Python top_k_categorical_accuracy Examples

Example #1

File: metrics_test.py Project: StephenOman/tensorflow

 def test_top_k_categorical_accuracy(self):
   with self.test_session():
     y_pred = K.variable(np.array([[0.3, 0.2, 0.1], [0.1, 0.2, 0.7]]))
     y_true = K.variable(np.array([[0, 1, 0], [1, 0, 0]]))
     result = K.eval(metrics.top_k_categorical_accuracy(y_true, y_pred, k=3))
     self.assertEqual(result, 1)
     result = K.eval(metrics.top_k_categorical_accuracy(y_true, y_pred, k=2))
     self.assertEqual(result, 0.5)
     result = K.eval(metrics.top_k_categorical_accuracy(y_true, y_pred, k=1))
     self.assertEqual(result, 0.)

Example #2

 def test_top_k_categorical_accuracy(self):
   with self.cached_session():
     y_pred = K.variable(np.array([[0.3, 0.2, 0.1], [0.1, 0.2, 0.7]]))
     y_true = K.variable(np.array([[0, 1, 0], [1, 0, 0]]))
     result = K.eval(metrics.top_k_categorical_accuracy(y_true, y_pred, k=3))
     self.assertEqual(result, 1)
     result = K.eval(metrics.top_k_categorical_accuracy(y_true, y_pred, k=2))
     self.assertEqual(result, 0.5)
     result = K.eval(metrics.top_k_categorical_accuracy(y_true, y_pred, k=1))
     self.assertEqual(result, 0.)

Example #3

File: clippervsranger_base.py Project: altostratous/dnnfault

 def evaluate(self, model, x, y_true, config):
     y_pred = model.predict(x, batch_size=64)
     return {
         'acc': top_k_categorical_accuracy(y_true, y_pred, k=1),
         'y_true': np.argmax(y_true, axis=1),
         'y_pred': np.argsort(y_pred, axis=1).T[-5:].T
     }

Example #4

File: egbaselines.py Project: ameyxd/aml-project-cnarm

def tkca(y_true,y_pred):
    # last_good_index = max([i for i in range(19) if int(tfksum(y_true[i,:]))!=0])
    mc = 0.0
    for i in range(19):
        print(y_true)
        print(y_pred)
        mc = mc + top_k_categorical_accuracy(y_true[:,i,:],y_pred[:,i,:])
        if y_true.numpy()[0][i][0] == 1:
            return mc/i

Example #5

File: model.py Project: tkuanlun350/Kaggle_Doodle

def cls_loss(label_logits, label):
    with tf.name_scope('cls_label_metrics'):
        label_pred = tf.nn.softmax(label_logits)
        top3_acc = top_k_categorical_accuracy(label, label_pred, k=3)
        add_moving_summary(top3_acc)

    #label_loss = tf.nn.sparse_softmax_cross_entropy_with_logits(
    #    labels=label, logits=label_logits)
    label_loss = tf.nn.softmax_cross_entropy_with_logits(labels=label,
                                                         logits=label_logits)
    label_loss = tf.reduce_mean(label_loss, name='label_loss')
    return label_loss

Example #6

File: util.py Project: rheehot/keras-flask-deployment

 def top_3_accuracy(true, pred):
     return top_k_categorical_accuracy(true, pred, 3)

Example #7

File: helper_util.py Project: softsys4ai/neural-distiller

def top_5_accuracy(y_true, y_pred):
    y_true = y_true[:, :256]
    y_pred = y_pred[:, :256]
    return top_k_categorical_accuracy(y_true, y_pred)

Example #8

 def top_2_accuracy(y_true, y_pred):
     return top_k_categorical_accuracy(y_true, y_pred, k=2)