def rbmdiscriminative(rbm, x, ey, opts, chains, chainsy, debug=None):
n_classes = rbm.d.shape[0]
p_y_given_x, F = rbmpygivenx(rbm, x, 'train')
F_sigm = sigm(F)
F_sigm_prob = np.zeros(F_sigm.shape)
for c in range(n_classes):
F_sigm_prob[:, :, c] = np.multiply(F_sigm[:, :, c],
np.transpose(p_y_given_x[:, c]))
# O: F_sigm_prob[:,:,c] = np.matmul(F_sigm[:,:,c], np.transpose(p_y_given_x[:,c]))
# init grads
dw = np.zeros(rbm.W.shape) # :o dw = rbm.zeros((rbm.W.shape)
du = np.zeros(rbm.U.shape) # :o du = rbm.zeros(rbm.U.shape)
dc = np.zeros(rbm.c.shape) # :o dc = rbm.zeros(rbm.c.shape)
class_labels = predict(ey)
for c in range(n_classes):
# dw grad
# find idx for current class
bin_idx = class_labels == c
lin_idx = np.where(c == class_labels)
a = np.matmul(F_sigm[:, lin_idx[0], c],
x[lin_idx[0], :]) # # O: a = F_sigm[:, lin_idx, c]
b = np.matmul(F_sigm_prob[:, :, c], x)
dw = dw + a - b
# du grad
sum_F_sigm = np.sum(F_sigm[:, bin_idx, c], axis=1)
sum_F_sigm_prob = np.sum(F_sigm_prob[:, :, c], axis=1)
du[:, c] = sum_F_sigm - sum_F_sigm_prob
# dc
dc_diff = np.subtract(np.sum(F_sigm[:, bin_idx, c], axis=1),
np.sum(F_sigm_prob[:, :, c], axis=1))
dc = dc + np.reshape(dc_diff, (dc_diff.shape[0], 1))
# :o np.reshape(dc, (1, dc.shape[0])) + np.transpose(dc_diff)
# dd grad
dd = np.transpose(np.sum(ey - p_y_given_x, axis=0))
# create grads struct and scale grad by minibatch size.
grads = {
"dw": dw / opts.batchsize,
"db": np.zeros(rbm.b.shape),
"dc": dc / opts.batchsize,
"dd": dd / opts.batchsize,
"du": du / opts.batchsize,
}
curr_err = 0
chains = []
chainsy = []
return grads, curr_err, chains, chainsy
HL1 = np.zeros((2, 1))
x3_1 = np.zeros((3, 3))
out = np.zeros((4, 1))
for i in range(iterations):
out = np.zeros((4, 1))
for j in range(4):
inputs[:, 0] = input[:, j]
#HL1 = w1*[-1; inputs];
temp1[0, 0] = -1
temp1[1, 0] = inputs[0, 0]
temp1[2, 0] = inputs[1, 0]
HL1 = np.dot(w1, temp1)
HiddenLayerOutput1 = S.sigm(HL1)
temp2[0, 0] = -1
temp2[1, 0] = HiddenLayerOutput1[0, 0]
temp2[2, 0] = HiddenLayerOutput1[1, 0]
x3_1 = np.dot(w2, temp2)
out[j, 0] = S.sigm(x3_1)
delta3 = np.dot(SG.sigmDerivative(x3_1), groundTruth[j, 0] - out[j, 0])
temp3 = w2[:, 1:3].T
delta2 = np.dot(np.multiply(SG.sigmDerivative(HL1), temp3), delta3)
w2 = w2 + np.multiply(np.multiply(temp1.T, coeff), delta3)
c = np.ones((2, 1))
d = np.ones((2, 1))
e = np.ones((1, 3))
f = np.ones((1, 3))
for i in range(iteration):
out = np.zeros((4, 1))
for j in range(4):
inputs[:, 0] = input[:, j]
k[0, 0] = -1
k[1, 0] = inputs[0, 0]
k[2, 0] = inputs[1, 0]
#Hidden Layer 1
hl1 = np.dot(w1, k)
HiddenLayerOutput1 = sigm.sigm(hl1)
#Output Layer
h[0, 0] = -1
h[1, 0] = HiddenLayerOutput1[0, 0]
h[2, 0] = HiddenLayerOutput1[1, 0]
#Output Layer
x3_1 = np.dot(w2, h)
out[j, 0] = sigm.sigm(x3_1)
delta3 = np.multiply(sigmDerivative.sigmDerivative(x3_1), groundTruth[j,0] - out[j,0])
c = sigmDerivative.sigmDerivative(hl1)
d[0,0] = w2[0,1]
d[1,0] = w2[0,2]
delta2 = np.multiply(np.multiply(c,d), delta3)
fig = plt.Figure()
inputs = np.zeros([5, 1])
p = np.zeros([3, 1])
for i in range(iterations):
err = 0
for j in range(y1.shape[0]):
inputs[:, 0] = input[:, j]
outputStack1 = inputs
#forward propagation
outputStack2 = np.subtract(np.dot(stack1_w, outputStack1), stack1_b)
outputStack2 = sigm.sigm(outputStack2)
outputStack3 = np.subtract(np.dot(stack2_w, outputStack2), stack2_b)
outputStack3 = sigm.sigm(outputStack3)
#backward propagation
p[0:3, 0] = outputStack3[0:3, 0]
epsilon = nnloss.nnloss(groundTruth[j:j + 1, 0:3].T, p, 1)
cost = nnloss.nnloss(groundTruth[j:j + 1, 0:3].T, p, 0)
err = err + cost
gradStack_epsilon2 = np.multiply(
np.multiply(outputStack3, (1 - outputStack3)), epsilon)
epsilon = np.dot(stack2_w.T, gradStack_epsilon2)
counter = 0
for i in range(iterations):
err = 0
for j in range(0, y1.shape[0], batchSize):
data = input[:, j:j + batchSize]
labels = groundTruth[j:j + batchSize, :]
cost = 0
for kk in range(batchSize):
inputs[0:5, 0] = data[:, kk]
outputStack1 = inputs
# forward propagation
outputStack2 = np.subtract(np.dot(mystack_1_w, outputStack1),
mystack_1_b)
outputStack2 = S.sigm(outputStack2)
outputStack3 = np.subtract(np.dot(mystack_2_w, outputStack2),
mystack_2_b)
outputStack3 = S.sigm(outputStack3)
# backward propagation
p = outputStack3
epsilon = NL.nnloss(labels[kk:kk + 1, :].T, p, 1)
cost = NL.nnloss(groundTruth[kk:kk + 1, :].T, p, 0)
err = err + cost
if j == 0:
gradStack2_epsilon = np.multiply(
np.multiply(outputStack3, (1 - outputStack3)), epsilon)
epsilon = np.dot(mystack_2_w.T, gradStack2_epsilon)