Python nd.transpose方法代碼示例

# 需要導入模塊: from mxnet import nd [as 別名]
# 或者: from mxnet.nd import transpose [as 別名]
def forward(self,x):
        """
        return shape:(batch_size,2000,2)
        """
        # Encode layer
        question = x[:,0:30]
        question = self.Embed(question)
        question = self.gru(question)

        #interaction layer
        interaction = nd.dot(question,self.topic_embedding.data())
        interaction = nd.transpose(interaction,axes=(0,2,1))
        interaction = interaction.reshape((batch_size*2000,-1))
        # interaction = interaction.expand_dims(axis=1)
        # print("interaction done")

        #agg layer
        # interaction = self.pooling(self.conv_2(self.conv_1(interaction)))
        # print("agg done")
        res = self.mlp_2(self.mlp_1(interaction))
        res = res.reshape((batch_size,2000))

        return res

#Train Model 

# 需要導入模塊: from mxnet import nd [as 別名]
# 或者: from mxnet.nd import transpose [as 別名]
def __getitem__(self, idx):
        img_path = self.data_frame.iloc[idx, 0]
        img = cv2.imread(img_path, 1)
        img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)

        x, y, w, h = self.data_frame.iloc[idx, 1:5]
        l, t, ww, hh = enlarge_bbox(x, y, w, h, self.enlarge_factor)
        r, b = l + ww, t + hh

        img = img[t: b, l:r, :]
        img = cv2.resize(img, (self.img_size, self.img_size))
        img = img.astype(np.float32) - 127.5

        img = nd.transpose(nd.array(img), (2, 0, 1))

        label_path = img_path.replace('.jpg', '.mat')

        label = sio.loadmat(label_path)

        params_shape = label['Shape_Para'].astype(np.float32).ravel()
        params_exp = label['Exp_Para'].astype(np.float32).ravel()

        return img, params_shape, params_exp 

# 需要導入模塊: from mxnet import nd [as 別名]
# 或者: from mxnet.nd import transpose [as 別名]
def _convert_bbox(self, delta, anchor):
        """from loc to predict postion

        Parameters
        ----------
            delta : ndarray or np.ndarray
                network output
            anchor : np.ndarray
                generate anchor location

        Returns
        -------
            rejust predict postion though Anchor
        """
        delta = nd.transpose(delta, axes=(1, 2, 3, 0))
        delta = nd.reshape(delta, shape=(4, -1))
        delta = delta.asnumpy()
        delta[0, :] = delta[0, :] * anchor[:, 2] + anchor[:, 0]
        delta[1, :] = delta[1, :] * anchor[:, 3] + anchor[:, 1]
        delta[2, :] = np.exp(delta[2, :]) * anchor[:, 2]
        delta[3, :] = np.exp(delta[3, :]) * anchor[:, 3]
        return delta 

# 需要導入模塊: from mxnet import nd [as 別名]
# 或者: from mxnet.nd import transpose [as 別名]
def _convert_score(self, score):
        """from cls to score

        Parameters
        ----------
            score : ndarray
                network output

        Returns
        -------
            get feature map score though softmax
        """
        score = nd.transpose(score, axes=(1, 2, 3, 0))
        score = nd.reshape(score, shape=(2, -1))
        score = nd.transpose(score, axes=(1, 0))
        score = nd.softmax(score, axis=1)
        score = nd.slice_axis(score, axis=1, begin=1, end=2)
        score = nd.squeeze(score, axis=1)
        return score.asnumpy() 

# 需要導入模塊: from mxnet import nd [as 別名]
# 或者: from mxnet.nd import transpose [as 別名]
def load_data_fashion_mnist(batch_size, resize=None, root="~/.mxnet/datasets/fashion-mnist"):
    """download the fashion mnist dataest and then load into memory"""

    def transform_mnist(data, label):
        # Transform a batch of examples.
        if resize:
            n = data.shape[0]
            new_data = nd.zeros((n, resize, resize, data.shape[3]))
            for i in range(n):
                new_data[i] = image.imresize(data[i], resize, resize)
            data = new_data
        # change data from batch x height x width x channel to batch x channel x height x width
        return nd.transpose(data.astype('float32'), (0, 3, 1, 2)) / 255, label.astype('float32')

    mnist_train = gluon.data.vision.FashionMNIST(root=root, train=True, transform=None)
    mnist_test = gluon.data.vision.FashionMNIST(root=root, train=False, transform=None)
    # Transform later to avoid memory explosion.
    train_data = DataLoader(mnist_train, batch_size, shuffle=True, transform=transform_mnist)
    test_data = DataLoader(mnist_test, batch_size, shuffle=False, transform=transform_mnist)
    return (train_data, test_data) 

