Python numpy.argmax() Examples

def _peaks1D(self):
        if self.num_src == 1:
            self.src_idx[0] = np.argmax(self.P)
            self.sources[:, 0] = self.loc[:, self.src_idx[0]]
            self.phi_recon = self.theta[self.src_idx[0]]
        else:
            peak_idx = []
            n = self.P.shape[0]
            for i in range(self.num_loc):
                # straightforward peak finding
                if self.P[i] >= self.P[(i-1)%n] and self.P[i] > self.P[(i+1)%n]:
                    if len(peak_idx) == 0 or peak_idx[-1] != i-1:
                        if not (i == self.num_loc and self.P[i] == self.P[0]):
                            peak_idx.append(i)

            peaks = self.P[peak_idx]
            max_idx = np.argsort(peaks)[-self.num_src:]
            self.src_idx = [peak_idx[k] for k in max_idx]
            self.sources = self.loc[:, self.src_idx]
            self.phi_recon = self.theta[self.src_idx]
            self.num_src = len(self.src_idx)


# ------------------Miscellaneous Functions---------------------# 

def process_box(self, b, h, w, threshold):
	max_indx = np.argmax(b.probs)
	max_prob = b.probs[max_indx]
	label = self.meta['labels'][max_indx]
	if max_prob > threshold:
		left  = int ((b.x - b.w/2.) * w)
		right = int ((b.x + b.w/2.) * w)
		top   = int ((b.y - b.h/2.) * h)
		bot   = int ((b.y + b.h/2.) * h)
		if left  < 0    :  left = 0
		if right > w - 1: right = w - 1
		if top   < 0    :   top = 0
		if bot   > h - 1:   bot = h - 1
		mess = '{}'.format(label)
		return (left, right, top, bot, mess, max_indx, max_prob)
	return None 

def train(self):
        while (self.epoch < self.option.max_epoch and not self.early_stopped):
            self.one_epoch_train()
            self.one_epoch_valid()
            self.one_epoch_test()
            self.epoch += 1
            model_path = self.saver.save(self.sess, 
                                         self.option.model_path,
                                         global_step=self.epoch)
            print("Model saved at %s" % model_path)
            
            if self.early_stop():
                self.early_stopped = True
                print("Early stopped at epoch %d" % (self.epoch))
        
        all_test_in_top = [np.mean(x[1]) for x in self.test_stats]
        best_test_epoch = np.argmax(all_test_in_top)
        best_test = all_test_in_top[best_test_epoch]
        
        msg = "Best test in top: %0.4f at epoch %d." % (best_test, best_test_epoch + 1)       
        print(msg)
        self.log_file.write(msg + "\n")
        pickle.dump([self.train_stats, self.valid_stats, self.test_stats],
                    open(os.path.join(self.option.this_expsdir, "results.pckl"), "w")) 

def __getitem__(self, index):

        img=self.adv_flat[self.sample_num,:]

        if(self.shuff == False):
            # shuff is true for non-pgd attacks
            img = torch.from_numpy(np.reshape(img,(3,32,32)))
        else:
            img = torch.from_numpy(img).type(torch.FloatTensor)
        target = np.argmax(self.adv_dict["adv_labels"],axis=1)[self.sample_num]
        # doing this so that it is consistent with all other datasets
        # to return a PIL Image
        if self.transform is not None:
            img = self.transform(img)

        if self.target_transform is not None:
            target = self.target_transform(target)

        self.sample_num = self.sample_num + 1
        return img, target 

def __getitem__(self, index):

        img=self.adv_flat[self.sample_num,:]

        if(self.shuff == False):
            # shuff is true for non-pgd attacks
            img = torch.from_numpy(np.reshape(img,(3,32,32)))
        else:
            img = torch.from_numpy(img).type(torch.FloatTensor)
        target = np.argmax(self.adv_dict["adv_labels"],axis=1)[self.sample_num]
        # doing this so that it is consistent with all other datasets
        # to return a PIL Image
        if self.transform is not None:
            img = self.transform(img)

        if self.target_transform is not None:
            target = self.target_transform(target)

