TorchMetrics
lightning.ai
- Free plan
- Linux
7.4 Club score Visit lightning.ai
Plans
Every plan and priceTorchMetrics
Free
Free plan
What the maker publishes
- Batch accumulation
- Metrics can accumulate results across batches and compute an aggregate value. source
- Bayesian analysis
- No source
- Community support
- The project repository directs users with questions to its Discord community. source
- Compatibility limit
- The documentation says TorchMetrics supports the latest two major PyTorch Lightning versions and recommends keeping both frameworks up to date. source
- Custom metrics
- Users can create custom metrics by subclassing Metric and implementing update() and compute(). source
- Distributed training
- Metrics support distributed training and synchronize state across devices. source
- Distributed training
- Module metrics support automatic accumulation across batches and synchronization across devices for distributed training. source
- Free plan
- Yes source
- Installation
- The documentation lists installation with pip install torchmetrics or conda install -c conda-forge torchmetrics. source
- Installation
- The project documents installation with pip, conda, uv, or directly from its source repository. source
- Interfaces
- TorchMetrics provides module-based metrics and functional metrics that take tensors as input and return metric values as tensors. source
- License
- The project repository states that TorchMetrics is licensed under Apache 2.0. source
- Lightning integration
- When used with PyTorch Lightning, metrics can be logged with self.log and are automatically placed on the correct device when properly defined inside a LightningModule. source
- Metric collections
- MetricCollection wraps multiple metrics in one callable metric class. source
- Metric coverage
- The project lists more than 100 metrics across audio, classification, detection, information retrieval, image, multimodal, nominal, regression, segmentation, and text domains. source
- Optional dependencies
- Specialized audio, image, and text metrics may require extra dependencies, which can be installed with package extras. source
- Plotting
- Modular metrics provide a plot method, and the plotting interface requires matplotlib. source
- Plotting
- Nearly all modular metrics support plotting through the plot method when the visualization dependencies are installed. source
- Purpose
- TorchMetrics is a collection of more than 100 PyTorch metrics implementations with an API for creating custom metrics. source
- PyTorch integration
- TorchMetrics can be used directly with PyTorch models independently of PyTorch Lightning. source
- PyTorch Lightning integration
- When metrics are properly defined inside a LightningModule, Lightning can place them on the module’s device and log them with self.log or self.log_dict. source
- Regression models
- No source
- Scripting support
- Yes source
- Standardized interface
- Its standardized interface is intended to improve reproducibility and reduce boilerplate. source
Checked against the maker's pages on 11 Oct 2026.