Tensor Regression 📉

The task of TensorRegression involves predicting continuous values within the entire tensor system.

📌 Inputs:

• SampleTensor [input]:
  • A tensor ranging from 1D to 5D.

• SampleTensor [target]: (optional)
  • A 1D tensor representing continuous numerical values.

• SampleTensor [extra]: (optional)
  • Additional tensors that may assist in exploratory data analysis or the training process.

🛠️ Use Cases:

• Temperature Estimation: Predicting the average temperature of a region based on its satellite imagery.
• Soil Moisture Assessment: Estimating moisture levels in agricultural fields to aid in irrigation planning and crop management.
• Radiation Monitoring: Assessing radiation levels in specific areas, crucial after incidents like forest fires or volcanic eruptions.

🔍 Example:

import mlstac

name = "https://huggingface.co/datasets/mlstac/tensor_classification_demo.json"
dataset = mlstac.dataset(name, streaming=True, framework="torch")
print(next(iter(dataset)))

# Output example:
# {'input': tensor([[[[...]]]]), 'target': tensor([0.18, 0.28, 0.58])}