add smartlab-action-recognition-0001 readme file.

Author: wdkwyf

models/intel/device_support.md

@@ -140,5 +140,6 @@
 | smartlab-object-detection-0002 | YES | YES |  |
 | smartlab-object-detection-0003 | YES | YES |  |
 | smartlab-object-detection-0004 | YES | YES |  |
+| smartlab-action-recognition-0001 | YES | YES |  |
 | smartlab-sequence-modelling-0001 | YES | YES |  |
 | smartlab-sequence-modelling-0002 | YES | YES |  |

models/intel/index.md

@@ -475,8 +475,11 @@ Deep Learning models for online sequence modeling.
 
 | Model Name | Complexity (GFLOPs) | Size (Mp) |
 |------------|---------------------|-----------|
-| [smartlab-sequence-modelling-0001](./smartlab-sequence-modelling-0001/README.md) | 0.049   | 1.02    |
-
+| [smartlab-sequence-modelling-0001](./smartlab-sequence-modelling-0001/README.md) | 0.11   | 2.537    |
+| [smartlab-sequence-modelling-0002](./smartlab-sequence-modelling-0002/README.md) | 0.049   | 1.02    |
+| [smartlab-action-recognition-0001](./smartlab-action-recognition-0001/README.md) |    -   |   -      |
+|   smartlab-action-recognition-encoder-0001                                       | 0.611   | 3.387   |
+|   smartlab-action-recognition-decoder-0001                                       | 0.008   | 4.099   |
 ## See Also
 
 * [Open Model Zoo Demos](../../demos/README.md)

models/intel/smartlab-action-recognition-0001/README.md

@@ -0,0 +1,22 @@
+# smartlab-action-recognition-0001 (composite)
+
+## Use Case and High-Level Description
+
+This is an smartlab action recogntion model that recognizes smartlab actions.
+The model uses smartlab dataset to predict actions.
+The model is classfier for 3 class actions.
+
+## Example of the input data
+![](./assets/frame0001.jpg)
+
+## Example of the output
+Name: `decoder_hidden`, shape: `1, 3`. The foramt is:
+
+[`has_action_conf_score`, `action_1_logits`, `action_2_logits`].
+
+Detailed explaination is available in [smartlab-action-recognition-0001-decoder](./smartlab-action-recognition-0001-decoder/README.md)
+
+
+## Legal Information
+
+[*] Other names and brands may be claimed as the property of others.

models/intel/smartlab-action-recognition-0001/assets/frame0001.jpg

@@ -0,0 +1,34 @@
+# smartlab-action-recognition-0001 (decoder)
+
+## Use Case and High-Level Description
+
+This is the decoder part of smartlab action recogntion model.
+
+This model classifies action from noise_action, put_take and adjust_rider.
+
+## Decoder model specification
+
+The smartlab-action-recognition-decoder-0001 is a fully connected decoder part which accepts features from top and front views, computed by encoder and predicts score for action across following label list: `no_action`, `noise_action`,  `adjust_rider`
+
+| Metric  | Value |
+| ------- | ----- |
+| GFlops  | 0.008 |
+| MParams | 4.099 |
+
+### Inputs
+
+1. Name: `input_feature_1`, shape: `1, 1280`. Encoded features from topview.
+2. Name: `input_feature_2`, shape: `1, 1280`. Encoded features from frontview.
+
+### Outputs
+
+1. Name: `decoder_hidden`, shape: `1, 3`. The foramt [`has_action_conf_score`, `action_1_logits`, `action_2_logits`]
+    * `has_action_conf_score` - confidence for action frame. If>0.5, there is specified action.
+    * `action_1_logits` - confidence for the put_take action class
+    * `action_2_logits` - confidence for the adjust_rider action class
+
+Classification confidence scores in the [0, 1] range.
+
+## Legal Information
+
+[*] Other names and brands may be claimed as the property of others.

models/intel/smartlab-action-recognition-0001/smartlab-action-recognition-0001-decoder/README.md

@@ -0,0 +1,34 @@
+# smartlab-action-recognition-0001 (encoder-side)
+
+## Use Case and High-Level Description
+
+This is the encoder-side part of smartlab action recogntion model.
+
+This model encodes the side-view of image frame into feature vector.
+
+## Encoder model specification
+
+The smartlab-action-recognition-encoder-0001 is a Mobilenet-V2 like backbone with convolutional encoder part of the action recognition.
+
+| Metric  | Value |
+| ------- | ----- |
+| GFlops  | 0.611 |
+| MParams | 3.387 |
+
+### Inputs
+
+Image, name: `input_image`, shape: `1, 3, 224, 224` in the `B, C, H, W` format, where:
+
+- `B` - batch size
+- `C` - number of channels
+- `H` - image height
+- `W` - image width
+Expected color order is `BGR`
+
+### Outputs
+
+1. Name: `output_feature`, shape: `1, 1280`. Features from encoder part of action recogntion head.
+
+## Legal Information
+
+[*] Other names and brands may be claimed as the property of others.

models/intel/smartlab-action-recognition-0001/smartlab-action-recognition-0001-encoder-side/README.md

@@ -0,0 +1,34 @@
+# smartlab-action-recognition-0001 (encoder-top)
+
+## Use Case and High-Level Description
+
+This is the encoder-top part of smartlab action recogntion model.
+
+This model encodes the top-view of image frame into feature vector.
+
+## Encoder model specification
+
+The smartlab-action-recognition-encoder-0001 is a Mobilenet-V2 like backbone with convolutional encoder part of the action recognition.
+
+| Metric  | Value |
+| ------- | ----- |
+| GFlops  | 0.611 |
+| MParams | 3.387 |
+
+### Inputs
+
+Image, name: `input_image`, shape: `1, 3, 224, 224` in the `B, C, H, W` format, where:
+
+- `B` - batch size
+- `C` - number of channels
+- `H` - image height
+- `W` - image width
+Expected color order is `BGR`
+
+### Outputs
+
+1. Name: `output_feature`, shape: `1, 1280`. Features from encoder part of action recogntion head.
+
+## Legal Information
+
+[*] Other names and brands may be claimed as the property of others.