Abhishek-Thakur
The video showcases the process of training a state-of-the-art image classification model without any coding using Hugging Face's AutoTrain Advanced. To do so, users need to duplicate the AutoTrain Advanced space, add their zip file-formatted dataset, select the number of models to tune, and choose between Auto Train or a model from the Hugging Face Hub. The presenter illustrates the process by uploading a flower classification dataset, which is automatically divided into training and validation sets. The free tier of AutoTrain allows users to train models up to 1,500 images, after which there is a cost. Once trained, the model is stored in the user's private repository on the Hugging Face Hub and tested using the hosted inference API. The video concludes with a request to like, subscribe, and share the content.
In this section of the video, the presenter demonstrates how to use Hugging Face's AutoTrain Advanced to train a state-of-the-art image classification model without writing any code. After duplicating the AutoTrain Advanced space, the user needs to add their data set in a zip file format, select the number of models they want to tune, and choose between Auto Train or a model from the Hugging Face Hub. Users can also add a job and select which jobs they want to train. AutoTrain divides the data into training and validation sets automatically. The presenter then demonstrates how to upload a dataset for flower classification and shows folders of class names inside the training set.
In this section, the presenter demonstrates how to create a compressed folder for image classification models, and then uploads the training and validation data to the AutoTrain project. The presenter explains that AutoTrain offers a free tier of service that allows users to train a model for up to 1,500 images, beyond which there is a cost. Once the training is complete, the model is stored in the user's own repository on Hugging Face Hub, and it is private. The model can be tested using the hosted inference API in the model's page.
In this section, the presenter demonstrates the use of the AutoTrain tool to train an image classification model and test it with a sunflower image. The model files are owned by the user, giving them the ability to deploy the model using Hugging Face API, inference endpoints like Sagemaker or Spaces, or use it directly in Transformers. The video concludes with a call for viewers to like, subscribe, and share the video.
No videos found.
No related videos found.
No music found.