Python imagenet_utils.preprocess_input方法代碼示例

# 需要導入模塊: from keras.applications import imagenet_utils [as 別名]
# 或者: from keras.applications.imagenet_utils import preprocess_input [as 別名]
def __getitem__(self, idx):
        images, masks = [], []

        for (image_path, mask_path) in zip(self.image_path_list[idx * self.batch_size: (idx + 1) * self.batch_size],
                                           self.mask_path_list[idx * self.batch_size: (idx + 1) * self.batch_size]):
            image = cv2.imread(image_path, 1)
            mask = cv2.imread(mask_path, 0)

            image = self._padding(image)
            mask = self._padding(mask)

            # augumentation
            augmentation = self.transformer(image=image, mask=mask)
            image = augmentation['image']
            mask = self._get_result_map(augmentation['mask'])

            images.append(image)
            masks.append(mask)

        images = np.array(images)
        masks = np.array(masks)
        images = pinput(images)

        return images, masks 

# 需要導入模塊: from keras.applications import imagenet_utils [as 別名]
# 或者: from keras.applications.imagenet_utils import preprocess_input [as 別名]
def display_heatmap(new_model, img_path, ids, preprocessing=None):
    # The quality is reduced.
    # If you have more than 8GB of RAM, you can try to increase it.
    img = image.load_img(img_path, target_size=(800, 1280))
    x = image.img_to_array(img)
    x = np.expand_dims(x, axis=0)
    if preprocessing is not None:
        x = preprocess_input(x)

    out = new_model.predict(x)

    heatmap = out[0]  # Removing batch axis.

    if K.image_data_format() == 'channels_first':
        heatmap = heatmap[ids]
        if heatmap.ndim == 3:
            heatmap = np.sum(heatmap, axis=0)
    else:
        heatmap = heatmap[:, :, ids]
        if heatmap.ndim == 3:
            heatmap = np.sum(heatmap, axis=2)

    plt.imshow(heatmap, interpolation="none")
    plt.show() 

# 需要導入模塊: from keras.applications import imagenet_utils [as 別名]
# 或者: from keras.applications.imagenet_utils import preprocess_input [as 別名]
def helper_test(model):
    img_path = "../examples/dog.jpg"
    new_model = to_heatmap(model)

    # Loading the image
    img = image.load_img(img_path, target_size=(800, 800))
    x = image.img_to_array(img)
    x = np.expand_dims(x, axis=0)
    x = preprocess_input(x)

    out = new_model.predict(x)

    s = "n02084071"  # Imagenet code for "dog"
    ids = synset_to_dfs_ids(s)
    heatmap = out[0]
    if K.image_data_format() == 'channels_first':
        heatmap = heatmap[ids]
        heatmap = np.sum(heatmap, axis=0)
    else:
        heatmap = heatmap[:, :, ids]
        heatmap = np.sum(heatmap, axis=2)
    print(heatmap.shape)
    assert heatmap.shape[0] == heatmap.shape[1]
    K.clear_session() 

# 需要導入模塊: from keras.applications import imagenet_utils [as 別名]
# 或者: from keras.applications.imagenet_utils import preprocess_input [as 別名]
def test_preprocess_input():
    # Test image batch
    x = np.random.uniform(0, 255, (2, 10, 10, 3))
    assert utils.preprocess_input(x).shape == x.shape

    out1 = utils.preprocess_input(x, 'channels_last')
    out2 = utils.preprocess_input(np.transpose(x, (0, 3, 1, 2)),
                                  'channels_first')
    assert_allclose(out1, out2.transpose(0, 2, 3, 1))

    # Test single image
    x = np.random.uniform(0, 255, (10, 10, 3))
    assert utils.preprocess_input(x).shape == x.shape

    out1 = utils.preprocess_input(x, 'channels_last')
    out2 = utils.preprocess_input(np.transpose(x, (2, 0, 1)),
                                  'channels_first')
    assert_allclose(out1, out2.transpose(1, 2, 0)) 

# 需要導入模塊: from keras.applications import imagenet_utils [as 別名]
# 或者: from keras.applications.imagenet_utils import preprocess_input [as 別名]
def image_batch_preprocess(imgBatch, params, meanVals):
    """
    Apply preprocessing operations to the image data that also need to be applied during inference
    :param imgBatch: numpy array containing image data
    :param params: input parameters from params.py
    :param meanVals: used for mean subtraction if non-rgb imagery
    :return: numpy array containing preprocessed image data
    """
    if params.NUM_CHANNELS==3:
        imgBatch  = imagenet_utils.preprocess_input(imgBatch)
        imgBatch = imgBatch / 255.0
    else:
        for c in range(params.NUM_CATEGORIES):
            imgBatch[:,:,:,c] -= meanVals[c]
        imgBatch = imgBatch / params.MAX_VAL
    return imgBatch 

