predict_with_folders.py

import argparse
import logging
import os

import numpy as np
import torch
import torch.nn.functional as F
from PIL import Image
from torchvision import transforms

from utils.data_loading import BasicDataset
from unet import UNet
from utils.utils import plot_img_and_mask


def predict_img(net,
                full_img,
                device,
                out_threshold=0.5):
    net.eval()
    img = torch.from_numpy(BasicDataset.preprocess(None, full_img, is_mask=False))
    img = img.unsqueeze(0)
    img = img.to(device=device, dtype=torch.float32)

    with torch.no_grad():
        output = net(img).cpu()
        output = F.interpolate(output, (full_img.size[1], full_img.size[0]), mode='bilinear')
        if net.n_classes > 1:
            mask = output.argmax(dim=1)
        else:
            mask = torch.sigmoid(output) > out_threshold

    return mask[0].long().squeeze().numpy()


def get_args():
    parser = argparse.ArgumentParser(description='Predict masks from input images')
    parser.add_argument('--model', '-m', default='checkpoints/checkpoint_epoch200.pth', metavar='FILE',
                        help='Specify the file in which the model is stored')
    parser.add_argument('--input', '-i', metavar='INPUT', nargs='+', help='Filenames of input images',default="test/test2_img/")  # test/test2_img/
    parser.add_argument('--output', '-o', metavar='OUTPUT', nargs='+', help='Filenames of output images')
    parser.add_argument('--viz', '-v', action='store_true',
                        help='Visualize the images as they are processed')
    parser.add_argument('--no-save', '-n', action='store_true', help='Do not save the output masks')
    parser.add_argument('--mask-threshold', '-t', type=float, default=0.5,
                        help='Minimum probability value to consider a mask pixel white')
    parser.add_argument('--bilinear', action='store_true', default=False, help='Use bilinear upsampling')
    parser.add_argument('--classes', '-c', type=int, default=2, help='Number of classes')

    return parser.parse_args()


def get_output_filenames(args):
    def _generate_name(fn):
        print(os.path.splitext(fn)[0])
        return f'{os.path.splitext(fn)[0]}_OUT.png'

    return args.output or list(map(_generate_name, args.input))

def get_output_filenames_byfolder(imgs_list):  # 输入是一个列表 输出也是一个列表 作用是

    # save_mask_folder = './test/test1_label_in_premask'
    save_mask_folder = './test/test2_label_in_premask'
    if not os.path.exists(save_mask_folder):
        os.makedirs(save_mask_folder)
    out_put_imglist = [os.path.join(save_mask_folder,i.split('.')[0]+"_mask.png") for i in imgs_list]

    return out_put_imglist


def mask_to_image(mask: np.ndarray, mask_values):
    if isinstance(mask_values[0], list):
        out = np.zeros((mask.shape[-2], mask.shape[-1], len(mask_values[0])), dtype=np.uint8)
    elif mask_values == [0, 1]:
        out = np.zeros((mask.shape[-2], mask.shape[-1]), dtype=bool)
    else:
        out = np.zeros((mask.shape[-2], mask.shape[-1]), dtype=np.uint8)

    if mask.ndim == 3:
        mask = np.argmax(mask, axis=0)

    for i, v in enumerate(mask_values):
        out[mask == i] = v

    return Image.fromarray(out)


if __name__ == '__main__':
    args = get_args()
    logging.basicConfig(level=logging.INFO, format='%(levelname)s: %(message)s')

    in_files_folder = args.input  # 这里如果传一个文件夹进来 就是要预测一个文件夹下的图片 且传进来是['test/test_sub/']的格式

    all_files = os.listdir(in_files_folder)  # ['P48-0187.png','P48-0020.png']
    all_files_path = [os.path.join(in_files_folder,i) for i in all_files]  # ['test/test_sub/P48-0187.png'....]
    out_files = get_output_filenames_byfolder(all_files)

    net = UNet(n_channels=1, n_classes=args.classes, bilinear=args.bilinear)

    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
    logging.info(f'Loading model {args.model}')
    logging.info(f'Using device {device}')

    net.to(device=device)
    state_dict = torch.load(args.model, map_location=device)
    mask_values = state_dict.pop('mask_values', [0, 1])
    net.load_state_dict(state_dict)

    logging.info('Model loaded!')

    for i, filename in enumerate(all_files_path):
        logging.info(f'Predicting image {filename} ...')
        img = Image.open(filename)
        ############################
        temp_img = np.array(img)  # 为了解决可视化原图出来是纯白的
        #########################
        mask = predict_img(net=net,
                           full_img=img,
                           out_threshold=args.mask_threshold,
                           device=device)

        if not args.no_save:
            out_filename = out_files[i]
            result = mask_to_image(mask, mask_values)
            result.save(out_filename)
            logging.info(f'Mask saved to {out_filename}')

        if args.viz:
            logging.info(f'Visualizing results for image {filename}, close to continue...')
            plot_img_and_mask(temp_img, mask)