approach/setting to control search space of a specific attribute about nnsmith HOT 6 CLOSED

For example, any approach to control kernel_size of Conv2d to be in range [1, 15]?

One ad-hoc way would be to add something like cons.append(nnsmith_le(kernel_h_size, 15)) around here

from nnsmith.

Also, you might find the gist helpful: https://colab.research.google.com/drive/13LNQBvfpPFiaHWKnac6hxzvJY4LUAWWQ?usp=sharing

from nnsmith.

@jakc4103 You can try https://github.com/ise-uiuc/nnsmith/blob/main/doc/cli.md#add-extra-constraints with the latest nnsmith:

pip install "git+https://github.com/ise-uiuc/nnsmith@main#egg=nnsmith[torch,onnx]" --upgrade

Tks, this works.

from nnsmith.

Recall that conv2d only accepts 4-dimension inputs. Because the graph generation is randomized in a way to start with a placeholder that has a random rank, as a result, it must be lucky enough to start with 4 to be able to generate conv2d.

This should be fixed by adding an extra argument for configuring the rank (length of its shape dimensions) of the starter placeholder (WIP).

For adding extra constraints, because we don't want to bother users by editing the source code, there is a way to systematically patch constraints at user level with the patch_requires decorator. See the TensorRT example:

Probably something like:

@patch_requires(${THE_FACTORY_TYPE}$.system_name, "core.Pool2d")
def RulePool2d(self: AbsOpBase, _: List[AbsTensor]) -> List[Union[z3.BoolRef, bool]]:
    return [self.kernel_h_size <= 15, self.kernel_w_size <= 15]

Meanwhile for some good randomness of shapes, try to use other method="symbolic-cinit" in model_gen:

gen = model_gen(
    ...
    method: str = "symbolic-cinit", # or "concolic"
    ...
):

My apologies for the incomplete documentation and will be improving the doc soon (prob. next mon). For the rank issue there will be a patch soon and I will offer a colab example later today.

Meanwhile, for now please try to use the latest version with:

pip install "git+https://github.com/ise-uiuc/nnsmith@main#egg=nnsmith[torch,onnx]" --upgrade

This will provide a lot more features and possibly a better experience (in debugging etc.). Thanks!

from nnsmith.

@jakc4103 You can try https://github.com/ise-uiuc/nnsmith/blob/main/doc/cli.md#add-extra-constraints with the latest nnsmith:

pip install "git+https://github.com/ise-uiuc/nnsmith@main#egg=nnsmith[torch,onnx]" --upgrade

from nnsmith.

Feel free to reopen if you still encounter any issues on this.

from nnsmith.