Issues
- 4
KeyError: 'batch_input_shape'
#1135 opened by franhervas99 - 2
- 0
User-exposed optimiser skipping
#1128 opened by bo3z - 15
PyTorch: merge layer with a constant input
#1082 opened by sei-jgwohlbier - 4
- 6
- 1
merge_template reuse_factor
#1088 opened by sei-jgwohlbier - 3
Compiling PyTorch LSTM with Hidden State Input
#1074 opened by vishal-chandra - 5
Hello, after converting GRU network to IP core using hls4ml, the output of IP core is not always 0. Here is my conversion code.
#1111 opened by yulin3262 - 1
Add support for Layer Normalization
#1109 opened by rianbrooksflynn - 2
DSP packing Vivado backend
#1096 opened by steltze - 0
Failed to synthesize QKeras CNN model: Internal stream failed dataflow checking: it must be produced and consumed exactly once.
#1105 opened by AnouarITI - 2
Does hls4ml currently support transform architectures?
#1097 opened by LmDeng0 - 0
- 1
Error when converting HGQ model to proxy
#1090 opened by AnouarITI - 0
- 10
bug in Leaky_relu instantiation
#1076 opened by AnouarITI - 1
AttributeError: module 'tensorflow.keras.layers' has no attribute 'LocallyConnected1D'
#1077 opened by DrBwts - 1
AttributeError: module 'tensorflow.keras.layers' has no attribute 'LocallyConnected1D'
#1066 opened by deleteeeee - 3
Wrong bias in rtl
#1065 opened by osccircuit - 7
FPGA Output is Zero in CNN model with 8,512 parameters.
#1048 opened by zsrabbani - 4
TypeError: 'NoneType' object is not subscriptable
#1027 opened by zsrabbani - 3
Connecting Conv1d layer with LSTM Layer.
#1052 opened by svs11 - 0
Vivado FIFO optimization overestimates first FIFO depth
#1049 opened by rfforelli - 4
Torch "View"
#1038 opened by sei-jgwohlbier - 1
Prediction output of FPGA is always ZERO!
#1026 opened by zsrabbani - 16
CNN Synthesis fail : ERROR: [XFORM 203-504] Stop unrolling loop 'Product1' (firmware/nnet_utils/nnet_dense_latency.h:37) in function 'nnet::dense_latency<ap_fixed<2, 1, (ap_q_mode)5, (ap_o_mode)3, 0>, ap_fixed<2, 1, (ap_q_mode)5, (ap_o_mode)3, 0>, config6>' because it may cause large runtime and excessive memory usage due to increase in code size. Please avoid unrolling the loop or form sub-functions for code in the loop body. ERROR: [HLS 200-70] Pre-synthesis failed.
#1013 opened by ZWhimsi - 1
Reports not found!
#1030 opened by aleenaelsageorge12 - 1
Co-simulation report not found
#1029 opened by aleenaelsageorge12 - 1
- 1
- 7
TypeError: 'NoneType' object is not subscriptable
#990 opened by zsrabbani - 0
"warning: integer constant is so large that it is unsigned" causes hls_model.compile() to fail
#1011 opened by RikPi - 4
- 8
- 2
`output_rounding_saturation_mode` pass does not work with convolutional layers
#1001 opened by qberthet - 3
Wrong prediction of C Simulation compared to QKeras?
#978 opened by lcit - 0
- 0
SR backend doesn't work with Vitis HLS
#994 opened by bo3z - 1
The hls4ml transformation successful, however, the result of inference all zeros.
#980 opened by cantonsir - 5
- 1
- 0
Move transpose based on backend from hls4ml/model/layers.py to backend-specific areas
#957 opened by jmitrevs - 0
ERROR: [XFORM 203-504] Stop unrolling loop 'Product1' (firmware/nnet_utils/nnet_dense_latency.h:37) in function 'nnet::dense_latency<ap_fixed<16, 6, (ap_q_mode)5, (ap_o_mode)3, 0>, ap_fixed<16, 6, (ap_q_mode)5, (ap_o_mode)3, 0>, config42_mult>' because it may cause large runtime and excessive memory usage due to increase in code size. Please avoid unrolling the loop or form sub-functions for code in the loop body. myproject_prj:solution1 Dec 27, 2023 6:47:26 PM
#950 opened by layson-inventor - 6
[XFORM 203-502]
#922 opened by abd0smaali - 0
Concatenation Layer Issue with PyTorch ResNet
#931 opened by clw5710 - 1
Keras Reshape Layer is Built with Error
#932 opened by MrFaith2001 - 0
Non-quantized QKeras layers break conversion
#928 opened by vloncar - 0
part7b of tutorial has no result returned back
#913 opened by jsncepu - 0
Inconsistant behaviour of `accum_t` in `io_stream` and `io_parallel` for `pooling` layers with `Vivado` backend
#912 opened by calad0i