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

Before Change

    download(img_url, img)

    input_shape = (1, 3, in_size, in_size)
    target = "llvm"
    input_name = "input0"
    shape_list = [(input_name, input_shape)]
    score_threshold = 0.9

    scripted_model = generate_jit_model(1)
    mod, params = relay.frontend.from_pytorch(scripted_model, shape_list)

    with tvm.transform.PassContext(opt_level=3, disabled_pass=["FoldScaleAxis"]):
        vm_exec = relay.vm.compile(mod, target=target, params=params)

    ctx = tvm.cpu()
    vm = VirtualMachine(vm_exec, ctx)
    data = process_image(img)
    pt_res = scripted_model(data)
    data = data.detach().numpy()
    vm.set_input("main", **{input_name: data})
    tvm_res = vm.run()

    // Note: due to accumulated numerical error, we can"t directly compare results
    // 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

    for score in pt_scores:
        if score >= score_threshold:

After Change

        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
        )

Instances