def evaluateOneEpoch(inputCoor, inputGraph, inputLabel, para, sess, trainOperaion):
test_loss = []
test_acc = []
test_predict = []
for i in range(len(inputCoor)):
xTest, graphTest, labelTest = inputCoor[i], inputGraph[i], inputLabel[i]
graphTest = graphTest.tocsr()
labelBinarize = label_binarize(labelTest, classes=[i for i in range(para.outputClassN)])
test_batch_size = para.testBatchSize
for testBatchID in range(len(labelTest) / test_batch_size):
start = testBatchID * test_batch_size
end = start + test_batch_size
batchCoor, batchGraph, batchLabel = get_mini_batch(xTest, graphTest, labelBinarize, start, end)
batchWeight = uniform_weight(batchLabel)
batchGraph = batchGraph.todense()
feed_dict = {trainOperaion['inputPC']: batchCoor, trainOperaion['inputGraph']: batchGraph,
trainOperaion['outputLabel']: batchLabel, trainOperaion['weights']: batchWeight,
trainOperaion['keep_prob_1']: 1.0, trainOperaion['keep_prob_2']: 1.0}
predict, loss_test, acc_test = sess.run(
[trainOperaion['predictLabels'], trainOperaion['loss'], trainOperaion['acc']], feed_dict=feed_dict)
test_loss.append(loss_test)
test_acc.append(acc_test)
test_predict.append(predict)
test_average_loss = np.mean(test_loss)
test_average_acc = np.mean(test_acc)
return test_average_loss, test_average_acc, test_predict
def train(self, X_train, Y_train, X_valid, Y_valid, iterations=20):
"""Dictionary is fed in the graph to train the model"""
print("Training model.")
for i in range(iterations):
batch_X, batch_Y = get_mini_batch(X_train, Y_train)
acc, loss = self.sess.run([self.accuracy, self.loss],
feed_dict={
self.X: batch_X,
self.Y_: batch_Y,
self.step: i,
self.pkeep: 1.0
})
print("Step: {}, Accuracy: {}, Loss: {}".format(i, acc, loss))
self.graph_plot.addData((i, acc), 0)
self.sess.run(self.minimize,
feed_dict={
self.X: batch_X,
self.Y_: batch_Y,
self.step: i,
self.pkeep: pkeep
})
# save model and check for accuracy on the validation set every 100 steps
if i % 100 == 0:
if len(X_valid) != 0:
acc = self.check_accuracy(X_valid, Y_valid)
print("\nTesting data, Accuracy: {}\n".format(acc))
self.graph_plot.addData((i, acc), 1)
self.graph_plot.plot()
if i % 1000 == 0:
self.save_model(i)
def trainOneEpoch(inputCoor, inputGraph, inputLabel, para, sess, trainOperaion, weight_dict, learningRate):
dataChunkLoss = []
dataChunkAcc = []
dataChunkRegLoss = []
for i in range(len(inputCoor)):
xTrain_1, graphTrain_1, labelTrain_1 = inputCoor[i], inputGraph[i], inputLabel[i]
graphTrain_1 = graphTrain_1.tocsr()
labelBinarize = label_binarize(labelTrain_1, classes=[j for j in range(para.outputClassN)])
xTrain, graphTrain, labelTrain = shuffle(xTrain_1, graphTrain_1, labelBinarize)
# labelBinarize = label_binarize(labelTrain, classes=[j for j in range(40)])
batch_loss = []
batch_acc = []
batch_reg = []
batchSize = para.batchSize
for batchID in range(len(labelBinarize) / para.batchSize):
start = batchID * batchSize
end = start + batchSize
batchCoor, batchGraph, batchLabel = get_mini_batch(xTrain, graphTrain, labelTrain, start, end)
batchGraph = batchGraph.todense()
batchCoor = add_noise(batchCoor, sigma=0.008, clip=0.02)
if para.weighting_scheme == 'uniform':
batchWeight = uniform_weight(batchLabel)
elif para.weighting_scheme == 'weighted':
batchWeight = weights_calculation(batchLabel, weight_dict)
else:
print 'please enter the valid weighting scheme'
#print batchWeight
feed_dict = {trainOperaion['inputPC']: batchCoor, trainOperaion['inputGraph']: batchGraph,
trainOperaion['outputLabel']: batchLabel, trainOperaion['lr']: learningRate,
trainOperaion['weights']: batchWeight,
trainOperaion['keep_prob_1']: para.keep_prob_1, trainOperaion['keep_prob_2']: para.keep_prob_2}
