search

Xilinx / BNN-PYNQ

Quantized Neural Networks (QNNs) on PYNQ
https://xilinx.github.io/finn/
BSD 3-Clause "New" or "Revised" License
671 stars 306 forks source link

changing BNN weight #126

Closed mtenaw1 closed 4 years ago

mtenaw1 commented 4 years ago

we spoke today and you told me to uncomment line 106, 130 and 130 on cifar10-gen-weights-W1A1.py. After i did that and try to runt the python code, i got this problem.

~/Desktop/BNN-PYNQ/bnn/src/training$ python cifar10-gen-weights-W1A1.py Using peCount = 16 simdCount = 3 for engine 0 Extracting conv-BN complex, OFM=64 IFM=3 k=3 Layer 0: 64 x 27 WMem = 36 TMem = 4 IPrecision = 1.7 WPrecision = 1.0 APrecision = 1.0 Traceback (most recent call last): File "cifar10-gen-weights-W1A1.py", line 110, in m.createBinFiles(targetDirBin, str(convl)) File "/home/afrl/Desktop/BNN-PYNQ/bnn/src/training/finnthesizer.py", line 695, in createBinFiles self.wmem2bin(self.weightMem[pe], targetDir+"/"+prefix+"-"+str(pe)+"-weights.bin", self.WPrecision==1) File "/home/afrl/Desktop/BNN-PYNQ/bnn/src/training/finnthesizer.py", line 618, in wmem2bin import bitstring
ImportError: No module named bitstring

giuliogamba commented 4 years ago

You need to install the bitstring package. https://pypi.org/project/bitstring/