def local_predict(sess, model):
"""Test on the valid data."""
time0 = time.time()
predict_labels_list = list() # 所有的预测结果
marked_labels_list = list()
predict_scores = list()
for i in tqdm(xrange(n_va_batches)):
[X1_batch, X2_batch, y_batch] = get_batch(i)
marked_labels_list.extend(y_batch)
_batch_size = len(X1_batch)
fetches = [model.y_pred]
feed_dict = {model.X1_inputs: X1_batch, model.X2_inputs: X2_batch,
model.batch_size: _batch_size, model.tst: True, model.keep_prob: 1.0}
predict_labels = sess.run(fetches, feed_dict)[0]
predict_scores.append(predict_labels)
predict_labels = map(lambda label: label.argsort()[-1:-6:-1], predict_labels) # 取最大的5个下标
predict_labels_list.extend(predict_labels)
predict_label_and_marked_label_list = zip(predict_labels_list, marked_labels_list)
precision, recall, f1 = score_eval(predict_label_and_marked_label_list)
print('Local valid p=%g, r=%g, f1=%g' % (precision, recall, f1))
predict_scores = np.vstack(np.asarray(predict_scores))
local_scores_name = local_scores_path + model_name + '.npy'
np.save(local_scores_name, predict_scores)
print('local_scores.shape=', predict_scores.shape)
print('Writed the scores into %s, time %g s' % (local_scores_name, time.time() - time0))
def local_predict(sess, model):
"""Test on the valid data."""
time0 = time.time()
predict_labels_list = list() # 所有的预测结果
marked_labels_list = list()
predict_scores = list()
for i in tqdm(xrange(n_va_batches)):
[X1_batch, X2_batch, y_batch] = get_batch(i)
marked_labels_list.extend(y_batch)
_batch_size = len(X1_batch)
fetches = [model.y_pred]
feed_dict = {
model.X1_inputs: X1_batch,
model.X2_inputs: X2_batch,
model.batch_size: _batch_size,
model.tst: True,
model.keep_prob: 1.0
}
predict_labels = sess.run(fetches, feed_dict)[0]
predict_scores.append(predict_labels)
predict_labels = map(lambda label: label.argsort()[-1:-6:-1],
predict_labels) # 取最大的5个下标
predict_labels_list.extend(predict_labels)
predict_label_and_marked_label_list = zip(predict_labels_list,
marked_labels_list)
precision, recall, f1 = score_eval(predict_label_and_marked_label_list)
print('Local valid p=%g, r=%g, f1=%g' % (precision, recall, f1))
predict_scores = np.vstack(np.asarray(predict_scores))
local_scores_name = local_scores_path + model_name + '.npy'
np.save(local_scores_name, predict_scores)
print('local_scores.shape=', predict_scores.shape)
print('Writed the scores into %s, time %g s' %
(local_scores_name, time.time() - time0))
def valid_epoch(data_path, sess, model):
"""Test on the valid data."""
va_batches = os.listdir(data_path)
n_va_batches = len(va_batches)
_costs = 0.0
predict_labels_list = list() # 所有的预测结果
marked_labels_list = list()
for i in range(n_va_batches):
[X1_batch, X2_batch, y_batch] = get_batch(data_path, i)
marked_labels_list.extend(y_batch)
y_batch = to_categorical(y_batch)
_batch_size = len(y_batch)
fetches = [model.loss, model.y_pred]
feed_dict = {
model.X1_inputs: X1_batch,
model.X2_inputs: X2_batch,
model.y_inputs: y_batch,
model.batch_size: _batch_size,
model.tst: True,
model.keep_prob: 1.0
}
_cost, predict_labels = sess.run(fetches, feed_dict)
_costs += _cost
predict_labels = list(
map(lambda label: label.argsort()[-1:-6:-1],
predict_labels)) # 取最大的5个下标
predict_labels_list.extend(predict_labels)
predict_label_and_marked_label_list = zip(predict_labels_list,
marked_labels_list)
precision, recall, f1 = score_eval(predict_label_and_marked_label_list)
mean_cost = _costs / n_va_batches
return mean_cost, precision, recall, f1
def valid_epoch(data_path=data_valid_path):
"""Test on the valid data."""
