Jovan Mitrevski
Jovan Mitrevski
Updated to the latest main branch since I think it fixes the issue that caused the test failure.
For the "broken" diffs, we should look to see what the whitespace error is and fix it before merging.
We should squash the commits when we merge this.
Can you give an example that we can run that shows the problem?
I confirmed the bug in the main branch and will try to fix it. In the meantime, this works (though you should check if the alpha is the same default).
```python #!/usr/bin/env python import numpy as np import tensorflow as tf from tensorflow.keras.layers import ( Activation, Conv2D, Dense, BatchNormalization, Add, Input, GlobalAveragePooling2D, Dropout, Flatten, LeakyReLU, ) import hls4ml ### Model:...
I am slightly confused by the performance table above. Currently if io_parallel we don't have specific pointwise implementations and just the standard latency or resource convolutions are used. How much...
Also, so I understand the previous discussion, this is no longer selected as a separate implementation but is just io_parallel latency with size 1 kernel, right?
For automatic deployment, there is a pull request that will make it possible to use Vitis HLS: https://github.com/fastmachinelearning/hls4ml/pull/1134 (Generally we recommend Vitis HLS 2023.1 or later. Versions before 2022.2 produce...