supervisely 6.73.410__py3-none-any.whl → 6.73.470__py3-none-any.whl

supervisely/template/experiment/experiment.html.jinja

@@ -14,7 +14,7 @@ Here are prediction samples made with **{{ experiment.training.checkpoints.pytor
 
 ## Evaluation
 
-The **{{ experiment.training.checkpoints.pytorch.name }}** checkpoint was evaluated on the validation set containing **{{ experiment.project.splits.val }}
+The **{{ experiment.training.checkpoints.pytorch.name }}** checkpoint was evaluated on the validation set containing **{{ experiment.project.splits.val.size }}
 images**.
 
 See the full [📊 Evaluation Report]({{ experiment.training.evaluation.url }}) for details and visualizations.
@@ -28,6 +28,35 @@ was performed.
 
 {% endif %}
 
+{% if widgets.training_plots %}
+
+## Training Plots
+
+Visualization of the training scalars logged during the experiment.
+
+{% if experiment.training.logs.path %}
+<div>
+    <sly-iw-launch-button
+        class="training-plots-button"
+        style=""
+        :disabled="false"
+        :autoRun="true"
+        :state="{ 'slyFolder': '{{ experiment.training.logs.path }}' }"
+        :moduleId="{{ resources.apps.log_viewer.module_id }}"
+        :proxyKeepUrl="true"
+        :openInNewWindow="true"
+        :command="command">
+        <span>Open Logs</span> <i class="zmdi zmdi-arrow-right-top" />
+    </sly-iw-launch-button>
+</div>
+{% endif %}
+
+<div class="training-plots">
+    {{ widgets.training_plots | safe }}
+</div>
+
+{% endif %}
+
 ## Artifacts
 
 [📂 Open in Team Files]({{ experiment.paths.artifacts_dir.url }}){:target="_blank"}
@@ -89,10 +118,8 @@ The quick actions on this page, such as **Deploy**, **Predict**, or **Fine-tune*
 }}){:target="_blank"} - deploy your model in the Supervisely Platform.
 - [Train {{ experiment.model.framework }}]({{ env.server_address }}/ecosystem/apps/{{ resources.apps.train.slug
 }}){:target="_blank"} - train a model in the Supervisely Platform.
-- [Apply NN to Images]({{ env.server_address }}/ecosystem/apps/{{ resources.apps.apply_nn_to_images.slug }}){:target="_blank"} -
-connect to your model and make predictions on image project or dataset.
-- [Apply NN to Videos]({{ env.server_address }}/ecosystem/apps/{{ resources.apps.apply_nn_to_videos.slug }}){:target="_blank"} -
-for predictions on video project or dataset.
+- [Predict App]({{ env.server_address }}/ecosystem/apps/{{ resources.apps.predict.slug }}){:target="_blank"} -
+deploy your model and make predictions.
 
 ## API Integration & Deployment
 
@@ -100,10 +127,20 @@ In this section, you'll find the quickstart guides for integrating your model in
 
 ### Table of contents:
 
-- [Supervisely API](#supervisely-api)
-- [Deploy in Docker](#deploy-in-docker)
-- [Deploy locally with Supervisely SDK](#deploy-locally-with-supervisely-sdk)
-- [Using Original Model Codebase](#using-original-model-codebase)
+<ul>
+<li>
+<a :href="`${location.pathname}#supervisely-api`">Supervisely API</a>
+</li>
+<li>
+<a :href="`${location.pathname}#deploy-in-docker`">Deploy in Docker</a>
+</li>
+<li>
+<a :href="`${location.pathname}#deploy-locally-with-supervisely-sdk`">Deploy locally with Supervisely SDK</a>
+</li>
+<li>
+<a :href="`${location.pathname}#using-original-model-codebase`">Using Original Model Codebase API</a>
+</li>
+</ul>
 
 ## Supervisely API
 
@@ -137,6 +174,7 @@ can pass them in the terminal before running the script:
     model = api.nn.deploy(
         model="{{ experiment.paths.artifacts_dir.path }}/checkpoints/{{ experiment.training.checkpoints.pytorch.name }}",
         device="cuda:0", # or "cpu"
+        workspace_id={{ experiment.project.workspace_id }}
     )
 
     # 3. Predict
@@ -163,6 +201,7 @@ api = sly.Api()
 model = api.nn.deploy(
     model="{{ experiment.paths.artifacts_dir.path }}/checkpoints/{{ experiment.training.checkpoints.pytorch.name }}",
     device="cuda:0", # or "cpu"
+    workspace_id={{ experiment.project.workspace_id }}
 )
 ```
 
@@ -180,6 +219,7 @@ api = sly.Api()
 model = api.nn.deploy(
     model="{{ experiment.paths.artifacts_dir.path }}/export/{{ experiment.training.checkpoints.onnx.name }}",
     device="cuda:0", # or "cpu"
+    workspace_id={{ experiment.project.workspace_id }}
 )
 ```
 