opt, loss_train, acc_train, loss_reg_train = sess.run(
[trainOperaion['train'], trainOperaion['loss_total'], trainOperaion['acc'], trainOperaion['loss_reg']],
feed_dict=feed_dict)
#print('The loss loss_reg and acc for this batch is {},{} and {}'.format(loss_train, loss_reg_train, acc_train))
batch_loss.append(loss_train)
batch_acc.append(acc_train)
batch_reg.append(loss_reg_train)
dataChunkLoss.append(np.mean(batch_loss))
dataChunkAcc.append(np.mean(batch_acc))
dataChunkRegLoss.append(np.mean(batch_reg))
train_average_loss = np.mean(dataChunkLoss)
train_average_acc = np.mean(dataChunkAcc)
loss_reg_average = np.mean(dataChunkRegLoss)
return train_average_loss, train_average_acc, loss_reg_average
def evaluateOneEpoch(inputCoor, inputGraph, inputLabel, para, sess, trainOperaion):
# Description: Performance on the test set data
# Input: (1)inputCoor: input coordinates (B, N, 3) (2) inputGraph: input graph (B, N*N) (3) inputLabel: labels (B, 1)
# (4) para: global Parameters (5) sess: Session (6) trainOperaion: placeholder dictionary
# Return: average loss, acc, regularization loss for test set
test_loss = []
test_acc = []
test_predict = []
for i in range(len(inputCoor)):
xTest, graphTest, labelTest = inputCoor[i], inputGraph[i], inputLabel[i]
graphTest = graphTest.tocsr()
labelBinarize = label_binarize(labelTest, classes=[j for j in range(40)])
test_batch_size = para.testBatchSize
for testBatchID in range(len(labelTest) / test_batch_size):
start = testBatchID * test_batch_size
end = start + test_batch_size
batchCoor, batchGraph, batchLabel = get_mini_batch(xTest, graphTest, labelBinarize, start, end)
batchWeight = uniform_weight(batchLabel)
batchGraph = batchGraph.todense()
batchIndexL1, centroid_coordinates = farthest_sampling_new(batchCoor, M=para.clusterNumberL1,
k=para.nearestNeighborL1, batch_size=test_batch_size,
nodes_n=para.pointNumber)
batchMiddleGraph = middle_graph_generation(centroid_coordinates, batch_size = test_batch_size, M = para.clusterNumberL1)
feed_dict = {trainOperaion['inputPC']: batchCoor, trainOperaion['inputGraph']: batchGraph,
trainOperaion['outputLabel']: batchLabel, trainOperaion['weights']: batchWeight,
trainOperaion['keep_prob_1']: 1.0, trainOperaion['keep_prob_2']: 1.0,
trainOperaion['batch_index_l1']: batchIndexL1,
trainOperaion['l2Graph']: batchMiddleGraph, trainOperaion['batch_size']: test_batch_size
}
predict, loss_test, acc_test = sess.run(
[trainOperaion['predictLabels'], trainOperaion['loss'], trainOperaion['acc']], feed_dict=feed_dict)
test_loss.append(loss_test)
test_acc.append(acc_test)
test_predict.append(predict)
test_average_loss = np.mean(test_loss)
test_average_acc = np.mean(test_acc)
return test_average_loss, test_average_acc, test_predict
def evaluateOneEpoch(inputCoor, inputGraph, inputLabel, para, sess, trainOperaion):
# Description: Performance on the test set data
# Input: (1)inputCoor: input coordinates (B, N, 3) (2) inputGraph: input graph (B, N*N) (3) inputLabel: labels (B, 1)
# (4) para: global Parameters (5) sess: Session (6) trainOperaion: placeholder dictionary
# Return: average loss, acc, regularization loss for test set
test_loss = []
test_acc = []
test_predict = []
for i in range(len(inputCoor)):
xTest, graphTest, labelTest = inputCoor[i], inputGraph[i], inputLabel[i]
graphTest = graphTest.tocsr()
labelBinarize = label_binarize(labelTest, classes=[j for j in range(40)])
test_batch_size = para.testBatchSize
for testBatchID in range(len(labelTest) / test_batch_size):
start = testBatchID * test_batch_size
end = start + test_batch_size
batchCoor, batchGraph, batchLabel = get_mini_batch(xTest, graphTest, labelBinarize, start, end)
