def doit(dic,priors,classes,K,diag):
err = {'train':list(), 'test':list()}
for k in K:
print '*'*15,'K =',str(k),'*'*15
nums, means, covs, nll = {},{},{},{}
# Build GMM models
for dif in dic['train']:
data = pack(dic['train'][dif])
for i in xrange(6):
_nums,_means,_covs,_nll = gmm.gmm(data, weights=None, K=k, hard=True, diagcov=diag)
if(i != 0):
if(_nll > nll[dif]):
continue
nums[dif],means[dif],covs[dif],nll[dif] = _nums,_means,_covs,_nll
criteria = [snll for dif in dic['train']]
kwparams = [{'nums':nums[dif], 'means':means[dif], 'covs':covs[dif], 'prior':priors[dif]} for dif in dic['train']]
# Evaluate
for x in dic:
labels, labels_est = [], []
for dif in dic[x]:
points = dic[x][dif]
labels += [dif for i in xrange(len(points))]
labels_est += optcriterion(points, classes, criteria, kwparams=kwparams, _max=False);
e = 100.0*sum( np.array(labels) != np.array(labels_est) ) / len(labels)
err[x].append( e )
print 'Confusion marix for' , x , 'data','(K={:},diagcov={:})'.format(k,diag)
utils.confusion(labels, labels_est, True)
print '% Error: ', e,'\n'
if(len(K) > 1):
pl.plot(K,err['train'],'--', label= 'Train'+(' (diagcov=True)' if diag else ''))
pl.plot(K,err['test'], label= 'Test'+(' (diagcov=True)' if diag else ''))
def doit(dic, priors, classes, K, diag):
err = {'train': list(), 'test': list()}
for k in K:
print '*' * 15, 'K =', str(k), '*' * 15
nums, means, covs, nll = {}, {}, {}, {}
# Build GMM models
for dif in dic['train']:
data = pack(dic['train'][dif])
for i in xrange(6):
_nums, _means, _covs, _nll = gmm.gmm(data,
weights=None,
K=k,
hard=True,
diagcov=diag)
if (i != 0):
if (_nll > nll[dif]):
continue
nums[dif], means[dif], covs[dif], nll[
dif] = _nums, _means, _covs, _nll
criteria = [snll for dif in dic['train']]
kwparams = [{
'nums': nums[dif],
'means': means[dif],
'covs': covs[dif],
'prior': priors[dif]
} for dif in dic['train']]
# Evaluate
for x in dic:
labels, labels_est = [], []
for dif in dic[x]:
points = dic[x][dif]
labels += [dif for i in xrange(len(points))]
labels_est += optcriterion(points,
classes,
criteria,
kwparams=kwparams,
_max=False)
e = 100.0 * sum(
np.array(labels) != np.array(labels_est)) / len(labels)
err[x].append(e)
print 'Confusion marix for', x, 'data', '(K={:},diagcov={:})'.format(
k, diag)
utils.confusion(labels, labels_est, True)
print '% Error: ', e, '\n'
if (len(K) > 1):
pl.plot(K,
err['train'],
'--',
label='Train' + (' (diagcov=True)' if diag else ''))
pl.plot(K,
err['test'],
label='Test' + (' (diagcov=True)' if diag else ''))
templistlen = [] for c in range (len(keyList)): templistlen.append(hmm.negloglik(temp,trans = MarkovModel[c][0],dists = MarkovModel[c][1])) #lassifiedtests.append(keyList[(np.argmin(templistlen))]) TestClassification.append(keyList[(np.argmin(templistlen))]) OriginalTestClassification.append(keyList[a]) llist = getlistoflengths(traindataStack[a]) for b in range (len(llist)): temp = np.array([traindataStack[a][b]]) templistlen = [] for c in range (len(keyList)): templistlen.append(hmm.negloglik(temp,trans = MarkovModel[c][0],dists = MarkovModel[c][1])) TrainClassification.append(keyList[(np.argmin(templistlen))]) OriginalTrainClassification.append(keyList[a]) print "Test Confusion Matrix" utils.confusion(OriginalTestClassification,TestClassification) print "Train Confusion Matrix" utils.confusion(OriginalTrainClassification,TrainClassification) print k diagcov = True print "Diagonal Covariance Matrix" for k in range (1,7): MarkovModel = [] for a in traindataStack: trans = hmm.lrtrans(k) llist = getlistoflengths(a) MarkovModel.append(hmm.hmm(np.column_stack(a),llist,trans,diagcov = diagcov)) # print np.shape(testdataStack) # print np.shape(testdataStack[0][0]) TestClassification = [] OriginalTestClassification = []
'''
Tune:
spp layer
bilinear: 注意对称（kernel pooling）和不对称（理想？两个cnn学习不同的特征）的情形，还有很多地方（不同想法的组合）没人探索过
SE-net
confusion (label smoothing)
lr
stn
http://blog.csdn.net/xbinworld/article/details/69049680
http://pytorch.org/tutorials/intermediate/spatial_transformer_tutorial.html
kaggle
EDA
https://www.kaggle.com/muonneutrino/exploration-transforming-images-in-python
https://www.kaggle.com/submarineering/submarineering-size-matters-0-75-lb
https://www.kaggle.com/keremt/getting-color-composites
https://www.kaggle.com/asindico/icebergs-and-ships-eda-and-augmentation (PIL)
https://www.kaggle.com/dimitrif/other-sentinel-data （数据经过了啥处理）
