diff options
| author | Johan Alfven <johan.alfven@arm.com> | 2023-08-22 11:02:47 +0200 |
|---|---|---|
| committer | Johan Alfven <johan.alfven@arm.com> | 2023-08-22 11:02:47 +0200 |
| commit | c02eaa3e25840aee4ff909df263d4d0673227c5d (patch) | |
| tree | 4f8917f9ac22c2ebefc1f131e3d850a85386698b | |
| parent | 00a15db3e1a188b25065d095152d701f4394cdc5 (diff) | |
| download | ethos-u-vela-c02eaa3e25840aee4ff909df263d4d0673227c5d.tar.gz | |
MLBEDSW-7949: [MLCE] Remove duplicate cpu tensors
- If a npu op is followed by a convolution op than runs on the cpu,
the optimized file ends up containing a duplicated tensor called _cpu.
Functionality wise not a problem but the graph will look strange in a
graph viewer.
- This error was introduced when removing duplicate weights
tensors but the above use case was not considered in that patch.
- The fix is to make sure that only the weight and bias tensor are
modified.
Change-Id: I576f13650f1f9d3d50a421ab7100fc8b5ab62657
Signed-off-by: Johan Alfven <johan.alfven@arm.com>
| -rw-r--r-- | ethosu/vela/tflite_writer.py | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/ethosu/vela/tflite_writer.py b/ethosu/vela/tflite_writer.py index 5aa38a7..6d85567 100644 --- a/ethosu/vela/tflite_writer.py +++ b/ethosu/vela/tflite_writer.py @@ -103,10 +103,10 @@ class TFLiteSerialiser: self.align_nng_inputs_to_tflite(op) all_ops.append(op) if op.type.is_conv2d_op() or op.type.is_depthwise_conv2d_op() or op.type == Op.FullyConnected: - # Op is run on CPU, make sure original tensor are written back + # Op is run on CPU, make sure the original weight and bias tensors are written back # instead of the cloned/reshaped (see tflite_reader) for idx, inp in enumerate(op.inputs): - if inp is not None and inp.src_tensor is not None: + if inp != op.ifm and inp is not None and inp.src_tensor is not None: op.inputs[idx] = inp.src_tensor # list of tuple(Op, string, op.version); the custom code is only used for 3rd party custom operators |