Torch Fidelity
High-fidelity performance metrics for generative models in PyTorch
About
Numerical Precision: Unlike many other reimplementations, the values produced by torch-fidelity match reference implementations up to floating point's machine precision. This allows using torch-fidelity for reporting metrics in papers instead of scattered and slow reference implementations. Read more about numerical precision
Open Source Health
- Stars
- 1,202
- Forks
- 88
- License
- Not stated
- Last commit
- 5 months ago
Related Categories
Vendor
Anton Obukhov
Research Scientist in Computer Vision and Generative AI
Quick Links
Open Source
Related Products
Deepeval
The LLM Evaluation Framework
Top category match
Aifork
Aifork is a domain name available for purchase.
Top category match
CHaiDNN
HLS based Deep Neural Network Accelerator Library for Xilinx Ultrascale+ MPSoCs
Shared categories
SoulX-FlashTalk
SoulX-FlashTalk is the first 14B model to achieve sub-second start-up latency (0.87s) while maintaining a real-time throughput of 32 FPS on an 8xH800 node.
Shared categories
Ts Pattern
The exhaustive Pattern Matching library for TypeScript, with smart type inference.
Shared categories