def do_eval(sess, train_q, train_a, train_lab):
train_correct = 0.0
# number_examples = len(train_q)
# print("valid examples:", number_examples)
eval_loss, eval_accc, eval_counter = 0.0, 0.0, 0
eval_true_positive, eval_false_positive, eval_true_negative, eval_false_negative = 0, 0, 0, 0
# batch_size = 1
weights_label = {} # weight_label[label_index]=(number,correct)
weights = np.ones((opt.batch_size))
kf_train = get_minibatches_idx(len(train_q),
opt.batch_size,
shuffle=True)
for _, train_index in kf_train:
train_sents_1 = [train_q[t] for t in train_index]
train_sents_2 = [train_a[t] for t in train_index]
train_labels = [train_lab[t] for t in train_index]
train_labels_array = np.array(train_labels)
# print("train_labels", train_labels.shape)
# train_labels = train_labels.reshape((len(train_labels), opt.category))
train_labels = np.eye(opt.category)[train_labels_array]
x_train_batch_1, x_train_mask_1 = prepare_data_for_emb(
train_sents_1, opt)
x_train_batch_2, x_train_mask_2 = prepare_data_for_emb(
train_sents_2, opt)
curr_eval_loss, curr_accc, logits = sess.run(
[loss_, accuracy_, logits_],
feed_dict={
x_1_: x_train_batch_1,
x_2_: x_train_batch_2,
x_mask_1_: x_train_mask_1,
x_mask_2_: x_train_mask_2,
y_: train_labels,
opt.weights_label: weights,
keep_prob: 1.0
})
true_positive, false_positive, true_negative, false_negative = compute_confuse_matrix(
logits, train_labels
) # logits:[batch_size,label_size]-->logits[0]:[label_size]
# write_predict_error_to_file(start,file_object,logits[0], evalY[start:end][0],vocabulary_index2word,evalX1[start:end],evalX2[start:end])
eval_loss, eval_accc, eval_counter = eval_loss + curr_eval_loss, eval_accc + curr_accc, eval_counter + 1 # 注意这里计算loss和accc的方法，计算累加值，然后归一化
weights_label = compute_labels_weights(
weights_label, logits, train_labels_array
) # compute_labels_weights(weights_label,logits,labels)
eval_true_positive, eval_false_positive = eval_true_positive + true_positive, eval_false_positive + false_positive
eval_true_negative, eval_false_negative = eval_true_negative + true_negative, eval_false_negative + false_negative
# weights_label = compute_labels_weights(weights_label, logits, evalY[start:end]) #compute_labels_weights(weights_label,logits,labels)
print("true_positive:", eval_true_positive, ";false_positive:",
eval_false_positive, ";true_negative:", eval_true_negative,
";false_negative:", eval_false_negative)
p = float(eval_true_positive) / float(eval_true_positive +
eval_false_positive)
r = float(eval_true_positive) / float(eval_true_positive +
eval_false_negative)
f1_score = (2 * p * r) / (p + r)
print("eval_counter:", eval_counter, ";eval_acc:", eval_accc)
return eval_loss / float(eval_counter), eval_accc / float(
eval_counter), f1_score, p, r, weights_label
def do_eval(sess, textCNN, evalX1, evalX2, evalBlueScores, evalY, iteration,
vocabulary_index2word):
number_examples = len(evalX1)
print("valid examples:", number_examples)
eval_loss, eval_accc, eval_counter = 0.0, 0.0, 0
eval_true_positive, eval_false_positive, eval_true_negative, eval_false_negative = 0, 0, 0, 0
batch_size = 1
weights_label = {} # weight_label[label_index]=(number,correct)
weights = np.ones((batch_size))
for start, end in zip(range(0, number_examples, batch_size),
range(batch_size, number_examples, batch_size)):
feed_dict = {
textCNN.input_x1: evalX1[start:end],
textCNN.input_x2: evalX2[start:end],
textCNN.input_bluescores: evalBlueScores[start:end],
textCNN.input_y: evalY[start:end],
textCNN.weights: weights,
textCNN.dropout_keep_prob: 1.0,
textCNN.iter: iteration,
textCNN.tst: True
}
curr_eval_loss, curr_accc, logits = sess.run(
[textCNN.loss_val, textCNN.accuracy, textCNN.logits],
feed_dict) #curr_eval_acc--->textCNN.accuracy
true_positive, false_positive, true_negative, false_negative = compute_confuse_matrix(
logits[0], evalY[start:end]
[0]) #logits:[batch_size,label_size]-->logits[0]:[label_size]
write_predict_error_to_file(start, file_object, logits[0],
evalY[start:end][0], vocabulary_index2word,
evalX1[start:end], evalX2[start:end])
eval_loss, eval_accc, eval_counter = eval_loss + curr_eval_loss, eval_accc + curr_accc, eval_counter + 1
eval_true_positive, eval_false_positive = eval_true_positive + true_positive, eval_false_positive + false_positive
eval_true_negative, eval_false_negative = eval_true_negative + true_negative, eval_false_negative + false_negative
# print("logits", type(logits), "evalY:", type(evalY))
weights_label = compute_labels_weights(
weights_label, logits, evalY[start:end]
) #compute_labels_weights(weights_label,logits,labels)
print("true_positive:", eval_true_positive, ";false_positive:",
eval_false_positive, ";true_negative:", eval_true_negative,
";false_negative:", eval_false_negative)
p = float(eval_true_positive) / float(eval_true_positive +
eval_false_positive + small_value)
r = float(eval_true_positive) / float(eval_true_positive +
eval_false_negative + small_value)
f1_score = (2 * p * r) / (p + r + small_value)
print("eval_counter:", eval_counter, ";eval_acc:", eval_accc)
return eval_loss / float(eval_counter), eval_accc / float(
eval_counter), f1_score, p, r, weights_label
