Strona główna Odkrywaj Pomoc
Zaloguj się
4ycp
/
altera_devel
Obserwuj 5
Polub 0
Forkuj 0
Pliki Problemy 0 Oczekujące zmiany 0 Wiki
Drzewo: 688339f1fb
Gałęzie Tagi
altera_devel
/
scripts
/
neuron_net_test.py

neuron_net_test.py 2.0 KB
Historia Czysty

123456789101112131415161718192021222324252627282930313233343536373839404142434445 
  1. import numpy as np
    2. 

  2. from matplotlib import pyplot as plt
    3. 

  3. from fpu_test_gen import reverse_endian, dtype_size
    4. 

  4. 

  5. WEIGTHS = [
    6. 

  6.     [
    7. 

  7.         [0.7095146, -0.41895103, -0.08075078, -0.5218736],
    8. 

  8.         [-0.4351325, 1.0214638, 0.14494987, -0.78134096],
    9. 

  9.         [0.38553882, -1.0607314, 0.01327306, -0.28972188],
    10. 

  10.         [0.84955347, 0.32464203, 0.8879888, 0.00756884],
    11. 

  11.         [-0.8693629, 0.8418823, 0.60206324, -0.78290594],
    12. 

  12.         [0.1586302, 0.01737848, 0.75329006, -0.57819647],
    13. 

  13.         [-0.16126093, 0.5317601, 0.34316933, -0.7074082],
    14. 

  14.         [0.09219088, -0.624525, -0.61903083, -0.87057704]
    15. 

  15.     ],
    16. 

  16.     [[0.36770403, -0.78046024, 0.3979908, 0.5494289, -0.13859335, 0.40053025, 0.08249452, -0.32528356],
    17. 

  17.      [-0.17659009, 0.13901198, -0.45248222, -0.7894139, -0.81092286, -0.521815, 0.30632392, -0.3143816],
    18. 

  18.      [-0.04314173, 0.14361085, 0.6259473, 0.3571782, -0.38011226, 0.01378736, 0.05794358, 0.09667788],
    19. 

  19.      [-0.46864474, 0.36618456, -0.45595396, -0.39789405, 0.73964316, -0.30294785, 0.2482118, -0.2127953],
    20. 

  20.      [-0.37941265, 0.45330787, -0.12066315, 0.5636705, 0.68990386, 0.6543718, 0.86367106, -0.5707757],
    21. 

  21.      [-0.78606385, 0.24032554, -0.4472755, -0.24661142, -0.2698564, -0.8365823, -0.13674814, -0.39799848],
    22. 

  22.      [0.11138931, 0.48950365, 0.12998834, 0.4947537, 0.516593, 0.82281274, 0.04789656, 0.30206403],
    23. 

  23.      [0.23097174, 0.30290592, -0.596446, -0.40108407, 0.12246455, -0.47260976, -0.55030185, 0.44481543]
    24. 

  24.      ]
    25. 

  25.     [
    26. 

  26.         [0.5724262, 0.5853241, 0.3748752, -0.892384, -1.0270239, 0.2170913, -0.07271451, 0.14661156],
    27. 

  27.         [0.30391088, -0.92324615, 0.8088594, -1.0522624, 0.07374455, -0.550893, 0.8194236, -0.62796086]
    28. 

  28.     ]
    29. 

  29. ]
    30. 

  30. BIAS = [
    31. 

  31.     # L1
    32. 

  32.     [0.01425434, -0.06219335, -0.0201127, -0.04791382, -0.04360008, -0.05311861, -0.01731363, -0.00014839],
    33. 

  33.     # L2
    34. 

  34.     [0.03480967, 0.06208326, -0.01576317, -0.00037753, -0.03940378, 0.05157978, -0.02775403, 0.04540931],
    35. 

  35.     # L3
    36. 

  36.     [0.03787775, -0.03655371],
    37. 

  37. ]
    38. 

  38. 

  39. 

  40. def generate_nn_values(dtype=np.float32):
    41. 

  41.     dsize = dtype_size(dtype)
    42. 

  42. 

  43. 

  44. if __name__ == '__main__':
    45. 

  45.     generate_nn_values()
    46.