def proceed_validation(args, is_save=True, is_densecrf=False):
import cv2
#name = "ningbo_val"
name = "val"
ds = dataset.PSSD(args.base_dir, args.meta_dir, name)
ds = BatchData(ds, 1)
pred_config = PredictConfig(model=Model(),
session_init=get_model_loader(args.load),
input_names=['image'],
output_names=['prob'])
predictor = OfflinePredictor(pred_config)
from tensorpack.utils.fs import mkdir_p
result_dir = "result/pssd_apr26"
#result_dir = "ningbo_validation"
mkdir_p(result_dir)
i = 1
stat = MIoUStatistics(CLASS_NUM)
logger.info("start validation....")
for image, label in tqdm(ds.get_data()):
label = np.squeeze(label)
image = np.squeeze(image)
def mypredictor(input_img):
#input image: 1*H*W*3
#output : H*W*C
output = predictor(input_img)
return output[0][0]
prediction = predict_scaler(image,
mypredictor,
scales=[0.5, 0.75, 1, 1.25, 1.5],
classes=CLASS_NUM,
tile_size=CROP_SIZE,
is_densecrf=is_densecrf)
prediction = np.argmax(prediction, axis=2)
stat.feed(prediction, label)
if is_save:
cv2.imwrite(
os.path.join(result_dir, "{}.png".format(i)),
np.concatenate((image, visualize_label(label),
visualize_label(prediction)),
axis=1))
#imwrite_grid(image,label,prediction, border=512, prefix_dir=result_dir, imageId = i)
i += 1
logger.info("mIoU: {}".format(stat.mIoU))
logger.info("mean_accuracy: {}".format(stat.mean_accuracy))
logger.info("accuracy: {}".format(stat.accuracy))
def get_data(name, base_dir, meta_dir, batch_size):
isTrain = True if 'train' in name else False
ds = dataset.PSSD(base_dir, meta_dir, name, shuffle=True)
if isTrain: #special augmentation
shape_aug = [
imgaug.RandomResize(xrange=(0.7, 1.5),
yrange=(0.7, 1.5),
aspect_ratio_thres=0.15),
RandomCropWithPadding(CROP_SIZE, IGNORE_LABEL),
imgaug.Flip(horiz=True),
]
else:
shape_aug = []
ds = AugmentImageComponents(ds, shape_aug, (0, 1), copy=False)
if isTrain:
ds = BatchData(ds, batch_size)
ds = PrefetchDataZMQ(ds, 1)
else:
ds = BatchData(ds, 1)
return ds