        self.sample_num = self.sample_num + 1
        return img, target 

def __getitem__(self, index):
        img=self.adv_flat[self.sample_num,:]
        if(self.transp == False):
            # shuff is true for non-pgd attacks
            img = torch.from_numpy(np.reshape(img,(28,28)))
        else:
            img = torch.from_numpy(img).type(torch.FloatTensor)
        target = np.argmax(self.adv_dict["adv_labels"],axis=1)[self.sample_num]
        # doing this so that it is consistent with all other datasets
        # to return a PIL Image

        if self.transform is not None:
            img = self.transform(img)
        if self.target_transform is not None:
            target = self.target_transform(target)
        self.sample_num = self.sample_num + 1
        return img, target 

def binary_refinement(sess,Best_X_adv,
                      X_adv, Y, ALPHA, ub, lb, model, dataset='cifar'):
    num_samples = np.shape(X_adv)[0]
    print(dataset)
    if(dataset=="mnist"):
        X_place = tf.placeholder(tf.float32, shape=[1, 1, 28, 28])
    else:
        X_place = tf.placeholder(tf.float32, shape=[1, 3, 32, 32])

    pred = model(X_place)
    for i in range(num_samples):
        logits_op = sess.run(pred,feed_dict={X_place:X_adv[i:i+1,:,:,:]})
        if(not np.argmax(logits_op) == np.argmax(Y[i,:])):
            # Success, increase alpha
            Best_X_adv[i,:,:,:] = X_adv[i,:,:,]
            lb[i] = ALPHA[i,0]
        else:
            ub[i] = ALPHA[i,0]
        ALPHA[i] = 0.5*(lb[i] + ub[i])
    return ALPHA, Best_X_adv 

def test_attack_strength(self):
        """
        If clipping is not done at each iteration (not passing clip_min and
        clip_max to fgm), this attack fails by
        np.mean(orig_labels == new_labels) == .39.
        """
        x_val = np.random.rand(100, 2)
        x_val = np.array(x_val, dtype=np.float32)

        x_adv = self.attack.generate_np(x_val, eps=1.0, ord=np.inf,
                                        clip_min=0.5, clip_max=0.7,
                                        nb_iter=5)

        orig_labs = np.argmax(self.sess.run(self.model(x_val)), axis=1)
        new_labs = np.argmax(self.sess.run(self.model(x_adv)), axis=1)
        self.assertTrue(np.mean(orig_labs == new_labs) < 0.1) 

def test_generate_np_targeted_gives_adversarial_example(self):
        x_val = np.random.rand(100, 2)
        x_val = np.array(x_val, dtype=np.float32)

        feed_labs = np.zeros((100, 2))
        feed_labs[np.arange(100), np.random.randint(0, 1, 100)] = 1
        x_adv = self.attack.generate_np(x_val, max_iterations=100,
                                        binary_search_steps=3,
                                        initial_const=1,
                                        clip_min=-5, clip_max=5,
                                        batch_size=100, y_target=feed_labs)

        new_labs = np.argmax(self.sess.run(self.model(x_adv)), axis=1)

        self.assertTrue(np.mean(np.argmax(feed_labs, axis=1) == new_labs)
                        > 0.9) 

def test_generate_gives_adversarial_example(self):

        x_val = np.random.rand(100, 2)
        x_val = np.array(x_val, dtype=np.float32)

        orig_labs = np.argmax(self.sess.run(self.model(x_val)), axis=1)
        feed_labs = np.zeros((100, 2))
        feed_labs[np.arange(100), orig_labs] = 1
        x = tf.placeholder(tf.float32, x_val.shape)
        y = tf.placeholder(tf.float32, feed_labs.shape)

        x_adv_p = self.attack.generate(x, max_iterations=100,
                                       binary_search_steps=3,
                                       initial_const=1,
                                       clip_min=-5, clip_max=5,
                                       batch_size=100, y=y)
        self.assertEqual(x_val.shape, x_adv_p.shape)
        x_adv = self.sess.run(x_adv_p, {x: x_val, y: feed_labs})

        new_labs = np.argmax(self.sess.run(self.model(x_adv)), axis=1)

        self.assertTrue(np.mean(orig_labs == new_labs) < 0.1) 