# 需要導入模塊: from keras.applications import imagenet_utils [as 別名]
# 或者: from keras.applications.imagenet_utils import preprocess_input [as 別名]
def preprocess(self, raw_inputs):
        """
        Args:
            raw_inputs (list of Images): a list of PIL Image objects
        Returns:
            array (float32): num images * height * width * num channels
        """
        image_arrays = []
        for raw_im in raw_inputs:
            im = raw_im.resize(VGG16_DIM[:2], Image.ANTIALIAS)
            im = im.convert('RGB')
            arr = np.array(im).astype('float32')
            image_arrays.append(arr)

        all_raw_inputs = np.array(image_arrays)
        return imagenet_utils.preprocess_input(all_raw_inputs) 

# 需要導入模塊: from keras.applications import imagenet_utils [as 別名]
# 或者: from keras.applications.imagenet_utils import preprocess_input [as 別名]
def preprocess_input(x):
    """Preprocesses a numpy array encoding a batch of images.

    This function applies the "Inception" preprocessing which converts
    the RGB values from [0, 255] to [-1, 1]. Note that this preprocessing
    function is different from `imagenet_utils.preprocess_input()`.

    # Arguments
        x: a 4D numpy array consists of RGB values within [0, 255].

    # Returns
        Preprocessed array.
    """
    x /= 128.
    x -= 1.
    return x.astype(np.float32) 

# 需要導入模塊: from keras.applications import imagenet_utils [as 別名]
# 或者: from keras.applications.imagenet_utils import preprocess_input [as 別名]
def preprocess_input(x):
    """Preprocesses a numpy array encoding a batch of images.

    # Arguments
        x: a 4D numpy array consists of RGB values within [0, 255].

    # Returns
        Preprocessed array.
    """
    return imagenet_utils.preprocess_input(x, mode='tf') 

# 需要導入模塊: from keras.applications import imagenet_utils [as 別名]
# 或者: from keras.applications.imagenet_utils import preprocess_input [as 別名]
def data_loader(q, ):
    for start in tqdm(range(0, len(filenames), batch_size)):
        x_batch = []
        end = min(start + batch_size, len(filenames))
        filenames_batch = filenames[start:end]

        for filename in filenames_batch:
            img = load_img(filename)

            stacked_channels = []
            for i in range(args.stacked_channels):
                channel_path = os.path.join(args.stacked_channels_dir,
                                            str(i),
                                            filename.split('/')[-1].replace('.jpg', '.png'))
                stacked_channel = load_img(channel_path, grayscale=True)
                stacked_channels.append(stacked_channel)
            stacked_img = np.dstack((img, *stacked_channels))

            x_batch.append(img_to_array(stacked_img))


        x_batch = preprocess_input(np.array(x_batch, np.float32), mode=args.preprocessing_function)
        if args.pred_tta:
            x_batch = do_tta(x_batch, args.pred_tta)
        padded_x = np.zeros((batch_size, 1280, 1920, args.stacked_channels + 3))
        padded_x[:, :, 1:-1, :] = x_batch
        q.put((filenames_batch, padded_x))

    for gpu in gpus:
        q.put((None, None)) 

# 需要導入模塊: from keras.applications import imagenet_utils [as 別名]
# 或者: from keras.applications.imagenet_utils import preprocess_input [as 別名]
def build_batch_generator(filenames, img_dir=None, batch_size=None,
                          shuffle=False, transformations=None,
                          out_size=None, crop_size=None, mask_dir=None, aug=False):
    mask_function = ImageWithMaskFunction(out_size=out_size, crop_size=crop_size, mask_dir=mask_dir)

    while True:
        # @TODO: Should we fixate the seed here?
        if shuffle:
            filenames = sklearn.utils.shuffle(filenames)

        for start in range(0, len(filenames), batch_size):
            batch_x = []
            end = min(start + batch_size, len(filenames))
            train_batch = filenames[start:end]

            for filename in train_batch:
                img = imread(os.path.join(img_dir, filename))

