def test(md, csv_file, model):
# load name of wavs to be classified
with open(csv_file, 'rb') as f:
reader = csv.reader(f)
lis = list(reader)
# do classification for each file
y_pred = []
te_y = []
for li in lis:
na = li[1]
#audio evaluation name
fe_path = eva_fd + '/' + feature + '/' + na + '.f'
info_path = label_csv + '/' + na + '.csv'
with open(info_path, 'rb') as g:
reader2 = csv.reader(g)
lis2 = list(reader2)
tags = lis2[-2][1]
y = np.zeros(num_classes)
for ch in tags:
y[lb_to_id[ch]] = 1
te_y.append(y)
X0 = cPickle.load(open(fe_path, 'rb'))
X0 = aud_utils.mat_2d_to_3d(X0, agg_num, hop)
X0 = aud_utils.mat_3d_to_nd(model, X0)
# predict
p_y_pred = md.predict(X0)
p_y_pred = np.mean(p_y_pred, axis=0) # shape:(n_label)
y_pred.append(p_y_pred)
return np.array(te_y), np.array(y_pred)
def GetAllData(fe_fd, csv_file, agg_num, hop):
"""
Input: Features folder(String), CSV file(String), agg_num(Integer), hop(Integer).
Output: Loaded features(Numpy Array) and labels(Numpy Array).
Loads all the features saved as pickle files.
"""
# read csv
with open( csv_file, 'rb') as f:
reader = csv.reader(f)
lis = list(reader)
# init list
X3d_all = []
y_all = []
i=0
for li in lis:
# load data
[na, lb] = li[0].split('\t')
na = na.split('/')[1][0:-4]
path = fe_fd + '/' + na + '.f'
X = aud_feature.load(path)
# reshape data to (n_block, n_time, n_freq)
i+=1
X3d = aud_utils.mat_2d_to_3d( X, agg_num, hop )
X3d_all.append( X3d )
y_all += [ lb_to_id[lb] ] * len( X3d )
print "Features loaded",i
print 'All files loaded successfully'
# concatenate list to array
X3d_all = np.concatenate( X3d_all )
y_all = np.array( y_all )
return X3d_all, y_all
def get_train_data(self):
"""
Loads all the features saved as pickle files.
Input: Features folder(str), CSV file(str)
Output: Loaded features(np array) and labels(np array).
"""
feature = self.feature
fe_fd = cfg.dev_fd + '/' + feature
csv_file = cfg.meta_train_csv
agg_num = self.agg_num
hop = self.hop
# read csv
with open(csv_file, 'rb') as f:
reader = csv.reader(f)
lis = list(reader)
# init list
X3d_all = []
y_all = []
i = 0
for li in lis:
# load data
na = li[1]
path = fe_fd + '/' + na + '.f'
info_path = cfg.label_csv + '/' + na + '.csv'
with open(info_path, 'rb') as g:
reader2 = csv.reader(g)
lis2 = list(reader2)
tags = lis2[-2][1]
y = np.zeros(len(cfg.labels))
for ch in tags:
y[cfg.lb_to_id[ch]] = 1
X = aud_feature.load(path)
# reshape data to (n_block, n_time, n_freq)
i += 1
X3d = aud_utils.mat_2d_to_3d(X, agg_num, hop)
X3d_all.append(X3d)
y_all += [y] * len(X3d)
print "Features loaded", i
print 'All files loaded successfully'
# concatenate list to array
X3d_all = np.concatenate(X3d_all)
y_all = np.array(y_all)
return X3d_all, y_all
def get_test_predictions(self, md):
model = self.model
feature = self.feature
fe_fd = cfg.eva_fd + '/' + feature
csv_file = cfg.txt_eva_path
agg_num = self.agg_num
hop = self.hop
eva_file = cfg.eva_file
# load name of wavs to be classified
with open(csv_file, 'rb') as f:
reader = csv.reader(f)
lis = list(reader)
# do classification for each file
names = []
pred_lbs = []
for li in lis:
names.append(li[0])
na = li[0][6:-4]
#audio evaluation name
fe_path = fe_fd + '/' + na + '.f'
X0 = cPickle.load(open(fe_path, 'rb'))
X0 = aud_utils.mat_2d_to_3d(X0, agg_num, hop)
X0 = aud_utils.mat_3d_to_nd(model, X0)
# predict
p_y_preds = md.predict(X0) # probability, size: (n_block,label)
preds = np.argmax(p_y_preds, axis=-1) # size: (n_block)
b = scipy.stats.mode(preds)
pred = int(b[0])
pred_lbs.append(cfg.id_to_lb[pred])
pred = []
# write out result
for i1 in xrange(len(names)):
fname = names[i1] + '\t' + pred_lbs[i1] + '\n'
pred.append(fname)
print 'write out finished!'
