fPecc

Support for non-zero padding

5

Hi all! I was interested in knowing if you are planning on supporting non-zero padding for the LoopConv state machine. **Use case** TFLite models quantize the input of a layer...

Is it possible to apply scale and offset to output?

1

I need to apply an offset and then scaling to the output of a matrix computation. Is it possible to do this? I know we can use the "acc_scale" parameter...

Added macro generation in MLF export

3

For description see this [forum topic](https://discuss.tvm.apache.org/t/exporting-generated-functions-input-and-output-sizes-in-the-model-library-format/13532). Tagged reviewers: @areusch (don't know who else can review microTVM-related code)

get_access_token is no longer being called in the developer tools tab in Chrome

2

I was trying to get the correct API to get the access token, but was unable to find the get_access_token API. Did spotify changed (again) how this access token is...

I was looking at the generated asm for the standard riscv_arithmetic_basic_test test using pyflow as simulator, and I was not able to find the handshake that says if the test...

Generating SPLIT and CONCAT layers

2

Hi, I am trying to generate a model with SPLIT and CONCAT layers, and I see that both functions are in the code but are not implemented. https://github.com/AlexMontgomerie/fpgaconvnet-hls/blob/dd28baa781df6e6dfebca3314305da4599816d83/fpgaconvnet/hls/generate/partition.py#L102 https://github.com/AlexMontgomerie/fpgaconvnet-hls/blob/dd28baa781df6e6dfebca3314305da4599816d83/fpgaconvnet/hls/generate/partition.py#L106) This...

Wrong 3D bounding boxes in release 2

2

I just found a couple of 3D bounding boxes that seem to be wrong in the dataset (or maybe it is just a bug in the visualization script). I am...