@@ -198,6 +238,7 @@ api = sly.Api()
 model = api.nn.deploy(
     model="{{ experiment.paths.artifacts_dir.path }}/export/{{ experiment.training.checkpoints.tensorrt.name }}",
     device="cuda:0", # or "cpu"
+    workspace_id={{ experiment.project.workspace_id }}
 )
 ```
 
@@ -207,7 +248,7 @@ model = api.nn.deploy(
 {% endtabs %}
 
 > For more information, see [Model
-API](https://docs.supervisely.com/neural-networks/overview-1/model-api){:target="_blank"}
+API](https://docs.supervisely.com/neural-networks/inference-and-deployment/model-api){:target="_blank"}
 documentation.
 
 ### Predict via API
@@ -232,7 +273,9 @@ predictions = model.predict(
 
 ```python
 # Predict images in Supervisely
-predictions = model.predict(image_ids=[123, 124] # Image IDs in Supervisely)
+predictions = model.predict(
+    image_ids=[123, 124] # Image IDs in Supervisely
+)
 ```
 
 {% endtab %}
@@ -241,7 +284,9 @@ predictions = model.predict(image_ids=[123, 124] # Image IDs in Supervisely)
 
 ```python
 # Predict dataset
-predictions = model.predict(dataset_id=12 # Dataset ID in Supervisely)
+predictions = model.predict(
+    dataset_id=12 # Dataset ID in Supervisely
+)
 ```
 
 {% endtab %}
@@ -250,7 +295,9 @@ predictions = model.predict(dataset_id=12 # Dataset ID in Supervisely)
 
 ```python
 # Predict project
-predictions = model.predict(project_id=21 # Project ID in Supervisely)
+predictions = model.predict(
+    project_id=21 # Project ID in Supervisely
+)
 ```
 
 {% endtab %}
@@ -259,7 +306,9 @@ predictions = model.predict(project_id=21 # Project ID in Supervisely)
 
 ```python
 # Predict video
-predictions = model.predict(video_id=123 # Video ID in Supervisely)
+predictions = model.predict(
+    video_id=123 # Video ID in Supervisely
+)
 ```
 
 {% endtab %}
@@ -267,55 +316,47 @@ predictions = model.predict(video_id=123 # Video ID in Supervisely)
 {% endtabs %}
 
 > For more information, see [Prediction
-API](https://docs.supervisely.com/neural-networks/overview-1/prediction-api){:target="_blank"}.
+API](https://docs.supervisely.com/neural-networks/inference-and-deployment/prediction-api){:target="_blank"}.
 
 {% if experiment.model.task_type == "object detection" %}
 
 ## Tracking Objects in Video
 
-You can track objects in video using `boxmot` library.
-[BoxMot](https://github.com/mikel-brostrom/boxmot){:target="_blank"} is a
-third-party library that implements lightweight neural networks for tracking-by-detection task (when the tracking is
-performed on the objects predicted by a separate detector). For `boxmot` models you can use even CPU device.
-
-First, install [BoxMot](https://github.com/mikel-brostrom/boxmot){:target="_blank"}:
+Supervisely now supports **tracking-by-detection** out of the box. We leverage a lightweight tracking algorithm (such as [BoT-SORT](https://github.com/NirAharon/BoT-SORT){:target="_blank"}) which identifies the unique objects across video frames and assigns IDs to them. This allows us to connect separate detections from different frames into a single track for each object.
 
-```bash
-pip install boxmot
-```
-
-Supervisely SDK has the `track()` method from `supervisely.nn.tracking` which allows you to apply `boxmot` models
-together with a detector in a single line of code. This method takes two arguments: a `boxmot` tracker, and a
-`PredictionSession` of a detector. It returns a `sly.VideoAnnotation` with the tracked objects.
+To apply tracking via API, first, deploy your detection model or connect to it, and then use the `predict()` method with `tracking=True` parameter. You can also specify tracking configuration parameters by passing `tracking_config={...}` with your custom settings.
 
 ```python
 import supervisely as sly
-from supervisely.nn.tracking import track
-import boxmot
-from pathlib import Path
-
-# Deploy a detector
-detector = api.nn.deploy(
-    model="{{ experiment.model.framework }}/{{ experiment.model.name }}",
-    device="cuda:0", # Use GPU for detection
-)
 
-# Load BoxMot tracker
-tracker = boxmot.BotSort(
-    reid_weights=Path('osnet_x0_25_msmt17.pt'),
-    device="cpu", # Use CPU for tracking
+api = sly.Api()
+
+# Deploy your model
+model = api.nn.deploy(
+    model="{{ experiment.paths.artifacts_dir.path }}/checkpoints/{{ experiment.training.checkpoints.pytorch.name }}",
+    device="cuda",
+    workspace_id={{ experiment.project.workspace_id }},
 )
 