def test_generate_np_targeted_gives_adversarial_example(self):
        x_val = np.random.rand(100, 2)
        x_val = np.array(x_val, dtype=np.float32)

        feed_labs = np.zeros((100, 2))
        feed_labs[np.arange(100), np.random.randint(0, 1, 100)] = 1
        x_adv = self.attack.generate_np(x_val, max_iterations=100,
                                        binary_search_steps=3,
                                        initial_const=1,
                                        clip_min=-5, clip_max=5,
                                        batch_size=100, y_target=feed_labs)

        new_labs = np.argmax(self.sess.run(self.model(x_adv)), axis=1)

        self.assertTrue(np.mean(np.argmax(feed_labs, axis=1) == new_labs) >
                        0.9) 

def test_generate_gives_adversarial_example(self):

        x_val = np.random.rand(100, 2)
        x_val = np.array(x_val, dtype=np.float32)

        orig_labs = np.argmax(self.sess.run(self.model(x_val)), axis=1)
        feed_labs = np.zeros((100, 2))
        feed_labs[np.arange(100), orig_labs] = 1
        x = tf.placeholder(tf.float32, x_val.shape)
        y = tf.placeholder(tf.float32, feed_labs.shape)

        x_adv_p = self.attack.generate(x, max_iterations=100,
                                       binary_search_steps=3,
                                       initial_const=1,
                                       clip_min=-5, clip_max=5,
                                       batch_size=100, y=y)
        self.assertEqual(x_val.shape, x_adv_p.shape)
        x_adv = self.sess.run(x_adv_p, {x: x_val, y: feed_labs})

        new_labs = np.argmax(self.sess.run(self.model(x_adv)), axis=1)

        self.assertTrue(np.mean(orig_labs == new_labs) < 0.1) 

def test_generate_gives_adversarial_example(self):

        x_val = np.random.rand(100, 2)
        x_val = np.array(x_val, dtype=np.float32)

        orig_labs = np.argmax(self.sess.run(self.model(x_val)), axis=1)
        x = tf.placeholder(tf.float32, x_val.shape)

        x_adv_p = self.attack.generate(x, over_shoot=0.02, max_iter=50,
                                       nb_candidate=2, clip_min=-5, clip_max=5)
        self.assertEqual(x_val.shape, x_adv_p.shape)
        x_adv = self.sess.run(x_adv_p, {x: x_val})

        new_labs = np.argmax(self.sess.run(self.model(x_adv)), axis=1)

        self.assertTrue(np.mean(orig_labs == new_labs) < 0.1) 

def test_attack_strength(self):
        """
        If clipping is not done at each iteration (not using clip_min and
        clip_max), this attack fails by
        np.mean(orig_labels == new_labels) == .5
        """
        x_val = np.random.rand(100, 2)
        x_val = np.array(x_val, dtype=np.float32)

        x_adv = self.attack.generate_np(x_val, eps=1.0, eps_iter=0.05,
                                        clip_min=0.5, clip_max=0.7,
                                        nb_iter=5)

        orig_labs = np.argmax(self.sess.run(self.model(x_val)), axis=1)
        new_labs = np.argmax(self.sess.run(self.model(x_adv)), axis=1)
        self.assertTrue(np.mean(orig_labs == new_labs) < 0.1) 

def test_generate_targeted_gives_adversarial_example(self):
        x_val = np.random.rand(100, 2)
        x_val = np.array(x_val, dtype=np.float32)

        feed_labs = np.zeros((100, 2))
        feed_labs[np.arange(100), np.random.randint(0, 1, 100)] = 1
        x = tf.placeholder(tf.float32, x_val.shape)
        y = tf.placeholder(tf.float32, feed_labs.shape)

        x_adv_p = self.attack.generate(x, max_iterations=100,
                                       binary_search_steps=3,
                                       initial_const=1,
                                       clip_min=-5, clip_max=5,
                                       batch_size=100, y_target=y)
        self.assertEqual(x_val.shape, x_adv_p.shape)
        x_adv = self.sess.run(x_adv_p, {x: x_val, y: feed_labs})

        new_labs = np.argmax(self.sess.run(self.model(x_adv)), axis=1)

        self.assertTrue(np.mean(np.argmax(feed_labs, axis=1) == new_labs)
                        > 0.9) 

