Action recognition** including action classification and detection
52
52
-**Anomaly recognition** tasks including anomaly classification, detection and segmentation
53
53
54
-
OpenVINO™ Training Extensions supports the [following learning methods](https://openvinotoolkit.github.io/training_extensions/stable/guide/explanation/algorithms/index.html):
54
+
OpenVINO™ Training Extensions supports the [following learning methods](https://openvinotoolkit.github.io/training_extensions/releases/v1.0.0/guide/explanation/algorithms/index.html):
55
55
56
56
-**Supervised**, incremental learning including class incremental scenario and contrastive learning for classification and semantic segmentation tasks
57
57
-**Semi-supervised learning**
@@ -61,17 +61,17 @@ OpenVINO™ Training Extensions will provide the following features in coming re
61
61
62
62
-**Distributed training** to accelerate the training process when you have multiple GPUs
63
63
-**Half-precision training** to save GPUs memory and use larger batch sizes
64
-
- Integrated, efficient [hyper-parameter optimization module (HPO)](https://openvinotoolkit.github.io/training_extensions/stable/guide/explanation/additional_features/hpo.html). Through dataset proxy and built-in hyper-parameter optimizer, you can get much faster hyper-parameter optimization compared to other off-the-shelf tools. The hyperparameter optimization is dynamically scheduled based on your resource budget.
64
+
- Integrated, efficient [hyper-parameter optimization module (HPO)](https://openvinotoolkit.github.io/training_extensions/releases/v1.0.0/guide/explanation/additional_features/hpo.html). Through dataset proxy and built-in hyper-parameter optimizer, you can get much faster hyper-parameter optimization compared to other off-the-shelf tools. The hyperparameter optimization is dynamically scheduled based on your resource budget.
65
65
- OpenVINO™ Training Extensions uses [Datumaro](https://openvinotoolkit.github.io/datumaro/docs/) as the backend to hadle datasets. Thanks to that, OpenVINO™ Training Extensions supports the most common academic field dataset formats for each task. We constantly working to extend supported formats to give more freedom of datasets format choice.
66
-
-[Auto-configuration functionality](https://openvinotoolkit.github.io/training_extensions/stable/guide/explanation/additional_features/auto_configuration.html). OpenVINO™ Training Extensions analyzes provided dataset and chooses the proper task and model template to have the best accuracy/speed trade-off. It will also make a random auto-split of your dataset if there is no validation set provided.
66
+
-[Auto-configuration functionality](https://openvinotoolkit.github.io/training_extensions/releases/v1.0.0/guide/explanation/additional_features/auto_configuration.html). OpenVINO™ Training Extensions analyzes provided dataset and chooses the proper task and model template to have the best accuracy/speed trade-off. It will also make a random auto-split of your dataset if there is no validation set provided.
67
67
68
68
---
69
69
70
70
## Getting Started
71
71
72
72
### Installation
73
73
74
-
Please refer to the [installation guide](https://openvinotoolkit.github.io/training_extensions/stable/guide/get_started/quick_start_guide/installation.html).
74
+
Please refer to the [installation guide](https://openvinotoolkit.github.io/training_extensions/releases/v1.0.0/guide/get_started/quick_start_guide/installation.html).
75
75
76
76
### OpenVINO™ Training Extensions CLI Commands
77
77
@@ -85,7 +85,7 @@ Please refer to the [installation guide](https://openvinotoolkit.github.io/train
85
85
-`otx demo` allows one to apply a trained model on the custom data or the online footage from a web camera and see how it will work in a real-life scenario.
86
86
-`otx explain` runs explain algorithm on the provided data and outputs images with the saliency maps to show how your model makes predictions.
87
87
88
-
You can find more details with examples in the [CLI command intro](https://openvinotoolkit.github.io/training_extensions/stable/guide/get_started/quick_start_guide/cli_commands.html).
88
+
You can find more details with examples in the [CLI command intro](https://openvinotoolkit.github.io/training_extensions/releases/v1.0.0/guide/get_started/quick_start_guide/cli_commands.html).
0 commit comments