Problem during CNN synthesis

[MagiPrince]

Prerequisites

Please make sure to check off these prerequisites before submitting a bug report.

• [x ] Test that the bug appears on the current version of the master branch. Make sure to include the commit hash of the commit you checked out.
• [ x] Check that the issue hasn't already been reported, by checking the currently open issues.
• [ x] If there are steps to reproduce the problem, make sure to write them down below.
• If relevant, please include the hls4ml project files, which were created directly before and/or after the bug.

Quick summary

Hi everyone,

I'm trying to build my CNN model quantized, but when I set the filters to 32 for some QConv2d layers, the Concatenation function returns an error and the pre-synthesis failed.

I figure out that it was the Concatenation function that was triggering the error, as I try to read and write the same variable "concatenated_outputs ". Is there an easy way to fix that inside the loop, or should I unroll my loop in my code ?

Details

My model :

input_ = Input(shape=(64, 64, 3))

x = Flatten()(input_)

output_1 = QDense(2, kernel_quantizer= quantized_bits(16, 0, alpha=1),
                    bias_quantizer=quantized_bits(16, 0, alpha=1),
                    kernel_initializer='lecun_uniform', use_bias=True)(x)
concatenated_outputs = QActivation(quantized_relu(16, 6))(output_1)
for _ in range(5):
    output_tmp = QDense(2, kernel_quantizer= quantized_bits(16, 0, alpha=1),
                    bias_quantizer=quantized_bits(16, 0, alpha=1),
                    kernel_initializer='lecun_uniform', use_bias=True)(x)
    output = QActivation(quantized_relu(16, 6))(output_tmp)
    concatenated_outputs = Concatenate(axis=-1)([concatenated_outputs, output])

reshaped_outputs = Reshape((5, 2))(concatenated_outputs)

model = Model(inputs=input_, outputs=reshaped_outputs)

My hls4ml script :

config = hls4ml.utils.config_from_keras_model(model, granularity="name")

config['Model']['Precision'] = 'ap_fixed<16,6>'
config['Model']['ReuseFactor'] = 4000
config['Model']['Strategy'] = 'Resource'

cfg = hls4ml.converters.create_config(backend='Vitis')
cfg['IOType'] = 'io_stream'
cfg['HLSConfig'] = config
cfg['KerasModel'] = model
cfg['OutputDir'] = 'model_1/'
cfg['Part'] = 'xc7z030sbv485-3'

hls_model = hls4ml.converters.keras_to_hls(cfg)

hls_model.compile()

hls_model.build(csim=False, synth=True)

Error returned :

ERROR: [HLS 214-256] in function 'myproject(hls::stream<nnet::array<ap_fixed<16, 6, (ap_q_mode)5, (ap_o_mode)3, 0>, 3u>, 0>&, hls::stream<nnet::array<ap_fixed<16, 6, (ap_q_mode)5, (ap_o_mode)3, 0>, 2u>, 0>&)': Unsupported aggregate pragma/directive on variable 'layer80_cpy1' as the bit-width after aggregation (8192) is larger than 4096 (firmware/myproject.cpp:374:28)
ERROR: [HLS 214-256] in function 'myproject(hls::stream<nnet::array<ap_fixed<16, 6, (ap_q_mode)5, (ap_o_mode)3, 0>, 3u>, 0>&, hls::stream<nnet::array<ap_fixed<16, 6, (ap_q_mode)5, (ap_o_mode)3, 0>, 2u>, 0>&)': Unsupported aggregate pragma/directive on variable 'layer80_cpy2' as the bit-width after aggregation (8192) is larger than 4096 (firmware/myproject.cpp:376:25)

Steps to Reproduce

Add what needs to be done to reproduce the bug. Add commented code examples and make sure to include the original model files / code, and the commit hash you are working on.

1. Use the last hls4ml version and Vitis HLS 2023.1
2. Run the hls script

Expected behavior

Synthetize the model

Actual behavior

Raises an error