print("\nStarting a Deep Belief Net..")
dbn = DeepBeliefNet(sizes={
"vis": image_size[0] * image_size[1],
"hid": 500,
"pen": 500,
"top": 2000,
"lbl": 10
},
image_size=image_size,
n_labels=10,
batch_size=100)
''' greedy layer-wise training '''
dbn.train_greedylayerwise(vis_trainset=train_imgs,
lbl_trainset=train_lbls,
n_iterations=20,
verbose=True)
# print("Classify training set")
# dbn.recognize(train_imgs, train_lbls)
#
# print("Classify test set")
# dbn.recognize(test_imgs, test_lbls)
print("Image generation")
for digit in range(10):
digit_1hot = np.zeros(shape=(1, 10))
digit_1hot[0, digit] = 1
dbn.generate(digit_1hot, name="rbm")
''' fine-tune wake-sleep training '''
dbn = DeepBeliefNet(
sizes={
"vis": image_size[0] * image_size[1],
"hid": 500,
"pen": 500,
"top": 2000,
"lbl": 10,
},
image_size=image_size,
n_labels=10,
batch_size=20,
)
dbn.train_greedylayerwise(
vis_trainset=train_imgs, lbl_trainset=train_lbls, n_iterations=10
)
rbm0 = dbn.rbm_stack["vis--hid"]
rbm1 = dbn.rbm_stack["hid--pen"]
rbm2 = dbn.rbm_stack["pen+lbl--top"]
image0 = train_imgs[:1,:]
lbl0 = train_lbls[:1,:]
lblany = np.ones(lbl0.shape) / 10
last = np.zeros((1,500))
losses = []
for i in range(500):
p_0, s_0 = rbm0.get_h_given_v_dir(p_v)
print("\nStarting a Deep Belief Net..")
dbn = DeepBeliefNet(sizes={
"vis": image_size[0] * image_size[1],
"hid": 500,
"pen": 500,
"top": 2000,
"lbl": 10
},
image_size=image_size,
n_labels=10,
batch_size=20)
''' greedy layer-wise training '''
aux = dbn.train_greedylayerwise(vis_trainset=train_imgs,
lbl_trainset=train_lbls,
n_iterations=ITERATIONS)
# plt.plot(range(10, 21), averages[-1], label="Original RBM")
# plt.plot(range(10, 21), aux, label="Greedy RBM")
# plt.xticks(range(10, 21))
# plt.xlabel("Epoch")
# plt.ylabel("Average Loss rate")
# plt.legend()
# plt.show()
dbn.recognize(train_imgs, train_lbls)
dbn.recognize(test_imgs, test_lbls)
#
# for digit in range(10):
# digit_1hot = np.zeros(shape=(1, 10))