def model_argmax(sess, x, predictions, samples, feed=None):
    """
    Helper function that computes the current class prediction
    :param sess: TF session
    :param x: the input placeholder
    :param predictions: the model's symbolic output
    :param samples: numpy array with input samples (dims must match x)
    :param feed: An optional dictionary that is appended to the feeding
             dictionary before the session runs. Can be used to feed
             the learning phase of a Keras model for instance.
    :return: the argmax output of predictions, i.e. the current predicted class
    """
    feed_dict = {x: samples}
    if feed is not None:
        feed_dict.update(feed)
    probabilities = sess.run(predictions, feed_dict)

    if samples.shape[0] == 1:
        return np.argmax(probabilities)
    else:
        return np.argmax(probabilities, axis=1) 

def predict(limit):
    _limit = limit if limit > 0 else 5

    td = TrainingData(LABEL_FILE, img_root=IMAGES_ROOT, mean_image_file=MEAN_IMAGE_FILE, image_property=IMAGE_PROP)
    label_def = LabelingMachine.read_label_def(LABEL_DEF_FILE)
    model = alex.Alex(len(label_def))
    serializers.load_npz(MODEL_FILE, model)

    i = 0
    for arr, im in td.generate():
        x = np.ndarray((1,) + arr.shape, arr.dtype)
        x[0] = arr
        x = chainer.Variable(np.asarray(x), volatile="on")
        y = model.predict(x)
        p = np.argmax(y.data)
        print("predict {0}, actual {1}".format(label_def[p], label_def[im.label]))
        im.image.show()
        i += 1
        if i >= _limit:
            break 

def _get_bp_indexes_labranchor(self, soi):
        """
        Get indexes of branch point regions in given sequences.

        :param soi: batch of sequences of interest for introns (intron-3..intron+6)
        :return: array of predicted bp indexes
        """
        encoded = [onehot(str(seq)[self.acc_i - 70:self.acc_i]) for seq in np.nditer(soi)]
        labr_in = np.stack(encoded, axis=0)
        out = self.labranchor.predict_on_batch(labr_in)
        # for each row, pick the base with max branchpoint probability, and get its index
        max_indexes = np.apply_along_axis(lambda x: self.acc_i - 70 + np.argmax(x), axis=1, arr=out)
        # self.write_bp(max_indexes)
        return max_indexes

# TODO boilerplate
#    def write_bp(self, max_indexes):
#        max_indexes = [str(seq) for seq in np.nditer(max_indexes)]
#        with open(''.join([this_dir, "/../customBP/example_files/bp_idx_chr21_labr.txt"]), "a") as bp_idx_file:
#            bp_idx_file.write('\n'.join(max_indexes))
#            bp_idx_file.write('\n')
#            bp_idx_file.close() 

def forward(self, x):
        N, C, H, W = x.shape
        out_h = int(1 + (H - self.pool_h) / self.stride)
        out_w = int(1 + (W - self.pool_w) / self.stride)

        col = im2col(x, self.pool_h, self.pool_w, self.stride, self.pad)
        col = col.reshape(-1, self.pool_h * self.pool_w)

        arg_max = np.argmax(col, axis=1)
        out = np.max(col, axis=1)
        out = out.reshape(N, out_h, out_w, C).transpose(0, 3, 1, 2)

        self.x = x
        self.arg_max = arg_max

        return out 

def predict_all(X, all_theta):
    rows = X.shape[0]
    params = X.shape[1]
    num_labels = all_theta.shape[0]
    