# 需要導入模塊: from mxnet import nd [as 別名]
# 或者: from mxnet.nd import transpose [as 別名]
def load_data_mnist(batch_size, resize=None, root="~/.mxnet/datasets/mnist"):
    """download the fashion mnist dataest and then load into memory"""

    def transform_mnist(data, label):
        # Transform a batch of examples.
        if resize:
            n = data.shape[0]
            new_data = nd.zeros((n, resize, resize, data.shape[3]))
            for i in range(n):
                new_data[i] = image.imresize(data[i], resize, resize)
            data = new_data
        # change data from batch x height x width x channel to batch x channel x height x width
        return nd.transpose(data.astype('float32'), (0, 3, 1, 2)) / 255, label.astype('float32')

    mnist_train = gluon.data.vision.MNIST(root=root, train=True, transform=None)
    mnist_test = gluon.data.vision.MNIST(root=root, train=False, transform=None)
    # Transform later to avoid memory explosion.
    train_data = DataLoader(mnist_train, batch_size, shuffle=True, transform=transform_mnist)
    test_data = DataLoader(mnist_test, batch_size, shuffle=False, transform=transform_mnist)
    return (train_data, test_data) 

# 需要導入模塊: from mxnet import nd [as 別名]
# 或者: from mxnet.nd import transpose [as 別名]
def net_define():
    net = nn.Sequential()
    with net.name_scope():
        net.add(nn.Embedding(config.MAX_WORDS, config.EMBEDDING_DIM))
        net.add(rnn.GRU(128,layout='NTC',bidirectional=True, num_layers=2, dropout=0.2))
        net.add(transpose(axes=(0,2,1)))
        # net.add(nn.MaxPool2D(pool_size=(config.MAX_LENGTH,1)))
        # net.add(nn.Conv2D(128, kernel_size=(101,1), padding=(50,0), groups=128,activation='relu'))
        net.add(PrimeConvCap(8,32, kernel_size=(1,1), padding=(0,0)))
        # net.add(AdvConvCap(8,32,8,32, kernel_size=(1,1), padding=(0,0)))
        net.add(CapFullyBlock(8*(config.MAX_LENGTH)/2, num_cap=12, input_units=32, units=16, route_num=5))
        # net.add(CapFullyBlock(8*(config.MAX_LENGTH-8), num_cap=12, input_units=32, units=16, route_num=5))
        # net.add(CapFullyBlock(8, num_cap=12, input_units=32, units=16, route_num=5))
        net.add(nn.Dropout(0.2))
        # net.add(LengthBlock())
        net.add(nn.Dense(6, activation='sigmoid'))
    net.initialize(init=init.Xavier())
    return net 

# 需要導入模塊: from mxnet import nd [as 別名]
# 或者: from mxnet.nd import transpose [as 別名]
def net_define_eu():
    net = nn.Sequential()
    with net.name_scope():
        net.add(nn.Embedding(config.MAX_WORDS, config.EMBEDDING_DIM))
        net.add(rnn.GRU(128,layout='NTC',bidirectional=True, num_layers=1, dropout=0.2))
        net.add(transpose(axes=(0,2,1)))
        net.add(nn.GlobalMaxPool1D())
        '''
        net.add(FeatureBlock1())
        '''
        net.add(extendDim(axes=3))
        net.add(PrimeConvCap(16, 32, kernel_size=(1,1), padding=(0,0),strides=(1,1)))
        net.add(CapFullyNGBlock(16, num_cap=12, input_units=32, units=16, route_num=3))
        net.add(nn.Dropout(0.2))
        net.add(nn.Dense(6, activation='sigmoid'))
    net.initialize(init=init.Xavier())
    return net 

# 需要導入模塊: from mxnet import nd [as 別名]
# 或者: from mxnet.nd import transpose [as 別名]
def forward(self, x):
        x_t = nd.transpose(x, axes=(0,2,1))
        conv3_out = self.conv3(x_t)
        conv5_out = self.conv5(conv3_out) + conv3_out
        conv7_out = self.conv7(conv5_out) + conv5_out 
        # conv_out = nd.concat(*[conv3_out, conv5_out, conv7_out], dim=1)
        conv_out = self.conv_drop(conv7_out)
        conv_max_pooled = self.conv_maxpool(conv_out)

        gru_out = self.gru(x)
        gru_out_t = nd.transpose(gru_out, axes=(0,2,1))
        # gru_pooled = nd.transpose(gru_out, axes=(0,2,1))
        # gru_maxpooled = self.gru_post_max(gru_out_t)
        # return gru_maxpooled
        # gru_avepooled = self.gru_post_ave(gru_out_t)
        # gru_pooled = nd.concat(*[gru_maxpooled, gru_avepooled], dim=1)

        # gru_pooled = nd.concat(*[gru_maxpooled, gru_avepooled], dim=1)
        gru_maxpooled = self.gru_maxpool(gru_out_t)
        # gru_avepooled = self.gru_maxpool(gru_out_t)
        # gru_pooled = nd.concat(*[gru_maxpooled, gru_avepooled], dim=1)

        # conv_ave_pooled = self.conv_avepool(conv_out)
        concated_feature = nd.concat(*[gru_maxpooled, conv_max_pooled], dim=1)
        return concated_feature 

