import strengthen_functions
parser = argparse.ArgumentParser()
parser.add_argument('-n', action="store", dest="number")
parser.add_argument('-i',
action="store",
dest="iterations",
default=80000,
help="default: 30000")
args = parser.parse_args()
number = int(args.number)
iterations = int(args.iterations)
pf = strengthen_functions.PF81
nn = NeuralNetwork(strength_function=pf,
image_scale=8,
transmission_history_len=10**4)
'''
train_imgs, _ = skl.load_data()
train_imgs = train_imgs[number]
size = len(train_imgs)
'''
# average_img = skl.average_img_by_number(number)
train_imgs = skl.get_imgs_by_number(number)
plotting_strength = True
if plotting_strength: strength_stats = []
start_time = datetime.datetime.now()
for i in range(iterations):
_, img = random.choice(train_imgs)
# import seaborn as sns
# import sys
import random
iters = 5 * 10**4
imgs_l = [skl.get_imgs_by_number(i) for i in range(10)]
strength_matrix_l = [
utils.read_pickle('pkl/nn_growable_' + str(i) + '.pkl') for i in range(10)
]
fig, axes = plt.subplots(2, 2, figsize=(10, 5), sharex=True, sharey=False)
axes = axes.flatten()
pfs = [
lambda img, matrix: NeuralNetwork.validate_linear(
img, matrix, gray_max=16, power=0, weight=10),
lambda img, matrix: NeuralNetwork.validate_linear(
img, matrix, gray_max=16, power=1, weight=10),
lambda img, matrix: NeuralNetwork.validate_linear(
img, matrix, gray_max=16, power=3, weight=10),
lambda img, matrix: NeuralNetwork.validate_threshold(
img, matrix, gray_max=16, power=3, threshhold=.2, weight=10)
]
# if True:
# for j, matrix in enumerate(strength_matrix_l):
for k, pf in enumerate(pfs):
j = 6
matrix = strength_matrix_l[j]
results_l = [[], [], [], [], [], [], [], [], [], []]
for imgs, result in zip(imgs_l, results_l):
strength_matrix_l = [
utils.read_pickle('pkl/nn_growable_' + str(i) + '.pkl') for i in range(10)
]
fig, axes = plt.subplots(5, 2, figsize=(3, 6), sharex=True, sharey=True)
axes = axes.flatten()
for j, matrix in enumerate(strength_matrix_l):
results_l = [[], [], [], [], [], [], [], [], [], []]
for imgs, result in zip(imgs_l, results_l):
for i in range(iters):
img = random.choice(imgs)[1]
result.append(
NeuralNetwork.validate_1(img,
matrix,
gray_max=16,
threshhold=.6,
weight=3))
for i, result in enumerate(results_l):
if i != j:
color = 'gray'
zorder = 0
line = 1
else:
color = 'red'
zorder = 1
line = 2
mu = np.mean(result)
std = np.std(result)
# sns.kdeplot(result, color=color, shade=False, shade_lowest=False, alpha=1, zorder=zorder)
import random
random.seed()
iters = 10 * 10 ** 4
num = 0
imgs_l = [skl.get_imgs_by_number(i) for i in range(10)]
strength_matrix_l = [utils.read_pickle('pkl/nn_growable_' + str(i) + '.pkl') for i in range(10)]
# fig, axes = plt.subplots(4, 1, figsize=(6, 6), sharex=True, sharey=False)
fig, axes = plt.subplots(3, 1, figsize=(6, 4), sharex=True, sharey=False)
axes = axes.flatten()
validators = [
lambda img, matrix: NeuralNetwork.validate_original(img, matrix),
lambda img, matrix: NeuralNetwork.validate_step(img, matrix, threshold=.6),
lambda img, matrix: NeuralNetwork.validate_linear(img, matrix, power=3, weight=10)]
# lambda img, matrix: NeuralNetwork.validate_threshold(img, matrix, power=3, threshhold=.2, weight=10)]
imgs = imgs_l[num]
for k, vldt in enumerate(validators):
matrix = strength_matrix_l[num]
results_l = [[], [], [], [], [], [], [], [], [], []]
for matrix, result in zip(strength_matrix_l, results_l):
for i in range(iters):
img = random.choice(imgs)[1]
result.append(vldt(img, matrix))
# get the mu and std for z-scores
results_l_part = [i for i in results_l if i != num]
imgs_l = [skl.get_imgs_by_number(i) for i in range(10)]
matrix_80_l = [
utils.read_pickle('pkl/nn_growable_80_' + str(i) + '.pkl')
for i in range(10)
]
matrix_81_l = [
utils.read_pickle('pkl/nn_growable_81_' + str(i) + '.pkl')
for i in range(10)
]
# fig, axes = plt.subplots(4, 1, figsize=(6, 6), sharex=True, sharey=False)
fig, axes = plt.subplots(3, 1, figsize=(6, 4), sharex=True, sharey=False)
axes = axes.flatten()
validators = [
lambda img, matrix: NeuralNetwork.validate_original(img, matrix),
lambda img, matrix: NeuralNetwork.validate_original(img, matrix),
# lambda img, matrix: NeuralNetwork.validate_step(img, matrix, threshold=.6),
lambda img, matrix: NeuralNetwork.validate_linear(
img, matrix, power=3, weight=100)
]
# lambda img, matrix: NeuralNetwork.validate_threshold(img, matrix, power=3, threshhold=.2, weight=10)]
imgs = imgs_l[num]
for k, (vldt, matrix_l) in enumerate(
zip(validators, (matrix_81_l, matrix_80_l, matrix_81_l))):
matrix = matrix_l[num]
results_l = [[], [], [], [], [], [], [], [], [], []]
for matrix, result in zip(matrix_l, results_l):
for i in range(iters):
img = random.choice(imgs)[1]