Fig. 2
Bragg peak reconstruction. Top panels. Inference results for the identification of Bragg peak locations in an undeformed bi-crystal gold sample. From left to right, we show results for three AI models, namely: (a) PyTorch(PT) baseline model; (b) an inference optimized TensorRT(TRT) model; and (c) a model trained with the SambaNova DataScale® (SN) system. In the panels, Truth stands for the ground truth location of Bragg peaks; PT,TRT and SN represent the predictions of our baseline PyTorch,TensorRT and SambaNova models, respectively. We produced these results by directly running these models in the ThetaGPU supercomputer, and found that 95% of the predicted peak locations in the test set are within a Euclidean distance of 0.688 pixels from the actual peak locations. FAIR AI Approach. Bottom panels. AI inference results obtained by combining DLHub, funcX and the ThetaGPU supercomputer. From left to right, we show results for our three AI models: (d) PT; (e) TRT; and (f) SN, which are hosted at DLHub. funcX manages the entire workflow by invoking AI models, launching workers in ThetaGPU and doing AI inference on a test set. This workflow also includes post-processing scripts to quantify the L2 norm that provides a measure for the reliability of our AI-driven regression analysis.
