def main():
imgs = tf.placeholder(tf.float32, [None, IMAGE_WIDTH * IMAGE_HEIGHT])
keys = tf.placeholder(tf.float32, [None, N_CLASS])
train_model = create_CNN(imgs, Weight_Dicts, Biases_Dict, Dropout_Dict)
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(train_model, keys))
optimizer = tf.train.AdamOptimizer(0.01).minimize(cost)
# Evaluate the train model
correct_model = tf.equal(tf.argmax(train_model, 1), tf.argmax(keys, 1))
accuracy = tf.reduce_mean(tf.cast(correct_model, tf.float32))
init = tf.initialize_all_variables()
obj = DataSet()
obj.load()
with tf.Session() as sess:
sess.run(init)
step = 1
while step * BATCH_SIZE < TRAINING_ITERS:
batch_imgs, batch_keys = obj.next_batch(BATCH_SIZE)
sess.run(optimizer, feed_dict = {imgs : batch_imgs, keys : batch_keys})
if step % DISPLAY_STEP == 0:
acc = sess.run(accuracy, feed_dict = {imgs : batch_imgs, keys : batch_keys})
loss = sess.run(cost, feed_dict = {imgs : batch_imgs, keys : batch_keys})
print "Iter " + str(step * BATCH_SIZE) + ", MiniBatch Loss = " + "{:.6f}".format(loss) + ", Training Accuracy = " + "{:.5f}".format(acc)
step = step + 1
def main():
imgs = tf.placeholder(tf.float32, [None, IMAGE_WIDTH * IMAGE_HEIGHT])
keys = tf.placeholder(tf.float32, [None, N_CLASS])
train_model = create_CNN(imgs, Weight_Dicts, Biases_Dict, Dropout_Dict)
# Define loss and optimizer
cost = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(train_model, keys))
optimizer = tf.train.AdamOptimizer(0.01).minimize(cost)
# Evaluate the train model
correct_model = tf.equal(tf.argmax(train_model, 1), tf.argmax(keys, 1))
accuracy = tf.reduce_mean(tf.cast(correct_model, tf.float32))
init = tf.initialize_all_variables()
obj = DataSet()
obj.load()
with tf.Session() as sess:
sess.run(init)
step = 1
while step * BATCH_SIZE < TRAINING_ITERS:
batch_imgs, batch_keys = obj.next_batch(BATCH_SIZE)
sess.run(optimizer, feed_dict={imgs: batch_imgs, keys: batch_keys})
if step % DISPLAY_STEP == 0:
acc = sess.run(accuracy,
feed_dict={
imgs: batch_imgs,
keys: batch_keys
})
loss = sess.run(cost,
feed_dict={
imgs: batch_imgs,
keys: batch_keys
})
print "Iter " + str(
step *
BATCH_SIZE) + ", MiniBatch Loss = " + "{:.6f}".format(
loss) + ", Training Accuracy = " + "{:.5f}".format(acc)
step = step + 1
with tf.name_scope("accuracy"):
test_acc = call_precision(yl, yt, isCNN=True)
acc_sum_1 = tf.summary.scalar('test_acc', test_acc)
train_acc = call_precision(yl, yt, isCNN=True)
acc_sum_2 = tf.summary.scalar('training_acc', train_acc)
sess = tf.InteractiveSession()
tf.random.set_random_seed(SEED)
tf.global_variables_initializer().run()
writer = tf.summary.FileWriter('logs', sess.graph)
no_epoch = 100000
for i in range(no_epoch):
# breakpoint()
xl_batch, yt_batch, xl_batch_index = l_dataset.next_batch(batch_size)
xuindex_batch, _, xuindex_batch_index = uindex_dataset.random_batch(
batch_size)
xu_batch = samples[xuindex_batch]
xn_batch_index = neighborIndex[xl_batch_index, :k_of_knn] # .flatten()
xr_batch_index = remoteIndex[xl_batch_index, :m_of_knn]
xun_batch_index = neighborIndex[xuindex_batch_index +
labeled_data_size, :k_of_knn] # .flatten()
xur_batch_index = remoteIndex[xuindex_batch_index +
labeled_data_size, :m_of_knn]
wl_n = RBF_matrix[xl_batch_index.reshape(batch_size, 1),
xn_batch_index].reshape(-1, k_of_knn,
1) # 该reshape是必要的，不能去掉
wl_r = RBF_matrix[xl_batch_index.reshape(batch_size, 1),
xr_batch_index].reshape(-1, m_of_knn, 1)
wu_n = RBF_matrix[(xuindex_batch_index +