Python image.resize方法代码示例

# 需要导入模块: from utils import image [as 别名]
# 或者: from utils.image import resize [as 别名]
def loadImageAndTarget(sample, augmentation):

    # Load image
    img = image.openImage(sample[0], cfg.IM_DIM)

    # Resize Image
    img = image.resize(img, cfg.IM_SIZE[0], cfg.IM_SIZE[1], mode=cfg.RESIZE_MODE)

    # Do image Augmentation
    if augmentation:
        img = image.augment(img, cfg.IM_AUGMENTATION, cfg.AUGMENTATION_COUNT, cfg.AUGMENTATION_PROBABILITY)

    # Prepare image for net input
    img = image.normalize(img, cfg.ZERO_CENTERED_NORMALIZATION)
    img = image.prepare(img)

    # Get target
    label = sample[1]
    index = cfg.CLASSES.index(label)
    target = np.zeros((len(cfg.CLASSES)), dtype='float32')
    target[index] = 1.0

    return img, target    

#################### BATCH HANDLING ##################### 

# 需要导入模块: from utils import image [as 别名]
# 或者: from utils.image import resize [as 别名]
def getSpecBatches(split):

    # Random Seed
    random = cfg.getRandomState()

    # Make predictions for every testfile
    for t in split:

        # Spec batch
        spec_batch = []

        # Keep track of timestamps
        pred_start = 0

        # Get specs for file
        for spec in audio.specsFromFile(t[0],
                                        cfg.SAMPLE_RATE,
                                        cfg.SPEC_LENGTH,
                                        cfg.SPEC_OVERLAP,
                                        cfg.SPEC_MINLEN,
                                        shape=(cfg.IM_SIZE[1], cfg.IM_SIZE[0]),
                                        fmin=cfg.SPEC_FMIN,
                                        fmax=cfg.SPEC_FMAX):

            # Resize spec
            spec = image.resize(spec, cfg.IM_SIZE[0], cfg.IM_SIZE[1], mode=cfg.RESIZE_MODE)

            # Normalize spec
            spec = image.normalize(spec, cfg.ZERO_CENTERED_NORMALIZATION)

            # Prepare as input
            spec = image.prepare(spec)

            # Add to batch
            if len(spec_batch) > 0:
                spec_batch = np.vstack((spec_batch, spec))
            else:
                spec_batch = spec

            # Batch too large?
            if spec_batch.shape[0] >= cfg.MAX_SPECS_PER_FILE:
                break

            # Do we have enough specs for a prediction?
            if len(spec_batch) >= cfg.SPECS_PER_PREDICTION:

                # Calculate next timestamp
                pred_end = pred_start + cfg.SPEC_LENGTH + ((len(spec_batch) - 1) * (cfg.SPEC_LENGTH - cfg.SPEC_OVERLAP))
                
                # Store prediction
                ts = getTimestamp(int(pred_start), int(pred_end))

                # Advance to next timestamp
                pred_start = pred_end - cfg.SPEC_OVERLAP

                yield spec_batch, t[1], ts, t[0].split(os.sep)[-1]

                # Spec batch
                spec_batch = [] 

# 需要导入模块: from utils import image [as 别名]
# 或者: from utils.image import resize [as 别名]
def getSpecBatches(split):

    # Random Seed
    random = cfg.getRandomState()

    # Make predictions for every testfile
    for t in split:

        # Spec batch
        spec_batch = []

        # Get specs for file
        for spec in audio.specsFromFile(t[0],
                                        cfg.SAMPLE_RATE,
                                        cfg.SPEC_LENGTH,
                                        cfg.SPEC_OVERLAP,
                                        cfg.SPEC_MINLEN,
                                        shape=(cfg.IM_SIZE[1], cfg.IM_SIZE[0]),
                                        fmin=cfg.SPEC_FMIN,
                                        fmax=cfg.SPEC_FMAX,
                                        spec_type=cfg.SPEC_TYPE):

            # Resize spec
            spec = image.resize(spec, cfg.IM_SIZE[0], cfg.IM_SIZE[1], mode=cfg.RESIZE_MODE)

            # Normalize spec
            spec = image.normalize(spec, cfg.ZERO_CENTERED_NORMALIZATION)

            # Prepare as input
            spec = image.prepare(spec)

            # Add to batch
            if len(spec_batch) > 0:
                spec_batch = np.vstack((spec_batch, spec))
            else:
                spec_batch = spec

            # Batch too large?
            if spec_batch.shape[0] >= cfg.MAX_SPECS_PER_FILE:
                break

        # No specs?
        if len(spec_batch) == 0:
            spec = random.normal(0.0, 1.0, (cfg.IM_SIZE[1], cfg.IM_SIZE[0]))
            spec_batch = image.prepare(spec)

        # Shuffle spec batch
        spec_batch = shuffle(spec_batch, random_state=random)

        # yield batch, labels and filename
        yield spec_batch[:cfg.MAX_SPECS_PER_FILE], t[1], t[0].split(os.sep)[-1] 

# 需要导入模块: from utils import image [as 别名]
# 或者: from utils.image import resize [as 别名]
def main():
    # get symbol
    pprint.pprint(config)
    sym_instance = eval(config.symbol + '.' + config.symbol)()
    sym = sym_instance.get_symbol(config, is_train=False)