                stacked_channels = []
                for i in range(args.stacked_channels):
                    channel_path = os.path.join(args.stacked_channels_dir,
                                                str(i),
                                                filename.replace('.jpg', '.png'))
                    stacked_channel = imread(channel_path, mode='L')
                    stacked_channels.append(stacked_channel)
                stacked_img = np.dstack((img, *stacked_channels))
                batch_x.append(stacked_img)

            batch_x = np.array(batch_x, np.float32)
            batch_x, masks = mask_function.mask_pred(batch_x, train_batch, range(batch_size), aug)

            if crop_size is None:
                # @TODO: Remove hardcoded padding
                batch_x, masks = pad(batch_x, 1, 0), pad(masks, 1, 0)

            yield imagenet_utils.preprocess_input(batch_x, mode=args.preprocessing_function), masks 

# 需要導入模塊: from keras.applications import imagenet_utils [as 別名]
# 或者: from keras.applications.imagenet_utils import preprocess_input [as 別名]
def predict():
    output_dir = args.pred_mask_dir
    model = make_model((None, None, 3))
    model.load_weights(args.weights)
    batch_size = args.pred_batch_size
    nbr_test_samples = 100064

    filenames = [os.path.join(args.test_data_dir, f) for f in sorted(os.listdir(args.test_data_dir))]

    start_time = clock()
    for i in range(int(nbr_test_samples / batch_size) + 1):
        x = []
        for j in range(batch_size):
            if i * batch_size + j < len(filenames):
                img = load_img(filenames[i * batch_size + j], target_size=(args.img_height, args.img_width))
                x.append(img_to_array(img))
        x = np.array(x)
        x = preprocess_input(x, args.preprocessing_function)
        x = do_tta(x, args.pred_tta)
        batch_x = np.zeros((x.shape[0], 1280, 1920, 3))
        batch_x[:, :, 1:-1, :] = x
        preds = model.predict_on_batch(batch_x)
        preds = undo_tta(preds, args.pred_tta)
        for j in range(batch_size):
            filename = filenames[i * batch_size + j]
            prediction = preds[j][:, 1:-1, :]
            array_to_img(prediction * 255).save(os.path.join(output_dir, filename.split('/')[-1][:-4] + ".png"))
        time_spent = clock() - start_time
        print("predicted batch ", str(i))
        print("Time spent: {:.2f}  seconds".format(time_spent))
        print("Speed: {:.2f}  ms per image".format(time_spent / (batch_size * (i + 1)) * 1000))
        print("Elapsed: {:.2f} hours  ".format(time_spent / (batch_size * (i + 1)) / 3600 * (nbr_test_samples - (batch_size * (i + 1))))) 

# 需要導入模塊: from keras.applications import imagenet_utils [as 別名]
# 或者: from keras.applications.imagenet_utils import preprocess_input [as 別名]
def _load_image_from_uri(local_uri):
    img = (PIL.Image
           .open(local_uri)
           .convert('RGB')
           .resize((299, 299), PIL.Image.ANTIALIAS))
    img_arr = np.array(img).astype(np.float32)
    img_tnsr = preprocess_input(img_arr[np.newaxis, :])
    return img_tnsr 

# 需要導入模塊: from keras.applications import imagenet_utils [as 別名]
# 或者: from keras.applications.imagenet_utils import preprocess_input [as 別名]
def load_image(path):
    img = image.load_img(path, target_size=(224,224))
    x = image.img_to_array(img)
    x = np.expand_dims(x, axis=0)
    x = preprocess_input(x)
    return np.asarray(x) 

# 需要導入模塊: from keras.applications import imagenet_utils [as 別名]
# 或者: from keras.applications.imagenet_utils import preprocess_input [as 別名]
def preprocess_input(x):
    """Preprocesses a numpy array encoding a batch of images.
    # Arguments
        x: a 4D numpy array consists of RGB values within [0, 255].
    # Returns
        Preprocessed array.
    """
    return imagenet_utils.preprocess_input(x, mode='tf') 

# 需要導入模塊: from keras.applications import imagenet_utils [as 別名]
# 或者: from keras.applications.imagenet_utils import preprocess_input [as 別名]
def preprocess_input(x):
    """Preprocesses a numpy array encoding a batch of images.
    # Arguments
        x: a 4D numpy array consists of RGB values within [0, 255].
    # Returns
        Input array scaled to [-1.,1.]
    """
    return imagenet_utils.preprocess_input(x, mode='tf')