I am trying to create neural nets with random weights in keras. I am using set_weights() function of models, to assign random weights. However, model.predict() gives the same output on a certain input regardless of weights. The output differs every time I run the program, but it's same while a program is running. Here is the code:
ConnectFourAI.py:
from keras.models import Sequential
from keras.layers import Dense
from minimax2 import ConnectFour
import numpy as np
from time import sleep
import itertools
import random
import time
def get_model():
model = Sequential()
model.add(Dense(630, input_dim=84, kernel_initializer='uniform', activation='relu'))
model.add(Dense(630,kernel_initializer='normal', activation='relu'))
model.add(Dense(7, kernel_initializer='normal', activation='relu'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
return model
map = {
'x':[1,0],
' ':[0,0],
'o':[0,1]
}
model = get_model()
def get_AI_move(grid):
global model
inp = np.array(list(itertools.chain.from_iterable([map[t] for t in np.array(grid).reshape(42)]))).reshape(1,84)
nnout = model.predict(inp)
# print(list(nnout[0]))
out = np.argmax(nnout)
while grid[0][out] != " ":
out = np.random.randint(7)
print("out = %d"%out)
return out
shapes = [(w.shape) for w in model.get_weights()]
print(list(model.get_weights()[0][0][0:5]))
def score_func(x, win):
if win == "x":
return 10000
elif win == " ":
return 2000
else:
return x**2
if __name__=="__main__":
for i in range(100):
weights = [np.random.randn(*s) for s in shapes]
# print(list(weights[0][0][0:5]))
model.set_weights(weights)
print(list(model.get_weights()[0][0][0:5]))
game = ConnectFour()
game.start_new()
rounds = game._round
win = game._winner
score = score_func(rounds, win)
print("%dth game scored %.3f"%(i+1,score))
seed = int(time.time()* 10**6)%(2**32)+1
np.random.seed(seed)
To recreate this error, you need an extra file. Everything is OK in this file, but the only call to random always gives the same value. Here is the file .
I don't know what exactly was going wrong, but I came up with a work around. Apparently there was some problem in random module due to which this behaviour took place when random module is called from 2 different files. So I used one file instead of two, and got the results I expected.
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.