Model Card Template

For a public HubAI model, Model Card should be structured as follows:

Code

1# Model Details
2
3## Model Description
4
5TODO
6
7- **Developed by:**: TODO
8- **Shared by:** TODO
9- **Model type:** TODO
10- **License:** TODO
11- **Resources for more information:**
12    - TODO
13
14# Training Details
15
16## Training Data
17
18TODO
19
20# Testing Details
21
22## Metrics
23
24TODO
25
26# Technical Specifications
27
28## Input/Output Details
29
30- **Input**:
31    - Name: TODO
32    - Info: TODO
33- **Output**:
34    - Name: TODO
35    - Info: TODO
36
37## Model Architecture
38
39TODO
40
41## Throughput
42
43### Model variant: TODO
44• **Input shape**: TODO • **Output shape**: TODO
45• **Params (M)**: TODO • **GFLOPs**: TODO
46| Platform | Precision | Throughput (infs/sec) | Power Consumption (W) |
47|----------|-----------|-----------------------|-----------------------|
48| RVC2     | TODO      | TODO                  | TODO                  |
49| RVC3     | TODO      | TODO                  | TODO                  |
50| RVC4     | TODO      | TODO                  | TODO                  |
51
52### Model variant: TODO
53...
54
55\* Benchmarked with [DAIv3](https://docs.luxonis.com/software-v3/depthai/), using 2 threads (and the DSP runtime in balanced mode for RVC4).
56\* Parameters and FLOPs are obtained from the [onnx-tool](https://github.com/ThanatosShinji/onnx-tool) package.
57
58## Quantization
59
60TODO
61
62# Utilization
63
64TODO
65
66## Example
67<link to minimal working example>

Additional guidance

Some models have very specific postprocessing steps that need to be taken to get a meaningful output. We recommend you expand on those under the Utilization section so other community members can use them as well. Preferably this would be a combination of code snippets and additional comments.If you already have a working example feel free to share it as a link either through Github gist, repository, or similar. This should be a minimal working example that shows passing data into the model through the DepthAI pipeline, parsing the raw output, and optionally some basic visualization (if relevant).We already have some existing parsers which you can use for this in the depthai-nodes library. If none of them are applicable and you made a new parsing node do not hesitate to make a pull request to the repository and help with thedevelopment.Important: To make usage of your example as straightforward as possible we strongly encourage you to state the DepthaAI version (and potentially depthai-nodes version) which you used during testing. This way others can easily replicate your environment.

ON THIS PAGE

Model Card Template

Additional guidance