    # same as before, insert ones to match the shape
    X = np.insert(X, 0, values=np.ones(rows), axis=1)
    
    # convert to matrices
    X = np.matrix(X)
    all_theta = np.matrix(all_theta)
    
    # compute the class probability for each class on each training instance
    h = sigmoid(X * all_theta.T)
    
    # create array of the index with the maximum probability
    h_argmax = np.argmax(h, axis=1)
    
    # because our array was zero-indexed we need to add one for the true label prediction
    h_argmax = h_argmax + 1
    
    return h_argmax 

def cleaned_visual_areas(visual_areas, faces):
        '''
        mdl.cleaned_visual_areas is the same as mdl.visual_areas except that vertices with visual
        area values of 0 (boundary values) are given the mode of their neighbors.
        '''
        area_ids = np.array(visual_areas)
        boundaryNeis = {}
        for (b,inside) in [(b, set(inside))
                           for t in faces.T
                           for (bound, inside) in [([i for i in t if area_ids[i] == 0],
                                                    [i for i in t if area_ids[i] != 0])]
                           if len(bound) > 0 and len(inside) > 0
                           for b in bound]:
            if b in boundaryNeis: boundaryNeis[b] |= inside
            else:                 boundaryNeis[b] =  inside
        for (b,neis) in six.iteritems(boundaryNeis):
            area_ids[b] = np.argmax(np.bincount(area_ids[list(neis)]))
        return pimms.imm_array(np.asarray(area_ids, dtype=np.int)) 

def main():
    parser = argparse.ArgumentParser()
    parser.add_argument("path", help="Path to the CAPTCHA image file")
    parser.add_argument("--prefix", help="Checkpoint prefix [Default 'ocr']", default='ocr')
    parser.add_argument("--epoch", help="Checkpoint epoch [Default 100]", type=int, default=100)
    args = parser.parse_args()

    init_state_names, init_state_arrays = lstm_init_states(batch_size=1)
    img = read_img(args.path)

    sample = SimpleBatch(
        data_names=['data'] + init_state_names,
        data=[mx.nd.array(img)] + init_state_arrays)

    mod = load_module(args.prefix, args.epoch, sample.data_names, sample.provide_data)

    mod.forward(sample)
    prob = mod.get_outputs()[0].asnumpy()

    prediction = CtcMetrics.ctc_label(np.argmax(prob, axis=-1).tolist())
    # Predictions are 1 to 10 for digits 0 to 9 respectively (prediction 0 means no-digit)
    prediction = [p - 1 for p in prediction]
    print("Digits:", prediction)
    return 

def accuracy(self, label, pred):
        """ Simple accuracy measure: number of 100% accurate predictions divided by total number """
        hit = 0.
        total = 0.
        batch_size = label.shape[0]
        for i in range(batch_size):
            l = self._remove_blank(label[i])
            p = []
            for k in range(self.seq_len):
                p.append(np.argmax(pred[k * batch_size + i]))
            p = self.ctc_label(p)
            if len(p) == len(l):
                match = True
                for k, _ in enumerate(p):
                    if p[k] != int(l[k]):
                        match = False
                        break
                if match:
                    hit += 1.0
            total += 1.0
        assert total == batch_size
        return hit / total 

def exec_mnist(model, train_dataiter, val_dataiter):
    # print logging by default
    logging.basicConfig(level=logging.DEBUG)
    console = logging.StreamHandler()
    console.setLevel(logging.DEBUG)
    logging.getLogger('').addHandler(console)

    model.fit(X=train_dataiter,
              eval_data=val_dataiter)
    logging.info('Finish fit...')
    prob = model.predict(val_dataiter)
    logging.info('Finish predict...')
    val_dataiter.reset()
    y = np.concatenate([batch.label[0].asnumpy() for batch in val_dataiter]).astype('int')
    py = np.argmax(prob, axis=1)
    acc1 = float(np.sum(py == y)) / len(y)
    logging.info('final accuracy = %f', acc1)
    assert(acc1 > 0.94)

# run as a script 

def predict(self, Z_):
        """
        Make predictions on new dataset.

        Parameters
        ----------
        Z : array
            new data set (M samples by D features)

        Returns
        -------
        preds : array
            label predictions (M samples by 1)

        """
        # Data shape
        M, D = Z_.shape

        # If classifier is trained, check for same dimensionality
        if self.is_trained:
            if not self.train_data_dim == D:
                raise ValueError('''Test data is of different dimensionality
                                 than training data.''')

        if self.loss in ['lda', 'qda']:

            # Compute probabilities under each distribution
            probs = self.neg_log_likelihood(Z_, self.parameters)

            # Take largest probability as predictions
            preds = np.argmax(probs, axis=1)

        # Map predictions back to original labels
        preds = self.classes[preds]

        # Return predictions array
        return preds 

def predict(self, Z, zscore=False):
        """
        Make predictions on new dataset.