_costs = 0.0
predict_labels_list = list() # 所有的预测结果
marked_labels_list = list() # 真实标签
_global_step = sess.run(global_step)
for i in range(n_va_batches):
[X1_batch, X2_batch, y_batch] = get_batch(data_path, i)
marked_labels_list.extend(y_batch)
y_batch = to_categorical(y_batch)
_batch_size = len(y_batch)
fetches = [merged, cost, y_pred]
feed_dict = {
X1_inputs: X1_batch,
X2_inputs: X2_batch,
y_inputs: y_batch,
batch_size: _batch_size,
keep_prob: 1.0,
tst: True,
n_updates: _global_step
}
summary, _cost, predict_labels = sess.run(fetches, feed_dict)
_costs += _cost
predict_labels = map(lambda label: label.argsort()[-1:-6:-1],
predict_labels) # 取最大的5个下标
predict_labels_list.extend(predict_labels)
predict_label_and_marked_label_list = zip(predict_labels_list,
marked_labels_list)
precision, recall, f1 = score_eval(predict_label_and_marked_label_list)
mean_cost = _costs / n_va_batches
return mean_cost, precision, recall, f1
def valid_epoch():
"""Testing or valid."""
data_valid._index_in_epoch = 0 # 先指向第一个值
_batch_size = te_batch_size
fetches = [cost, y_pred]
batch_num = int(valid_data_size / _batch_size)
start_time = time.time()
_costs = 0.0
predict_labels_list = list() # 所有的预测结果
for i in range(batch_num):
X_batch, y_batch = data_valid.next_batch(_batch_size)
X1_batch = X_batch[:, :n_step1]
X2_batch = X_batch[:, n_step1:]
y_batch = to_categorical(y_batch)
feed_dict = {
X1_inputs: X1_batch,
X2_inputs: X2_batch,
y_inputs: y_batch,
lr: 1e-5,
batch_size: _batch_size,
keep_prob: 1.0,
fc_keep_prob: 1.0,
tst: True,
n_updates: global_step
}
_cost, predict_labels = sess.run(fetches, feed_dict)
_costs += _cost
predict_labels = map(lambda label: label.argsort()[-1:-6:-1],
predict_labels) # 取最大的5个下标
predict_labels_list.extend(predict_labels)
predict_label_and_marked_label_list = zip(predict_labels_list,
marked_labels_list)
precision, recall, f1 = score_eval(predict_label_and_marked_label_list)
mean_cost = _costs / batch_num
return mean_cost, precision, recall, f1
def valid_epoch(data_path, sess, model):
"""Test on the valid data."""
va_batches = os.listdir(data_path)
n_va_batches = len(va_batches)
_costs = 0.0
predict_labels_list = list() # 所有的预测结果
marked_labels_list = list()
for i in xrange(n_va_batches):
[X1_batch, X2_batch, y_batch] = get_batch(data_path, i)
marked_labels_list.extend(y_batch)
y_batch = to_categorical(y_batch)
_batch_size = len(y_batch)
fetches = [model.loss, model.y_pred]
feed_dict = {model.X1_inputs: X1_batch, model.X2_inputs: X2_batch, model.y_inputs: y_batch,
model.batch_size: _batch_size, model.tst: True, model.keep_prob: 1.0}
_cost, predict_labels = sess.run(fetches, feed_dict)
_costs += _cost
predict_labels = map(lambda label: label.argsort()[-1:-6:-1], predict_labels) # 取最大的5个下标
predict_labels_list.extend(predict_labels)
predict_label_and_marked_label_list = zip(predict_labels_list, marked_labels_list)
precision, recall, f1 = score_eval(predict_label_and_marked_label_list)
mean_cost = _costs / n_va_batches
return mean_cost, precision, recall, f1
