-
Hey!
I realize this is realistically out of scope for `tract`, but I figured I'd ask anyways. For some background, we have a bit of a weird situation with some of our ML assets at Embark - we work …
-
The current charter states in its [out of scope](https://webmachinelearning.github.io/charter/#out-of-scope) section:
>This Community Group does not attempt to mandate a specific neural network or …
-
ONNX If only works has a loading macro expansion: the condition must be known and fixed at loading time, the right branch is substituted in the type phase. This blocks Silero VAD v4 (see #1029).
* …
-
Reading the current spec it seems that NNEF supports only fixed (constant) shape sizes. Is that correctly understood or not and if so do you intend to support dynamic/variable shapes?
botev updated
5 years ago
-
First, thanks for providing this up-to-date repository !
I am trying to match the defined operations from the OpenAPI definitions to the 3GPP _functional_ services definitions. In some yaml file, t…
-
Hello!
I have some trouble with the ONNX Resize operator.
Short list:
- Does not support mode: nearest & nearest_modes like floor, ceil, round_prefer_ceil, round_prefer_floor (Fixed by #723)
- D…
-
# Step 0: Preliminaries
* cancel chunk support
# Step 1: Replace Scan by Loop
* support ONNX Loop
* simplify (?) scan code by splitting to separate ops
* state management
* scan sli…
-
Related to the _The Lottery Ticket Hypothesis_, pruning allows to discard a large amount of parameters within a network [1, 2, 3, 4] without sacrificing model accuracy (depending on the amount of cour…
-
In the last publicly available version (0.7.0) of PlaidML the Tile language was used to write operators. The latest documentation talks about a C++/Python EDSL being developed as well, however, docume…
-
I'm not too familiar with the model loading process but is it possible to use this library to load in different model formats (like h5) other than the provided .model extension?
P.S. amazing work o…