background
https://www.kaggle.com/devm2024/keras-model-for-beginners-0-210-on-lb-eda-r-d （数据采集原理）
https://www.kaggle.com/jgroff/despeckling-synthetic-aperture-radar-sar-images (去噪)
https://www.kaggle.com/dimitrif/domain-knowledge
https://www.kaggle.com/plarmuseau/how-to-use-the-angle-imho
angle
https://www.kaggle.com/c/statoil-iceberg-classifier-challenge/discussion/46195#261600
https://www.kaggle.com/brassmonkey381/viewing-leak-and-machine-images
Pseudo-labeling
https://towardsdatascience.com/simple-explanation-of-semi-supervised-learning-and-pseudo-labeling-c2218e8c769b
https://www.kaggle.com/c/statoil-iceberg-classifier-challenge/discussion/45852
OriginalTestClassification = []
TrainClassification = []
OriginalTrainClassification = []
for a in range(0, 5):
for b in range(3, len(signatures[a])):
OriginalTestClassification.append(a)
templist = []
for c in range(0, 5):
#print np.shape(np.array([np.column_stack(signatures[a][b]).T]))
templist.append(
hmm.negloglik(np.array(
[np.column_stack(signatures[a][b]).T]),
trans=MarkovModel[c][0],
dists=MarkovModel[c][1]))
TestClassification.append(np.argmin(templist))
utils.confusion(OriginalTestClassification, TestClassification)
print "completed for k = %d" % k
diagcov = True
#print np.shape(signatures)
#print np.shape(np.column_stack(signatures[1][0:3]).T)
print "Diagonal Covariance Matrix"
for k in range(1, 7):
MarkovModel = []
for a in range(0, 5):
trans = hmm.lrtrans(k)
llist = []
for b in range(0, 3):
# print np.shape(signatures[a][b])
llist.append([len(signatures[a][b])])
MarkovModel.append(
hmm.hmm(np.column_stack(signatures[a][0:3]),
hidden_num -= 2
new_rnn = reduced_rnn_net(old_rnn, int(row['row']),
int(row['col']), hidden_num)
print(
"\n======= RNN hidden size: {}==========\n".format(hidden_num))
start_time = time.time()
# Unsqueeze from 2-dimension to 3-dimension to match the rnn model.
acc, pred = test_model(new_rnn, flat_input_test, y_test,
test_seq_lens)
stop_time = time.time()
print("Execution time: %s ms" % ((stop_time - start_time) * 1000))
times.append((stop_time - start_time) * 1000)
mat = confusion(x_test.size(0), 3, pred, y_test)
F1_score(mat)
# Save the new network and evaluate its vector angle.
rnns.append(new_rnn)
old_rnn = new_rnn
saveNNParas(new_rnn, x_test, hidden_num)
vectors = pd.read_excel('vector_angle.xls', header=None)
if (vectors.empty):
cnt = 10
print("\n Finished: Vectors are empty! \n")
break
df = pd.DataFrame({
'row': vectors.iloc[:, 0],
# Various sequence length used for padding sequence and packed sequence in rnn modol.
l = [1104, 1028, 980, 964, 960, 956, 956, 932, 868, 840, 836, 808]
train_seq_lens = np.zeros((12 * 12))
for i in range(len(l)):
train_seq_lens[i * 12:(i + 1) * 12] = l[i]
test_seq_lens = np.zeros((4 * 12))
for i in range(len(l)):
test_seq_lens[i * 4:(i + 1) * 4] = l[i]
# Unsqueeze from 2-dimension to 3-dimension to match the rnn model.
flat_input_train = input_train.unsqueeze(-1)
train_model(rnn,
flat_input_train,
label_train,
train_seq_lens,
lr=lr,
epochs=epochs)
flat_input_test = input_test.unsqueeze(-1)
acc, pred = test_model(rnn, flat_input_test, label_test, test_seq_lens)
# if accuracy > 40:
# all_weight = rnn.rnn.all_weights.data
# saveExcel(all_weight, 'all_weight.xls', u'sheet1')
# saveDataset(input_test, label_test)
mat = confusion(input_test.size(0), output_dim, pred, label_test)
print("Confusion Matrix：")
print(mat)
F1_score(mat)
#normalized = min_max_norm(raw_data, 14)
#normalized.to_excel('music-features-processed.xlsx')
X_train, Y_train, X_test, Y_test = load_data(
'music-affect_v1/music-features-processed.xlsx',
features_num,
label_loc,
features_selector=selector,
spliting_ratio=0.8)
net = Net(features_num, hidden_num, classes_num)
train_model(net, X_train, Y_train, lr=learning_rate, epochs=epochs_num)
start_time = time.time()
accuracy, Y_pred = test_model(net, X_test, Y_test)
print("Execution time: %s ms" % ((time.time() - start_time) * 1000))
#Save relevant parameter for analysis.
if accuracy > 40:
saveNNParas(net, X_test, hidden_num)
torch.save(net.state_dict(), 'net_model.pt')
saveDataset(X_train, Y_train, 'training')
saveDataset(X_test, Y_test, 'testing')
mat = confusion(X_test.size(0), classes_num, Y_pred, Y_test)
print("Confusion Matrix：")
print(mat)
F1_score(mat)
print("\n========================== END ==================================")
