Before it for Keras LSTM it throws IndexError: list index out of range.
I know, that there is a low chance that it will be run without the HLS model, but still would be good to set properly.
Type of change
[X] Bug fix (non-breaking change that fixes an issue)
Tests
import hls4ml
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Conv1D, Activation, MaxPooling1D, LSTM, Dense, Input
input = Input(shape = (600, 10 ), name = 'input')
x = Conv1D(
filters = 4,
kernel_size = 3,
strides = 1,
padding = 'valid',
name = 'conv_1',
)(input)
x = Activation(
'relu',
name = 'conv_act_1'
)(x)
x = MaxPooling1D(
pool_size = 3,
padding = 'valid',
name = 'pool_1'
)(x)
x = LSTM(16, name = 'lstm')(x)
x = Dense(10, name = 'dense')(x)
model = Model(inputs = input, outputs = x)
hls4ml.model.profiling.numerical(model = model, hls_model = None)
Description
Before it for Keras LSTM it throws IndexError: list index out of range. I know, that there is a low chance that it will be run without the HLS model, but still would be good to set properly.
Type of change
Tests
Checklist
pre-commit
on the files I edited or added.