Command Palette
Search for a command to run...
Knowledge Distillation Student Model Accuracy Student Acc
Student Model Accuracy (Knowledge Distillation) is an important evaluation metric in model optimization and knowledge distillation tasks. It represents the prediction accuracy of a lightweight student model on the test set, and is used to measure the student model's actual task performance and the effectiveness of knowledge transfer after learning knowledge from the teacher model. This metric is usually reported as a percentage or a decimal between 0 and 1, with higher values being better, and is widely used in related benchmarks and papers (in practice, evaluation often also considers teacher model accuracy, non-distilled baselines, and model size/inference efficiency for comprehensive reference).
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.