Hi
I am using theano lib....i wanted to know how weights are getting updates
...and how i can print those weight value at every epoch ....i tried to
search on google a lot but not able to do ....i just wanted to save my
weights value in pickle file while training and load it back while
prediction ...i am pasting code here if you can help me out...thanks in
advace...
srng = RandomStreams()
def floatX(X):
return np.asarray(X, dtype=theano.config.floatX)
def init_weights(shape):
return theano.shared(floatX(np.random.randn(*shape) * 0.01))
def rectify(X):
return T.maximum(X, 0.)
def softmax(X):
e_x = T.exp(X - X.max(axis=1).dimshuffle(0, 'x'))
return e_x / e_x.sum(axis=1).dimshuffle(0, 'x')
def dropout(X, p=0.):
if p > 0:
retain_prob = 1 - p
X *= srng.binomial(X.shape, p=retain_prob,
dtype=theano.config.floatX)
X /= retain_prob
return X
def RMSprop(cost, params, lr=0.001, rho=0.9, epsilon=1e-6):
grads = T.grad(cost=cost, wrt=params)
updates = []
for p, g in zip(params, grads):
acc = theano.shared(p.get_value() * 0.)
acc_new = rho * acc + (1 - rho) * g ** 2
#print (rho * acc + (1 - rho) * g ** 2).eval()
gradient_scaling = T.sqrt(acc_new + epsilon)
g = g / gradient_scaling
updates.append((acc, acc_new))
updates.append((p, p - lr * g))
return updates
def model(X, w, w2, w3, w4, p_drop_conv, p_drop_hidden):
l1a = rectify(conv2d(X, w, border_mode='full'))
l1 = max_pool_2d(l1a, (2, 2))
l1 = dropout(l1, p_drop_conv)
l2a = rectify(conv2d(l1, w2))
l2 = max_pool_2d(l2a, (2, 2))
l2 = dropout(l2, p_drop_conv)
l3a = rectify(conv2d(l2, w3))
l3b = max_pool_2d(l3a, (2, 2))
l3 = T.flatten(l3b, outdim=2)
l3 = dropout(l3, p_drop_conv)
l4 = rectify(T.dot(l3, w4))
l4 = dropout(l4, p_drop_hidden)
pyx = softmax(T.dot(l4, w_o))
return l1, l2, l3, l4, pyx
trX = trX.reshape(-1, 1, 28, 28)
teX = teX.reshape(-1, 1, 28, 28)
print "Train Data ::::",trX.shape,"Train Lables :::",trY.shape#,trY
print "Test Data ::::",teX.shape,"Test Lables :::",teY.shape#,teY
X = T.dtensor4()
Y = T.dmatrix()
w = init_weights((32, 1, 3, 3))
w2 = init_weights((64, 32, 3, 3))
w3 = init_weights((128, 64, 3, 3))
w4 = init_weights((128*3*3 , 625))
w_o = init_weights((625, 5))
noise_l1, noise_l2, noise_l3, noise_l4, noise_py_x = model(X, w, w2, w3,
w4, 0.2, 0.5)
l1, l2, l3, l4, py_x = model(X, w, w2, w3, w4, 0., 0.)
y_x = T.argmax(noise_py_x, axis=1)
cost = T.mean(T.nnet.categorical_crossentropy(noise_py_x, Y))
params = [w, w2, w3, w4, w_o]
updates = RMSprop(cost, params, lr=0.001)
train = theano.function(inputs=[X, Y], outputs=cost, updates=updates,
allow_input_downcast=True)
predict = theano.function(inputs=[X], outputs=y_x,
allow_input_downcast=True)
--
---
You received this message because you are subscribed to the Google Groups
"theano-users" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
For more options, visit https://groups.google.com/d/optout.
