Closed Sudharsan-V closed 7 months ago
The Benchmarking of GS MNIST model is completed. Data-set: MNIST Metric: Accuracy
Corresponding: commit
PR for MNIST GS demo benchmarking , model is tested with 1000 datapoints extracted from the MNIST handwritten digits dataset , the accuracy is listed below:
Metric: Accuracy Accuracy: 62.2
PR - #4502
PR is approved. CI is pending
PR is merged. Hence closing the ticket.
GS e2e Demo
test uses batched real inputs and produces batched outputs
this test is looped (takes several batches of inputs, produces several batches of outputs)
test evaluates results of TT model against validation data in selected data set
test is documented
how to run test (commands to execute) what does the model do (high-level explanation in a couple of sentences) description of what is input and what is output this demo should load inputs and expected outputs from a data set on Weka (TBD which one)