You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2020/07/10 18:40:24 UTC
[GitHub] [incubator-tvm] trevor-m opened a new pull request #6038: [Frontend][TFLite] Fix fully_connected converter when batch size is not 1
trevor-m opened a new pull request #6038:
URL: https://github.com/apache/incubator-tvm/pull/6038
The fully_connected converter used the shapes from the TFLite model to reshape the data tensor. However, the TFLite model shapes do not reflect those provided by the `data_shape` parameter in `from_tflite()`. The TFLite model shape `input_tensor.tensor.ShapeAsNumpy()` will give a batch size of `1` because the TFLite model obviously doesn't know about the `data_shape` dict the user provided to the relay importer.
For this particular op, the reshape can always be set to `(-1, n_units)` without needing to calculate a batch size.
For inceptionv4, without this PR we would incorrectly compute a batch size of 1 adding this reshape from %515: `(4, 1, 1, 1536)` to %516: `(1, 1536)`. This ultimately causes the model output to become `(1, 1001)` instead of `(4, 1001)`
```
..
%515 = nn.avg_pool2d(%514, pool_size=[8, 8], padding=[0, 0, 0, 0], layout="NHWC") /* ty=Tensor[(4, 1, 1, 1536), float32] */;
%516 = reshape(%515, meta[relay.Constant][0] /* ty=Tensor[(2), int32] */ /* ty=Tensor[(2), int32] */, newshape=[1, 1536]) /* ty=Tensor[(1, 1536), float32] */;
%517 = nn.dense(%516, %v_param_299, units=None) /* ty=Tensor[(1, 1001), float32] */;
%518 = nn.bias_add(%517, %v_param_300) /* ty=Tensor[(1, 1001), float32] */;
nn.softmax(%518, axis=1) /* ty=Tensor[(1, 1001), float32] */
}
```
Btw, should the reshape op have some validation to prevent reshapes where the numbers of elements don't match? `(4, 1, 1, 1536)` -> `(1, 1536)` shouldn't be valid.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [incubator-tvm] FrozenGene merged pull request #6038: [Frontend][TFLite] Fix fully_connected converter when batch size is not 1
Posted by GitBox <gi...@apache.org>.
FrozenGene merged pull request #6038:
URL: https://github.com/apache/incubator-tvm/pull/6038
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [incubator-tvm] FrozenGene commented on pull request #6038: [Frontend][TFLite] Fix fully_connected converter when batch size is not 1
Posted by GitBox <gi...@apache.org>.
FrozenGene commented on pull request #6038:
URL: https://github.com/apache/incubator-tvm/pull/6038#issuecomment-657415618
I think we could add some check in `bool ReshapeRel` function
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [incubator-tvm] FrozenGene commented on pull request #6038: [Frontend][TFLite] Fix fully_connected converter when batch size is not 1
Posted by GitBox <gi...@apache.org>.
FrozenGene commented on pull request #6038:
URL: https://github.com/apache/incubator-tvm/pull/6038#issuecomment-657909009
@trevor-m @anijain2305 Thank you. This pr is merged now.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org