diff options
| author | eyyub.sari@epitech.eu <eyyub.sari@epitech.eu> | 2019-02-10 20:05:32 -0800 |
|---|---|---|
| committer | Facebook Github Bot <facebook-github-bot@users.noreply.github.com> | 2019-02-10 20:08:45 -0800 |
| commit | e661dc27ffbdd64c6bed1bf9a7c5a601f91e6386 (patch) | |
| tree | 841d9a9b16a4d87660ad83436169c5b6afa18d0f /caffe2 | |
| parent | 8f6ee88a1d14d2f783c65e487b5cbda3f7211980 (diff) | |
| download | pytorch-e661dc27ffbdd64c6bed1bf9a7c5a601f91e6386.tar.gz pytorch-e661dc27ffbdd64c6bed1bf9a7c5a601f91e6386.tar.bz2 pytorch-e661dc27ffbdd64c6bed1bf9a7c5a601f91e6386.zip | |
Int8GivenTensorFill Operator Schema fix typo (#16204)
Summary:
Hi,
caffe2/operators/quantized/int8_given_tensor_fill_op.cc expects the value array to be named "values" but the operator schema describe "value" (no s). I guess it is a little typo but it made me losing a bit of time before understanding why I had this error by passing "value" instead of "values":
```
[F int8_given_tensor_fill_op.h:95] Check failed: output->t.numel() == values_.numel() output size: 3 given size: 0
Aborted (core dumped)
```
Thanks,
Eyyüb Sari
Pull Request resolved: https://github.com/pytorch/pytorch/pull/16204
Differential Revision: D14020476
Pulled By: ezyang
fbshipit-source-id: a8a46bfc44ec125e7925ce4b7c79fdf99c890a50
Diffstat (limited to 'caffe2')
| -rw-r--r-- | caffe2/operators/quantized/int8_given_tensor_fill_op.cc | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/caffe2/operators/quantized/int8_given_tensor_fill_op.cc b/caffe2/operators/quantized/int8_given_tensor_fill_op.cc index 4840b4880b..dc108d1f3f 100644 --- a/caffe2/operators/quantized/int8_given_tensor_fill_op.cc +++ b/caffe2/operators/quantized/int8_given_tensor_fill_op.cc @@ -5,7 +5,7 @@ namespace caffe2 { OPERATOR_SCHEMA(Int8GivenTensorFill) .NumInputs(0) .NumOutputs(1) - .Arg("value", "Input array of type char(byte)") + .Arg("values", "Input array of type char(byte)") .Arg("shape", "Input tensor shape") .Arg("Y_scale", "Output tensor quantization scale") .Arg("Y_zero_point", "Output tensor quantization offset") @@ -17,7 +17,7 @@ OPERATOR_SCHEMA(Int8GivenTensorFill) OPERATOR_SCHEMA(Int8GivenIntTensorFill) .NumInputs(0) .NumOutputs(1) - .Arg("value", "Input array of type int32") + .Arg("values", "Input array of type int32") .Arg("shape", "Input tensor shape") .Arg("Y_scale", "Output tensor quantization scale") .Arg("Y_zero_point", "Output tensor quantization offset") |