onnx-light — shape inference coverage

Per-intermediate shape inference correctness on every backend test tagged inference (collected via onnx_light.backend.test.case.collect_test_case, same set exercised by unittests/backend/test_backend_with_shape_inference.py). Each case has its output and intermediate value_info shapes stripped, then re-inferred with four runtimes: onnx-light, onnx_light.onnx_optim.shape_inference, onnx.shape_inference and onnx-shape-inference. The table reports the percentage of intermediates whose elem_type and shape were correctly recovered. Click a row to see the per-intermediate detail for each runtime; the graph input shapes fed to the runtimes are listed first for context.

⚠ The results displayed on this page are indicative and experimental.