This hair matting / hair segmentation deep neural network is a binary segmentation network. Input facial images will be categorized into two distinguished areas: one containing hair (excluding facial hair) and the other containing no hair. The network is based on a similar architecture as the facial feature segmentation network. However, we use a special dataset that includes examples image from people facing away from the camera lens. This allows the model to cover the full 360 degrees angle camera range
You can deploy the model in any way you like on a server, public or private cloud, directly in your application or an edge device. It is your choice no constraints, you do not pay any transaction for using the model from Mut1ny
Deliverable in these supported neural network formats*:
*In your order please use the additional field to indicate which neural network format you would prefer
What is included in the hair matting deep neural network?
- The model in the network framework format of your choice (see above)
- For ONNX format only:
- an inference script in Python using ONNXRuntime our recommended ONNX inference framework
- C# code for using our Model using ONNXRuntime
- C++ code for using our Model using ONNXRuntime
- A deployment script for using our Model in combination with AzureMachineLearning
- For PyTorch only:
- For mxnet only
Why buy a deep neural network model? When you can build and train one yourself? Or get one free from the internet?
- Training a segmentation model from scratch using a large enough dataset takes between 2-3 days even with a high-end equipped GPU. This translates to € 80-150,- public cloud instance spending costs alone.
- No need for you to spend development time instead you can fully concentrate on your actual product feature.
- Acquiring a large enough annotated dataset can take many man-months.
- To our knowledge there are no public hair segmentation models available that cover a similar range in gender,ethnicity,age & pose. Those that do exist have most likely a very restrictive licensing scheme.
Why go for a subscription instead of single one-off purchase?
- Subscription allows you take advantage of Mut1ny’s future neural network model improvements. We improve our neural network models on a permanent basis adopting to latest research developments. This mean you benefit from our research and therefore will get better models over time.
- Subscription allows you take advantage of Mut1ny’s constantly growing training set. We constantly enlarge our training set with new data to cover a wider variety. Also if you are subscription user and you encounter cases that do not produce a result to our satisfactions you can send them to us. We’ll be including those in our training set.
There are no reviews yet.