diff options
author | Patrik Gustavsson <patrik.gustavsson@arm.com> | 2021-06-28 07:41:58 +0200 |
---|---|---|
committer | Patrik Gustavsson <patrik.gustavsson@arm.com> | 2021-07-08 10:57:25 +0200 |
commit | 8f1f9aaa58175b17cd2e505bfcdb0e40c955ea72 (patch) | |
tree | 0174f8ef15007f5e220cfc4d283046451282102e /ethosu/vela/high_level_command_stream_generator.py | |
parent | 6f4955aa7097b123bbf31aae4654547bb3e3c68c (diff) | |
download | ethos-u-vela-8f1f9aaa58175b17cd2e505bfcdb0e40c955ea72.tar.gz |
MLBEDSW-4838 Added basic TOSA support.
Added basic TOSA support, enabling Vela to
read and compile a .tosa file corresponding to
CONV2D + Rescale + Clamp, and writing it to an
optimized .tflite file.
The optimized .tflite file, will in this case, hold
a commandstream where the Rescale and Clamp has been
fused into the CONV2D.
The optimized tflite file is not output from Vela.
-Added support to read .tosa file into Vela
internal structure.
- Added tosa_reader.py, tosa_mapper.py and
helper files stored under tosa/
- Support for this limited to ~10 ops
-Added reader_util.py for functions common
for TOSA and TFLite
-Added tosa_graph_optimiser.py
-Added support to fuse Rescale into convolution
-Modified handling for padding
-Added support to fuse Clamp to previous op
-Added graph_optimiser_util.py
-Moved functions common for TOSA/TFLite graph
optimization to this file.
-Renamed graph_optimiser.py to tflite_graph_optmiser.py
-Added separate tosa_supported_operators.py
-Added supported_operator_util.py
-For functions in common for TOSA/TFLite
Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com>
Change-Id: Ic3c540504ec8c5eb4771397fdc6882050ecf33ab
Diffstat (limited to 'ethosu/vela/high_level_command_stream_generator.py')
-rw-r--r-- | ethosu/vela/high_level_command_stream_generator.py | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/ethosu/vela/high_level_command_stream_generator.py b/ethosu/vela/high_level_command_stream_generator.py index 6fcf80cb..b3ea9d49 100644 --- a/ethosu/vela/high_level_command_stream_generator.py +++ b/ethosu/vela/high_level_command_stream_generator.py @@ -109,7 +109,9 @@ def generate_high_level_commands_for_sched_op(sched_op, schedule): # Create activation function if needed for op in ps.ops: if op.type.is_relu_op() or op.type in (Op.Tanh, Op.Sigmoid): - ps.primary_op.activation = create_activation_function(op.type) + ps.primary_op.activation = create_activation_function( + op.type, min=op.attrs.get("min", None), max=op.attrs.get("max", None) + ) # Generate commands for the Op that produces this Op's IFM, if applicable if cascade_info is None or cascade_info.start == sched_op.index: |