    # load demo data
    image_names = ['000240.jpg', '000437.jpg', '004072.jpg', '007912.jpg']
    image_all = []
    data = []
    for im_name in image_names:
        assert os.path.exists(cur_path + '/../demo/deform_conv/' + im_name), \
            ('%s does not exist'.format('../demo/deform_conv/' + im_name))
        im = cv2.imread(cur_path + '/../demo/deform_conv/' + im_name, cv2.IMREAD_COLOR | cv2.IMREAD_IGNORE_ORIENTATION)
        image_all.append(im)
        target_size = config.SCALES[0][0]
        max_size = config.SCALES[0][1]
        im, im_scale = resize(im, target_size, max_size, stride=config.network.IMAGE_STRIDE)
        im_tensor = transform(im, config.network.PIXEL_MEANS)
        im_info = np.array([[im_tensor.shape[2], im_tensor.shape[3], im_scale]], dtype=np.float32)
        data.append({'data': im_tensor, 'im_info': im_info})

    # get predictor
    data_names = ['data', 'im_info']
    label_names = []
    data = [[mx.nd.array(data[i][name]) for name in data_names] for i in xrange(len(data))]
    max_data_shape = [[('data', (1, 3, max([v[0] for v in config.SCALES]), max([v[1] for v in config.SCALES])))]]
    provide_data = [[(k, v.shape) for k, v in zip(data_names, data[i])] for i in xrange(len(data))]
    provide_label = [None for i in xrange(len(data))]
    arg_params, aux_params = load_param(cur_path + '/../model/deform_conv', 0, process=True)
    predictor = Predictor(sym, data_names, label_names,
                          context=[mx.gpu(0)], max_data_shapes=max_data_shape,
                          provide_data=provide_data, provide_label=provide_label,
                          arg_params=arg_params, aux_params=aux_params)

    # test
    for idx, _ in enumerate(image_names):
        data_batch = mx.io.DataBatch(data=[data[idx]], label=[], pad=0, index=idx,
                                     provide_data=[[(k, v.shape) for k, v in zip(data_names, data[idx])]],
                                     provide_label=[None])

        output = predictor.predict(data_batch)
        res5a_offset = output[0]['res5a_branch2b_offset_output'].asnumpy()
        res5b_offset = output[0]['res5b_branch2b_offset_output'].asnumpy()
        res5c_offset = output[0]['res5c_branch2b_offset_output'].asnumpy()

        im = image_all[idx]
        im = cv2.cvtColor(im, cv2.COLOR_BGR2RGB)
        show_dconv_offset(im, [res5c_offset, res5b_offset, res5a_offset]) 

# 需要导入模块: from utils import image [as 别名]
# 或者: from utils.image import resize [as 别名]
def main():
    # get symbol
    pprint.pprint(config)
    sym_instance = eval(config.symbol + '.' + config.symbol)()
    sym = sym_instance.get_symbol_rfcn(config, is_train=False)

    # load demo data
    image_names = ['000057.jpg', '000149.jpg', '000351.jpg', '002535.jpg']
    image_all = []
    # ground truth boxes
    gt_boxes_all = [np.array([[132, 52, 384, 357]]), np.array([[113, 1, 350, 360]]),
                    np.array([[0, 27, 329, 155]]), np.array([[8, 40, 499, 289]])]
    gt_classes_all = [np.array([3]), np.array([16]), np.array([7]), np.array([12])]
    data = []
    for idx, im_name in enumerate(image_names):
        assert os.path.exists(cur_path + '/../demo/deform_psroi/' + im_name), \
            ('%s does not exist'.format('../demo/deform_psroi/' + im_name))
        im = cv2.imread(cur_path + '/../demo/deform_psroi/' + im_name, cv2.IMREAD_COLOR | cv2.IMREAD_IGNORE_ORIENTATION)
        image_all.append(im)
        target_size = config.SCALES[0][0]
        max_size = config.SCALES[0][1]
        im, im_scale = resize(im, target_size, max_size, stride=config.network.IMAGE_STRIDE)
        im_tensor = transform(im, config.network.PIXEL_MEANS)
        gt_boxes = gt_boxes_all[idx]
        gt_boxes = np.round(gt_boxes * im_scale)
        data.append({'data': im_tensor, 'rois': np.hstack((np.zeros((gt_boxes.shape[0], 1)), gt_boxes))})

    # get predictor
    data_names = ['data', 'rois']
    label_names = []
    data = [[mx.nd.array(data[i][name]) for name in data_names] for i in xrange(len(data))]
    max_data_shape = [[('data', (1, 3, max([v[0] for v in config.SCALES]), max([v[1] for v in config.SCALES])))]]
    provide_data = [[(k, v.shape) for k, v in zip(data_names, data[i])] for i in xrange(len(data))]
    provide_label = [None for i in xrange(len(data))]
    arg_params, aux_params = load_param(cur_path + '/../model/deform_psroi', 0, process=True)
    predictor = Predictor(sym, data_names, label_names,
                          context=[mx.gpu(0)], max_data_shapes=max_data_shape,
                          provide_data=provide_data, provide_label=provide_label,
                          arg_params=arg_params, aux_params=aux_params)

    # test
    for idx, _ in enumerate(image_names):
        data_batch = mx.io.DataBatch(data=[data[idx]], label=[], pad=0, index=idx,
                                     provide_data=[[(k, v.shape) for k, v in zip(data_names, data[idx])]],
                                     provide_label=[None])

        output = predictor.predict(data_batch)
        cls_offset = output[0]['rfcn_cls_offset_output'].asnumpy()

        im = image_all[idx]
        im = cv2.cvtColor(im, cv2.COLOR_BGR2RGB)
        boxes = gt_boxes_all[idx]
        show_dpsroi_offset(im, boxes, cls_offset, gt_classes_all[idx])