parser.add_argument('--plot', dest='plot', action='store_const',
const=True, default=False,
help='plots the NN weights')
parser.add_argument('-i', dest='interactive', action='store_const',
const=True, default=False,
help='once done training starts an interactive mode')
args = parser.parse_args()
# init
xornn = NN(2, 10, 1, 3, actifunc, dactifunc, 0.1)
# load brain
if args.load:
with open(args.load) as f:
xornn.load_brain(json.load(f))
# training
for x in range(args.train_amount):
inputs = [random.randint(0, 1), random.randint(0, 1)]
goal_output = [inputs[0] ^ inputs[1]]
xornn.backpropagate(inputs, goal_output)
# testing
if args.test:
for i in range(2):
for j in range(2):
print(f'{i} ^ {j} == {xornn.feedforward([i, j])[0]}')
# plotting
if args.plot:
parser.add_argument('-i',
dest='interactive',
action='store_const',
const=True,
default=False,
help='once done training starts an interactive mode')
args = parser.parse_args()
# init
calcnn = NN(3, 10, 1, 3, actifunc, dactifunc, 0.1)
# load brain
if args.load:
with open(args.load) as f:
calcnn.load_brain(json.load(f))
# data
traindata = []
testdata = []
with open('./train.txt') as f:
for line in f.readlines():
traindata.append(dataline(line))
with open('./test.txt') as f:
for line in f.readlines():
testdata.append(dataline(line))
# training
inputs = list(map(lambda x: x.mapped_inputs(), traindata))
goal_ouputs = list(map(lambda x: x.mapped_result(), traindata))
calcnn.train(inputs, goal_ouputs, args.train_amount)
