4c13ae9d17d1709ed7a777ce1bb72212e8d2559d,tests/python/frontend/pytorch/test_object_detection.py,,test_detection_models,#,88

Before Change

    // with pytorch output. Some boxes might have a quite tiny difference in score
    // and the order can become different. We just measure how many valid boxes
    // there are for input image.
    pt_scores = pt_res[1].detach().numpy().tolist()
    tvm_scores = tvm_res[1].asnumpy().tolist()
    num_pt_valid_scores = num_tvm_valid_scores = 0

After Change

        with tvm.transform.PassContext(opt_level=3):
            vm_exec = relay.vm.compile(mod, target=target, params=params)

        ctx = tvm.context(target, 0)
        vm = VirtualMachine(vm_exec, ctx)

        vm.set_input("main", **{input_name: data_np})
        tvm_res = vm.run()

        // Bounding boxes
        tvm.testing.assert_allclose(
            pt_res[0].cpu().numpy(), tvm_res[0].asnumpy(), rtol=1e-5, atol=1e-5
        )
        // Scores
        tvm.testing.assert_allclose(
            pt_res[1].cpu().numpy(), tvm_res[1].asnumpy(), rtol=1e-5, atol=1e-5
        )
        // Class ids
        np.testing.assert_equal(pt_res[2].cpu().numpy(), tvm_res[2].asnumpy())

        score_threshold = 0.9
        print("Num boxes:", pt_res[0].cpu().numpy().shape[0])
        print("Num valid boxes:", np.sum(pt_res[1].cpu().numpy() >= score_threshold))

Instances