No nodes produced in 'StreamingDataflowPartition' #541
Unanswered
caoimhelynch
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I am following the cnv_end2end_example in FINN, to deploy my own CNV model on an FPGA. Section 3 requires the nodes to be stored in a list 'StreamingDataflowPartition' on the line
'sdp_node = parent_model.get_nodes_by_op_type("StreamingDataflowPartition")[0].
The function get_nodes_by_op_type, produces a list from
'return list(filter(lambda x: x.op_type == op_type, self.graph.node))'
When I print print(lambda x: x.op_type == op_type, self.graph.node), I get out input:
"TopK_0_param0"
output: "TopK_0_out0"
output: "global_out"
name: "TopK_0"
op_type: "TopK"
attribute {
name: "axis"
i: -1
type: INT
}
attribute {
name: "largest"
i: 1
type: INT
}
attribute {
name: "sorted"
i: 1
type: INT
}
])
suggesting that there is node data being prodcued. However, once filtered and put into a list there is nothing in the list. Is this correct behavior? I am getting the error IndexError: list index out of range, and would appreciate any advice on where my issue lies here.
Apologies if this is an amateur question, I am relatively new to FINN
Thanks
Beta Was this translation helpful? Give feedback.
All reactions