batchWeight = uniform_weight(batchLabel)
batchGraph = batchGraph.todense()
# select the centroid points by farthest sampling and get the index of each centroid points n nearest neighbors
batchIndexL1, centroid_coordinates = farthest_sampling(batchCoor, M=para.clusterNumberL1,
k=para.nearestNeighborL1, batch_size=test_batch_size,
nodes_n=para.pointNumber)
batchMiddleGraph = middle_graph_generation(centroid_coordinates, batch_size = test_batch_size, M = para.clusterNumberL1)
feed_dict = {trainOperaion['inputPC']: batchCoor, trainOperaion['inputGraph']: batchGraph,
trainOperaion['outputLabel']: batchLabel, trainOperaion['weights']: batchWeight,
trainOperaion['keep_prob_1']: 1.0, trainOperaion['keep_prob_2']: 1.0,
trainOperaion['batch_index_l1']: batchIndexL1,
trainOperaion['l2Graph']: batchMiddleGraph, trainOperaion['batch_size']: test_batch_size
}
predict, loss_test, acc_test = sess.run(
[trainOperaion['predictLabels'], trainOperaion['loss'], trainOperaion['acc']], feed_dict=feed_dict)
test_loss.append(loss_test)
test_acc.append(acc_test)
test_predict.append(predict)
test_average_loss = np.mean(test_loss)
test_average_acc = np.mean(test_acc)
return test_average_loss, test_average_acc, test_predict
def trainOneEpoch(inputCoor, inputGraph, inputLabel, para, sess, trainOperaion,
weight_dict, learningRate):
# Description: training one epoch (two options to train the model, using weighted gradient descent or normal gradient descent)
# Input: (1)inputCoor: input coordinates (B, N, 3) (2) inputGraph: input graph (B, N*N) (3) inputLabel: labels (B, 1)
# (4) para: global Parameters (5) sess: Session (6) trainOperaion: placeholder dictionary
# (7) weight_dict: weighting scheme used of weighted gradient descnet (8)learningRate: learning rate for current epoch
# Return: average loss, acc, regularization loss for training set
dataChunkLoss = []
dataChunkAcc = []
dataChunkRegLoss = []
for i in range(len(inputLabel)):
xTrain_1, graphTrain_1, labelTrain_1 = inputCoor[i], inputGraph[
i], inputLabel[i]
graphTrain_1 = graphTrain_1.tocsr()
labelBinarize = label_binarize(labelTrain_1,
classes=[j for j in range(40)])
xTrain, graphTrain, labelTrain = shuffle(xTrain_1, graphTrain_1,
labelBinarize)
batch_loss = []
batch_acc = []
batch_reg = []
batchSize = para.batchSize
for batchID in range(len(labelBinarize) / para.batchSize):
start = batchID * batchSize
end = start + batchSize
batchCoor, batchGraph, batchLabel = get_mini_batch(
xTrain, graphTrain, labelTrain, start, end)
batchGraph = batchGraph.todense()
batchCoor = add_noise(batchCoor, sigma=0.008, clip=0.02)
if para.weighting_scheme == 'uniform':
batchWeight = uniform_weight(batchLabel)
elif para.weighting_scheme == 'weighted':
batchWeight = weights_calculation(batchLabel, weight_dict)
else:
print 'please enter a valid weighting scheme'
batchIndexL1, centroid_coordinates = farthest_sampling_new(
batchCoor,
M=para.clusterNumberL1,
k=para.nearestNeighborL1,
batch_size=batchSize,
nodes_n=para.pointNumber)
batchMiddleGraph = middle_graph_generation(centroid_coordinates,
batch_size=batchSize,
M=para.clusterNumberL1)
feed_dict = {
trainOperaion['inputPC']: batchCoor,
trainOperaion['inputGraph']: batchGraph,
trainOperaion['outputLabel']: batchLabel,
trainOperaion['lr']: learningRate,
trainOperaion['weights']: batchWeight,
trainOperaion['keep_prob_1']: para.keep_prob_1,
trainOperaion['keep_prob_2']: para.keep_prob_2,
trainOperaion['batch_index_l1']: batchIndexL1,
trainOperaion['l2Graph']: batchMiddleGraph,
trainOperaion['batch_size']: para.batchSize
}
opt, loss_train, acc_train, loss_reg_train = sess.run(
[
trainOperaion['train'], trainOperaion['loss_total'],
