index
:
specification.git
main
v0.23
v0.30
v0.40
v0.50
v0.60
v0.70
v0.80
v0.90
v1.0
[no description]
about
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
chapters
/
tensor_ops.adoc
Age
Commit message (
Expand
)
Author
2021-11-12
Use in_out_t when a type is used for input and output
Eric Kunze
2021-10-28
Readability fixes for pseudocode
Eric Kunze
2021-10-28
Remove zp subtraction from tensor_read pseudocode
Eric Kunze
2021-10-08
Force output shape to be correct for pooling operations
Matthew Haddon
2021-10-04
Move quantization parameters into argument tables
Eric Kunze
2021-09-29
Allow PAD operator to pad with non-zero
Eric Kunze
2021-09-24
Don't allow pooling ops with excessive padding
Eric Kunze
2021-09-16
Clarify range limitations for tensors
Eric Kunze
2021-09-03
MAX_POOL2D: Fix padding behaviour
Dominic Symes
2021-08-23
Fix pooling argument tables
Eric Kunze
2021-07-13
Add definition of TOSA compliance
Dominic Symes
2021-06-24
Replace assert with REQUIRE()
Eric Kunze
2021-03-16
Note limits on axis parameter
Eric Kunze
2021-03-11
Make pseudocode block tags consistent
Eric Kunze
2021-03-11
Adjust pseudocode types to account for zero point
Eric Kunze
2021-03-08
Consistency cleanup
Eric Kunze
2021-02-09
Add batch dimension to MatMul
Dominic Symes
2021-01-25
Remove aint8 type
Eric Kunze
2020-11-29
Fix minor spec issues
Eric Kunze
2020-11-05
Fix output argument type for convolutions
Eric Kunze
2020-11-03
Change weights to input for training profile
Eric Kunze
2020-10-22
Make rank() consistent across files
Dominic Symes
2020-10-01
TOSA spec 0.20.0, initial public version
v0.20.0
Eric Kunze