Method and device for testing operator precision in neural network and computer readable storage medium
A neural network and operator technology, applied in the field of artificial intelligence, can solve problems such as no testing methods or devices, and achieve the effect of flexible evaluation methods
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0023] The technical solution disclosed in the present disclosure provides a method, device and computer-readable storage medium for testing the accuracy of an operator in a neural network. Specifically, the present disclosure proposes to use the difference between the benchmark result obtained for the operator to be tested and the test result to evaluate the accuracy level of the operator, so as to reflect the fault tolerance of the operator to a certain extent. In the context of this disclosure, the evaluation of operator accuracy mentioned here may not only include the evaluation of the accuracy brought by the operation of the operator itself on different hardware platforms, but also include the evaluation of the accuracy of the operator due to the conversion of data types. The precision brought by the same or different hardware platforms, or the precision brought by the evaluation operator based on the combination of the hardware platform and data type conversion.
[0024]...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