        Parameters
        ----------
        Z : array
            new data set (M samples x D features)
        zscore : boolean
            whether to transform the data using z-scoring (def: false)

        Returns
        -------
        preds : array
            label predictions (M samples x 1)

        """
        # If classifier is trained, check for same dimensionality
        if self.is_trained:
            if not self.train_data_dim == Z.shape[1]:
                raise ValueError("""Test data is of different dimensionality
                                 than training data.""")

        # Call predict_proba() for posterior probabilities
        probs = self.predict_proba(Z, zscore=zscore)

        # Take maximum over classes for indexing class list
        preds = self.K[np.argmax(probs, axis=1)]

        # Return predictions array
        return preds 

def predict(self, Z, zscore=False):
        """
        Make predictions on new dataset.

        Parameters
        ----------
        Z : array
            new data set (M samples x D features)
        zscore : boolean
            whether to transform the data using z-scoring (def: false)

        Returns
        -------
        preds : array
            label predictions (M samples x 1)

        """
        # If classifier is trained, check for same dimensionality
        if self.is_trained:
            if not self.train_data_dim == Z.shape[1]:
                raise ValueError("""Test data is of different dimensionality
                                 than training data.""")

        # Call predict_proba() for posterior probabilities
        probs = self.predict_proba(Z, zscore=zscore)

        # Take maximum over classes for indexing class list
        preds = self.K[np.argmax(probs, axis=1)]

        # Return predictions array
        return preds 

def predict(self, Z_):
        """
        Make predictions on new dataset.

        Parameters
        ----------
        Z : array
            new data set (M samples by D features)

        Returns
        -------
        preds : array
            label predictions (M samples by 1)

        """
        # Data shape
        M, D = Z_.shape

        # If classifier is trained, check for same dimensionality
        if self.is_trained:
            if not self.train_data_dim == D:
                raise ValueError('''Test data is of different dimensionality
                                 than training data.''')

        # Predict target labels
        preds = np.argmax(np.dot(Z_, self.theta), axis=1)

        # Map predictions back to labels
        preds = self.classes[preds]

        # Return predictions array
        return preds 

def predict(self, Z):
        """
        Make predictions on new dataset.

        Parameters
        ----------
        Z : array
            new data set (M samples by D features)

        Returns
        -------
        preds : array
            label predictions (M samples by 1)

        """
        # Data shape
        M, D = Z.shape

        # If classifier is trained, check for same dimensionality
        if self.is_trained:
            if not self.train_data_dim == D:
                raise ValueError('''Test data is of different dimensionality
                                 than training data.''')

        # Compute posteriors
        post = self.predict_proba(Z)

        # Predictions through max-posteriors
        preds = np.argmax(post, axis=1)

        # Map predictions back to original labels
        return self.classes[preds] 

def _evaluate_final(self, model, xy_test, batch_size, history):
        res = {}
        pred_test = None

        if 'val_acc' in history.history:
            res['val_acc'] = max(history.history['val_acc'])
            rev_ix = -1 - list(reversed(history.history['val_acc'])).index(res['val_acc'])
            res['val_loss'] = history.history['val_loss'][rev_ix]

        res['acc'] = history.history['acc'][-1]
        res['loss'] = history.history['loss'][-1]

        if len(xy_test[0]):
            from sklearn.metrics import classification_report, roc_auc_score
            # evaluate with test data
            x_test, y_test = xy_test
            pred_test = model.predict(x_test, batch_size=batch_size, verbose=0)
            test_loss, test_acc = model.evaluate(x_test, y_test, batch_size=batch_size, verbose=0)
            res['test_loss'] = test_loss
            res['test_acc'] = test_acc

            report = classification_report(y_true = np.argmax(y_test, axis=1),
                                           y_pred = np.argmax(pred_test, axis=1),
                                           target_names=self.labels,
                                           digits=4,
                                           output_dict=True)

            res['auc'] = roc_auc_score(y_test.astype(np.int), pred_test)

            for label in self.labels:
                stats = report[label]
                res[label+"-precision"] = stats['precision']
                res[label+"-recall"] = stats['recall']
                res[label+"-f1"] = stats['f1-score']

        return pred_test, res