AttributeError during ConvertLayout to NHWC

[leandron]

When using tvm.relay.transform.ConvertLayout (in the context of #6302), I'm getting some errors that are not really clear on how they are related to the convert process.

It seems ConvertLayout it is looking for shape (this check was introduced in #5284), when trying to find depthwise convolutions, but it doesn't seem to be the case that shape is there for some imported models, and might need some fixing.
https://github.com/apache/incubator-tvm/blob/4b48d89c79a72f7799606e845bdb1ed938baa115/python/tvm/relay/op/nn/_nn.py#L158-L164

This is the error I see, when trying to run ConvertLayout on an ONNX model:

AttributeError: <class 'tvm.relay.expr.TupleGetItem'> has no attribute shape

To reproduce the issue, you can run the script below:

1. Download resnet50:

wget https://github.com/onnx/models/raw/master/vision/classification/resnet/model/resnet50-v2-7.onnx

2. Run the ConvertLayout following the script below:

import onnx
import tvm
from tvm import relay

# boilerplate to load the ONNX model
model = onnx.load("resnet50-v2-7.onnx")
name = model.graph.input[0].name
proto_shape = model.graph.input[0].type.tensor_type.shape.dim
shape = [d.dim_value for d in proto_shape]
shape_dict = {name: shape}
mod, params = relay.frontend.from_onnx(model, shape_dict)

# converting layout
desired_layouts = {'nn.conv2d': ['NHWC', 'default']}
seq = tvm.transform.Sequential([relay.transform.RemoveUnusedFunctions(),
                                relay.transform.ConvertLayout(desired_layouts)])

with tvm.transform.PassContext(opt_level=3):
    mod = seq(mod)

with relay.build_config(opt_level=3):
     graph, lib, params = relay.build(mod, "llvm", params=params)

PS: It also happens if I get a NHWC TFlite model and try to force it into an NHWC convertion, but that is a negative test, that is why I didn't add it here.

cc @comaniac @jwfromm

[lhutton1]

I think this is happening because the shape of data is accessed by data.shape, at some point something in TVM changed meaning shape needs to be accessed by data.checked_type.shape. It looks like the convert layout tests didn't pick this up.

[leandron]

If we agree this is a legitimate issue, I found two places that need fixing:

https://github.com/apache/incubator-tvm/blob/4b48d89c79a72f7799606e845bdb1ed938baa115/python/tvm/relay/op/nn/_nn.py#L160

https://github.com/apache/incubator-tvm/blob/4b48d89c79a72f7799606e845bdb1ed938baa115/python/tvm/relay/qnn/op/layout_conversions.py#L65

[zhiics]

cc @anijain2305

[anijain2305]

Thanks @leandron for raising the issue. Your fixes look good to me.

[leandron]

Just to mention, I checked PR #6419 and it completely fixes this issue here, so we can close it once that PR is merged.

[zhiics]

Thanks @leandron. This can be closed now.