truth = open(eva_file, 'r').readlines()
pred = [i.split('\t')[1].split('\n')[0] for i in pred]
truth = [i.split('\t')[1] for i in truth]
pred.sort()
truth.sort()
return truth, pred
def GetAllData(fe_fd, csv_file, agg_num, hop):
"""
Input: Features folder(String), CSV file(String), agg_num(Integer), hop(Integer).
Output: Loaded features(Numpy Array) and labels(Numpy Array).
Loads all the features saved as pickle files.
"""
# read csv
with open(csv_file, 'rb') as f:
reader = csv.reader(f)
lis = list(reader)
# init list
X3d_all = []
y_all = []
i = 0
for li in lis:
# load data
na = li[1]
path = fe_fd + '/' + na + '.f'
info_path = label_csv + '/' + na + '.csv'
with open(info_path, 'rb') as g:
reader2 = csv.reader(g)
lis2 = list(reader2)
tags = lis2[-2][1]
y = np.zeros(len(labels))
for ch in tags:
y[lb_to_id[ch]] = 1
try:
X = cPickle.load(open(path, 'rb'))
except Exception as e:
print 'Error while parsing', path
continue
# reshape data to (n_block, n_time, n_freq)
i += 1
X3d = aud_utils.mat_2d_to_3d(X, agg_num, hop)
X3d_all.append(X3d)
y_all += [y] * len(X3d)
print "Features loaded", i
print 'All files loaded successfully'
# concatenate list to array
X3d_all = np.concatenate(X3d_all)
y_all = np.array(y_all)
return X3d_all, y_all
def get_test_predictions(self, md):
model = self.model
feature = self.feature
fe_fd = cfg.eva_fd + '/' + feature
csv_file = cfg.meta_test_csv
agg_num = self.agg_num
hop = self.hop
# load name of wavs to be classified
with open(csv_file, 'rb') as f:
reader = csv.reader(f)
lis = list(reader)
# do classification for each file
y_pred = []
te_y = []
for li in lis:
na = li[1]
#audio evaluation name
fe_path = fe_fd + '/' + na + '.f'
info_path = cfg.label_csv + '/' + na + '.csv'
with open(info_path, 'rb') as g:
reader2 = csv.reader(g)
lis2 = list(reader2)
tags = lis2[-2][1]
y = np.zeros(len(cfg.labels))
for ch in tags:
y[cfg.lb_to_id[ch]] = 1
te_y.append(y)
X0 = cPickle.load(open(fe_path, 'rb'))
X0 = aud_utils.mat_2d_to_3d(X0, agg_num, hop)
X0 = aud_utils.mat_3d_to_nd(model, X0)
# predict
p_y_pred = md.predict(X0)
p_y_pred = np.mean(p_y_pred, axis=0) # shape:(n_label)
y_pred.append(p_y_pred)
return np.array(te_y), np.array(y_pred)
def get_train_data(self):
"""
Loads all the features saved as pickle files.
Input: Features folder(str), CSV file(str)
Output: Loaded features(np array) and labels(np array).
"""
feature = self.feature
fe_fd = cfg.dev_fd + '/' + feature
csv_file = cfg.label_csv
agg_num = self.agg_num
hop = self.hop
# read csv
with open(csv_file, 'rb') as f:
reader = csv.reader(f)
lis = list(reader)
# init list
X3d_all = []
y_all = []
i = 0
for li in lis:
# load data
[na, lb] = li[0].split('\t')
na = na.split('/')[1][0:-4]
path = fe_fd + '/' + na + '.f'
X = aud_feature.load(path)
# reshape data to (n_block, n_time, n_freq)
i += 1
X3d = aud_utils.mat_2d_to_3d(X, agg_num, hop)
X3d_all.append(X3d)
y_all += [cfg.lb_to_id[lb]] * len(X3d)
print "Features loaded", i
print 'All files loaded successfully'
# concatenate list to array
X3d_all = np.concatenate(X3d_all)
y_all = np.array(y_all)
return X3d_all, y_all