-# Track objects in a single line
-video_ann: sly.VideoAnnotation = track(
-    video_id=42,
-    detector=detector,
-    tracker=tracker,
+# Apply tracking
+predictions = model.predict(
+    video_id=YOUR_VIDEO_ID,  # Video ID in Supervisely
+    tracking=True,
+    tracking_config={
+        "tracker": "botsort",  # botsort is a powerful tracking algorithm used by default
+        # You can pass other tracking parameters here, see the docs for details
+    }
 )
+
+# Processing results
+for pred in predictions:
+    frame_index = pred.frame_index
+    annotation = pred.annotation
+    track_ids = pred.track_ids
+    print(f"Frame {frame_index}: {len(track_ids)} tracks")
 ```
 
-> For more information, see the section [Tracking Objects in
-Video](https://docs.supervisely.com/neural-networks/overview-1/prediction-api#tracking-objects-in-video){:target="_blank"}.
+> You can also apply trackers in your own code or applications. Read more about this in the docs [Video Object Tracking](https://docs.supervisely.com/neural-networks/inference-and-deployment/video-object-tracking){:target="_blank"}.
 
 {% endif %}
 
@@ -324,9 +365,9 @@ Video](https://docs.supervisely.com/neural-networks/overview-1/prediction-api#tr
 You can deploy the model in a 🐋 Docker Container with a single `docker run` command. Download a checkpoint, pull the
 docker image for the corresponding model's framework, and run the `docker run` command with addtional arguments.
 
-1. Download checkpoint from Supervisely ([Open in Team Files]({{ experiment.paths.checkpoints_dir.url }}){:target="_blank"})
+1. Download training artifacts from Supervisely ([Open in Team Files]({{ experiment.paths.artifacts_dir.url }}){:target="_blank"})
 
-2. Pull the Docker image
+2. Pull the Docker image for deployment
 
     ```bash
     docker pull {{ code.docker.deploy }}
@@ -361,7 +402,7 @@ docker image for the corresponding model's framework, and run the `docker run` c
     )
     ```
 
-See the [Model API](https://docs.supervisely.com/neural-networks/overview-1/model-api){:target="_blank"} documentation for more details on how to use the `ModelAPI` class.
+See the [Model API](https://docs.supervisely.com/neural-networks/inference-and-deployment/model-api){:target="_blank"} documentation for more details on how to use the `ModelAPI` class.
 
 Alternatively, you can use `docker run` with the `predict` action to make predictions in a single command. This is a
 quick way to start inference on your local images, videos, or directories without deploying the model. The container will be automatically stopped after the predictions are made.
@@ -379,7 +420,7 @@ docker run \
 ```
 
 > For more information, see [Deploy in Docker
-Container](https://docs.supervisely.com/neural-networks/overview-1/deploy_and_predict_with_supervisely_sdk#deploy-in-docker-container){:target="_blank"}
+Container](https://docs.supervisely.com/neural-networks/inference-and-deployment/deploy_and_predict_with_supervisely_sdk#deploy-in-docker-container){:target="_blank"}
 documentation.
 
 ## Deploy locally with Supervisely SDK
@@ -424,7 +465,7 @@ This approach helps you to quickly set up the environment and run inference with
     )
     ```
 
-> For more information, see [Local Deployment](https://docs.supervisely.com/neural-networks/overview-1/deploy_and_predict_with_supervisely_sdk){:target="_blank"} and [Prediction API](https://docs.supervisely.com/neural-networks/overview-1/prediction-api){:target="_blank"} documentations.
+> For more information, see [Local Deployment](https://docs.supervisely.com/neural-networks/inference-and-deployment/deploy_and_predict_with_supervisely_sdk){:target="_blank"} and [Prediction API](https://docs.supervisely.com/neural-networks/inference-and-deployment/prediction-api){:target="_blank"} documentations.
 
 {% if experiment.training.checkpoints.onnx.name or experiment.training.checkpoints.tensorrt.name %}
 ### Deploy ONNX/TensorRT
@@ -484,11 +525,20 @@ using the original code from the authors.
 
 1. Download checkpoint from Supervisely ([Open in Team Files]({{ experiment.paths.checkpoints_dir.url }}){:target="_blank"})
 
-2. Prepare environment following the instructions of the original repository [{{ code.local_prediction.repo.name }}]({{
-code.local_prediction.repo.url }}){:target="_blank"}
+{% if resources.original_repository.name and resources.original_repository.url %}
+
+2. Prepare environment following the instructions of the original repository [{{ resources.original_repository.name }}]({{
+resources.original_repository.url }}){:target="_blank"}
+
+3. Use the demo script for inference:
+
+{% else %}
+2. Prepare environment following the instructions of the original repository
 
 3. Use the demo script for inference:
 
+{% endif %}
+
 <details>
 <summary><strong>🐍 View Code</strong></summary>