MLBEDSW-7316: Fix crash for networks with resource variables
- The problem was that networks with resource variables have
not been thought of. The major problem was the graph traversal
where these ops were not visited resulting in an empty subgraph
that resulted in the crash.
- Fixed the problem by attaching virtual tensors to the ops simulating
subgraph output. These tensors are only used to get the graph
traversal to work.
- Fixed serializing of attribute container and shared_name
- Fixed subgraph index for operator CallOnce
- All resource variable ops are pushed to the CPU
Change-Id: I815f9c81baf7a3fbb686e895980b462f58208b6e
Signed-off-by: Johan Alfven <johan.alfven@arm.com>
diff --git a/ethosu/vela/nn_graph.py b/ethosu/vela/nn_graph.py
index 846632d..a43aac2 100644
--- a/ethosu/vela/nn_graph.py
+++ b/ethosu/vela/nn_graph.py
@@ -149,7 +149,11 @@
def __init__(self, name="<unnamed>", placement=PassPlacement.Cpu):
self.output_tensors = []
self.input_tensors = []
- self.original_inputs = [] # Preserve the original input order
+ # Preserve the original input order
+ self.original_inputs = []
+ # Attach virtual outputs to resource variables op
+ # in order to be able to traverse the graph correctly
+ self.virtual_outputs = []
self.passes = []
self.cascaded_passes = []
self.name = name