# 需要導入模塊: from mxnet import nd [as 別名]
# 或者: from mxnet.nd import transpose [as 別名]
def transformer(data, label):
    jitter_param = 0.4
    lighting_param = 0.1
    im = data
    auglist = image.CreateAugmenter(data_shape=(3, 224, 224),
                                    rand_crop=True,
                                    rand_resize=True,
                                    rand_mirror=True,
                                    brightness=jitter_param,
                                    saturation=jitter_param,
                                    contrast=jitter_param,
                                    pca_noise=lighting_param,
                                    mean=True,
                                    std=True)

    for aug in auglist:
        im = aug(im)

    im = nd.transpose(im, (2, 0, 1))
    return im, label 

# 需要導入模塊: from mxnet import nd [as 別名]
# 或者: from mxnet.nd import transpose [as 別名]
def load_data_fashion_mnist(batch_size, resize=None, root="~/.mxnet/datasets/fashion-mnist"):
    """download the fashion mnist dataest and then load into memory"""
    def transform_mnist(data, label):
        # Transform a batch of examples.
        if resize:
            n = data.shape[0]
            new_data = nd.zeros((n, resize, resize, data.shape[3]))
            for i in range(n):
                new_data[i] = image.imresize(data[i], resize, resize)
            data = new_data
        # change data from batch x height x width x channel to batch x channel x height x width
        return nd.transpose(data.astype('float32'), (0,3,1,2))/255, label.astype('float32')

    mnist_train = gluon.data.vision.FashionMNIST(root=root, train=True, transform=None)
    mnist_test = gluon.data.vision.FashionMNIST(root=root, train=False, transform=None)
    # Transform later to avoid memory explosion. 
    train_data = DataLoader(mnist_train, batch_size, shuffle=True, transform=transform_mnist)
    test_data = DataLoader(mnist_test, batch_size, shuffle=False, transform=transform_mnist)
    return (train_data, test_data) 

# 需要導入模塊: from mxnet import nd [as 別名]
# 或者: from mxnet.nd import transpose [as 別名]
def load_data_fashion_mnist(batch_size, resize=None):
    """download the fashion mnist dataest and then load into memory"""
    def transform_mnist(data, label):
        if resize:
            # resize to resize x resize
            data = image.imresize(data, resize, resize)
        # change data from height x weight x channel to channel x height x weight
        return nd.transpose(data.astype('float32'), (2,0,1))/255, label.astype('float32')
    mnist_train = gluon.data.vision.FashionMNIST(root='./data',
        train=True, transform=transform_mnist)
    mnist_test = gluon.data.vision.FashionMNIST(root='./data',
        train=False, transform=transform_mnist)
    train_data = gluon.data.DataLoader(
        mnist_train, batch_size, shuffle=True)
    test_data = gluon.data.DataLoader(
        mnist_test, batch_size, shuffle=False)
    return (train_data, test_data) 

# 需要導入模塊: from mxnet import nd [as 別名]
# 或者: from mxnet.nd import transpose [as 別名]
def load_data_mnist(batch_size, resize=None):
    """download the fashion mnist dataest and then load into memory"""
    def transform_mnist(data, label):
        if resize:
            # resize to resize x resize
            data = image.imresize(data, resize, resize)
        # change data from height x weight x channel to channel x height x weight
        return nd.transpose(data.astype('float32'), (2,0,1))/255, label.astype('float32')
    mnist_train = gluon.data.vision.MNIST(root='./data',
        train=True, transform=transform_mnist)
    mnist_test = gluon.data.vision.MNIST(root='./data',
        train=False, transform=transform_mnist)
    train_data = gluon.data.DataLoader(
        mnist_train, batch_size, shuffle=True)
    test_data = gluon.data.DataLoader(
        mnist_test, batch_size, shuffle=False)
    return (train_data, test_data) 

# 需要導入模塊: from mxnet import nd [as 別名]
# 或者: from mxnet.nd import transpose [as 別名]
def transform(data, label):
    return nd.transpose(data.astype(np.float32), (2,0,1))/255, label.astype(np.float32) 

# 需要導入模塊: from mxnet import nd [as 別名]
# 或者: from mxnet.nd import transpose [as 別名]
def transform(data, target_wd, target_ht, is_train, box):
    """Crop and normnalize an image nd array."""
    if box is not None:
        x, y, w, h = box
        data = data[y:min(y+h, data.shape[0]), x:min(x+w, data.shape[1])]

    # Resize to target_wd * target_ht.
    data = mx.image.imresize(data, target_wd, target_ht)

    # Normalize in the same way as the pre-trained model.
    data = data.astype(np.float32) / 255.0
    data = (data - mx.nd.array([0.485, 0.456, 0.406])) / mx.nd.array([0.229, 0.224, 0.225])

    if is_train:
        if random.random() < 0.5:
            data = nd.flip(data, axis=1)
        data, _ = mx.image.random_crop(data, (224, 224))
    else:
        data, _ = mx.image.center_crop(data, (224, 224))

    # Transpose from (target_wd, target_ht, 3)
    # to (3, target_wd, target_ht).
    data = nd.transpose(data, (2, 0, 1))

    # If image is greyscale, repeat 3 times to get RGB image.
    if data.shape[0] == 1:
        data = nd.tile(data, (3, 1, 1))
    return data.reshape((1,) + data.shape)