perch_v2_no_dft: Molecular Data for Chemistry Modeling

An ONNX model file named 'perch_v2_no_dft.onnx' is hosted on Kaggle. The dataset's specific content, such as the number of molecular structures or features, is not detailed in the available metadata. Its title suggests a connection to computational chemistry, likely involving molecular property prediction without density functional theory (DFT) calculations.

Use Cases

• Benchmarking machine learning models for molecular property prediction (inferred from domain, verify after download)
• Developing surrogate models to accelerate chemical simulations (inferred from domain, verify after download)
• Fine-tuning pre-trained models on specific chemical datasets (inferred from domain, verify after download)

Strengths

• Published on Kaggle, a platform for sharing data and models.
• The ONNX format suggests the model is portable across different frameworks.

Limitations

• Metadata is minimal; actual content requires verification after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

Kaggle