Nicolo's update

Small reusable blocks:

• The idea is to start by testing a function that can be reused (by using different input/output shapes) disregarding the functionality (Noemi is working with Dense - simpler than Conv)
• Core idea: fix the maximum size of input and output shape and create the "core". Then pass the actual input and output shapes as parameters (<= than the max ones) and perform the computation.
  • Note: different cores could be instantiated, with different maximum size of input/output shapes

FloatQuant

• First sample version implemented (QONNX meeting in 2 days, we will give an update on that)
• Spotted a couple of bugs in Brevitas FloatQuant, I am now discussing with the guys if I should open a PR or some issues on GH
• Waiting for feedbacks from Yaman

Edge SpAIce new models

• Tested and they works, the performance are not degradated as it happened before
  • There are mismatches between QONNX and hls4ml after pointwise conv. To try to understand why this happens I recreated a simple model composed by only the first part of the UNet model
• I opened a PR to automatically infer the datatype of a constant, namely param_t of LeakyReLU
• Preprocessing: I modified the input datatype to 4bits, as it is the first Quant node in QONNX. This remove the initial linear function that creates issues

---------------------

Stelios
    - Opened PR on II fix for zero-padding and pooling
    - Opened PR on Vitis Accelerator
    - No progress on DSP packing
    - Working on another FIFO matching
    - Talked with PixESL people
        - Working on getting the datasets
        - There is another person working on clustering on SoCs
        - New person from their side who is familiar with ML, will talk to him today

General
- Applied ML days

- Meeting with NTUA Wednesday