trainOperaion['acc'], trainOperaion['loss_reg']
],
feed_dict=feed_dict)
batch_loss.append(loss_train)
batch_acc.append(acc_train)
batch_reg.append(loss_reg_train)
#print "The loss, L2 loss and acc for this batch is {}, {} and {}".format(loss_train, loss_reg_train, acc_train)
dataChunkLoss.append(np.mean(batch_loss))
dataChunkAcc.append(np.mean(batch_acc))
dataChunkRegLoss.append(np.mean(batch_reg))
train_average_loss = np.mean(dataChunkLoss)
train_average_acc = np.mean(dataChunkAcc)
loss_reg_average = np.mean(dataChunkRegLoss)
return train_average_loss, train_average_acc, loss_reg_average
def trainOneEpoch(inputCoor, inputGraph, inputLabel, para, sess, trainOperaion,
weight_dict, learningRate):
# Description: training one epoch (two options to train the model, using weighted gradient descent or normal gradient descent)
# Input: (1)inputCoor: input coordinates (B, N, 3) (2) inputGraph: input graph (B, N*N) (3) inputLabel: labels (B, 1)
# (4) para: global Parameters (5) sess: Session (6) trainOperaion: placeholder dictionary
# (7) weight_dict: weighting scheme used of weighted gradient descnet (8)learningRate: learning rate for current epoch
# Return: average loss, acc, regularization loss for training set
dataChunkLoss = []
dataChunkAcc = []
dataChunkRegLoss = []
for i in range(len(inputLabel)):
xTrain_1, graphTrain_1, labelTrain_1 = inputCoor[i], inputGraph[i], inputLabel[i]
graphTrain_1 = graphTrain_1.tocsr()
labelBinarize = label_binarize(labelTrain_1, classes=[j for j in range(40)])
xTrain, graphTrain, labelTrain = shuffle(xTrain_1, graphTrain_1, labelBinarize)
batch_loss = []
batch_acc = []
batch_reg = []
batchSize = para.batchSize
for batchID in range(len(labelBinarize) / para.batchSize):
start = batchID * batchSize
end = start + batchSize
batchCoor, batchGraph, batchLabel = get_mini_batch(xTrain, graphTrain, labelTrain, start, end)
batchGraph = batchGraph.todense()
batchCoor = add_noise(batchCoor, sigma=0.008, clip=0.02)
if para.weighting_scheme == 'uniform':
batchWeight = uniform_weight(batchLabel)
elif para.weighting_scheme == 'weighted':
batchWeight = weights_calculation(batchLabel, weight_dict)
else:
print 'please enter a valid weighting scheme'
batchIndexL1, centroid_coordinates = farthest_sampling_new(batchCoor, M=para.clusterNumberL1,
k=para.nearestNeighborL1, batch_size=batchSize,
nodes_n=para.pointNumber)
batchMiddleGraph = middle_graph_generation(centroid_coordinates, batch_size = batchSize, M = para.clusterNumberL1)
feed_dict = {trainOperaion['inputPC']: batchCoor, trainOperaion['inputGraph']: batchGraph,
trainOperaion['outputLabel']: batchLabel, trainOperaion['lr']: learningRate,
trainOperaion['weights']: batchWeight,
trainOperaion['keep_prob_1']: para.keep_prob_1, trainOperaion['keep_prob_2']: para.keep_prob_2,
trainOperaion['batch_index_l1']: batchIndexL1,
trainOperaion['l2Graph']: batchMiddleGraph, trainOperaion['batch_size']: para.batchSize}
opt, loss_train, acc_train, loss_reg_train = sess.run(
[trainOperaion['train'], trainOperaion['loss_total'], trainOperaion['acc'], trainOperaion['loss_reg']],
feed_dict=feed_dict)
batch_loss.append(loss_train)
batch_acc.append(acc_train)
batch_reg.append(loss_reg_train)
#print "The loss, L2 loss and acc for this batch is {}, {} and {}".format(loss_train, loss_reg_train, acc_train)
dataChunkLoss.append(np.mean(batch_loss))
dataChunkAcc.append(np.mean(batch_acc))
dataChunkRegLoss.append(np.mean(batch_reg))
train_average_loss = np.mean(dataChunkLoss)
train_average_acc = np.mean(dataChunkAcc)
loss_reg_average = np.mean(dataChunkRegLoss)
return train_average_loss, train_average_acc, loss_reg_average