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 generate_trimap_pascal(rador=1):
#main_img_dir = "/data_a/dataset/cityscapes"
#meta_txt = "cityscapes"
main_img_dir = "/data_a/dataset/pascalvoc2012/VOC2012trainval/VOCdevkit/VOC2012"
meta_txt = "pascalvoc12"
from tensorpack.utils.fs import mkdir_p
trimap_dir = os.path.join(main_img_dir, "trimap_gt{}".format(rador))
mkdir_p(trimap_dir)
print(trimap_dir)
f = open(os.path.join(meta_txt, "train.txt"))
result_f = open(
os.path.join(meta_txt, "train_tripmap{}.txt".format(rador)), "w")
lines = f.readlines()
from tqdm import tqdm
for l in tqdm(lines):
l = l.strip("\n")
img_dir, label_dir = l.split(" ")
img = cv2.imread(os.path.join(main_img_dir, img_dir))
label = cv2.imread(os.path.join(main_img_dir, label_dir), 0)
new_label = label.copy()
basename = os.path.basename(label_dir)
#edge = cv2.Canny(label, 100, 200).astype("float32")
#xs,ys = np.where(edge==255)
w, h = label.shape
for x in range(w):
for y in range(h):
if is_edge(x, y, label):
new_label[x - rador:x + rador, y - rador:y + rador] = 255
tripmap_name = os.path.join(trimap_dir, basename)
cv2.imshow("im", img / 255.0)
cv2.imshow("raw-originlabel", label)
cv2.imshow("color-originlabel", visualize_label(label))
cv2.imshow("raw-newlabel", new_label)
cv2.imshow("color-newlabel", visualize_label(new_label))
cv2.waitKey(0)
#cv2.imwrite(tripmap_name, new_label)
result_f.write("{} {}\n".format(img_dir, tripmap_name))
f.close()
result_f.close()
def view_data(base_dir, meta_dir, batch_size):
ds = RepeatedData(get_data('train', base_dir, meta_dir, batch_size), -1)
ds.reset_state()
for ims, labels in ds.get_data():
for im, label in zip(ims, labels):
#aa = visualize_label(label)
#pass
cv2.imshow("im", im / 255.0)
cv2.imshow("raw-label", label)
cv2.imshow("color-label", visualize_label(label))
cv2.waitKey(0)
def proceed(detection_json):
_coco = COCO(detection_json)
result = _coco.getCatIds()
catToImgs = _coco.catToImgs
imgToAnns = _coco.imgToAnns
img_ids_set = set()
for id, coco_id in enumerate(voc_ids_list):
img_ids_set = img_ids_set | set(catToImgs[coco_id])
img_ids_list = list(img_ids_set)
for img_id in tqdm(img_ids_list[1:]):
img = _coco.loadImgs(img_id)[0]
origin_img = cv2.imread(os.path.join(val_dir, img['file_name']))
annIds = _coco.getAnnIds(imgIds=img_id)
img_mask = np.zeros((img['height'], img['width'], 1), dtype=np.uint8)
for annId in annIds:
ann = _coco.loadAnns(annId)[0]
if ann['category_id'] in voc_ids_set:
# polygon
if type(ann['segmentation']) == list:
for _instance in ann['segmentation']:
rle = mask.frPyObjects([_instance], img['height'],
img['width'])
# mask
else: # mostly is aeroplane
if type(ann['segmentation']['counts']) == list:
rle = mask.frPyObjects([ann['segmentation']],
img['height'], img['width'])
else:
rle = [ann['segmentation']]
m = mask.decode(rle)
img_mask[np.where(
m == 1)] = coco_to_voc_dict[ann['category_id']]
f.write("{} {}\n".format(
os.path.join(train_prefix_dir, img['file_name']),
os.path.join(val_prefix_dir,
img['file_name'].replace("jpg", "png"))))
cv2.imwrite(
os.path.join(pasalvoc_root, train_prefix_dir, img['file_name']),
origin_img)
cv2.imwrite(
os.path.join(pasalvoc_root, val_prefix_dir,
img['file_name'].replace("jpg", "png")),
img_mask[:, :, 0]) #single channel
if False:
cv2.imwrite("cv.jpg", origin_img)
cv2.imwrite("mask.jpg", img_mask)
cv2.imshow("im", origin_img)
cv2.imshow("color-label", visualize_label(img_mask[:, :, 0]))
cv2.waitKey(0)
def vis_seg(imgs, labels, waitkey=10000):
import cv2
from tensorpack.utils.segmentation.segmentation import predict_slider, visualize_label, predict_scaler
img = torchvision.utils.make_grid(imgs).numpy()
img = np.transpose(img, (1, 2, 0))
img = img[:, :, ::-1] + 128
label = torchvision.utils.make_grid(labels.unsqueeze(1)).numpy()
label = np.transpose(label, (1, 2, 0))
# plt.imshow(img)
# plt.show()
cv2.imshow("source image", img.astype(np.uint8))
cv2.imshow("source label", visualize_label(label[:, :, 0]))
cv2.waitKey(waitkey)
def proceed_test_dir(args):
import cv2
ll = os.listdir(args.test_dir)
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 = "test-from-dir"
visual_dir = os.path.join(result_dir, "visualization")
final_dir = os.path.join(result_dir, "final")
import shutil
shutil.rmtree(result_dir, ignore_errors=True)
mkdir_p(result_dir)
mkdir_p(visual_dir)
mkdir_p(final_dir)
logger.info("start validation....")
def mypredictor(input_img):
# input image: 1*H*W*3
# output : H*W*C
output = predictor(input_img[np.newaxis, :, :, :])
return output[0][0]
for i in tqdm(range(len(ll))):
filename = ll[i]
image = cv2.imread(os.path.join(args.test_dir, filename))
prediction = predict_scaler(image,
mypredictor,
scales=[0.5, 0.75, 1, 1.25, 1.5],
classes=CLASS_NUM,
tile_size=CROP_SIZE,
is_densecrf=False)
prediction = np.argmax(prediction, axis=2)
cv2.imwrite(os.path.join(final_dir, "{}".format(filename)), prediction)
cv2.imwrite(
os.path.join(visual_dir, "{}".format(filename)),
np.concatenate((image, visualize_label(prediction)), axis=1))
def view_data(base_dir, meta_dir, batch_size):
ds = RepeatedData(get_data('train', base_dir, meta_dir, batch_size), -1)
ds.reset_state()
from tensorpack.utils.fs import mkdir_p
result_dir = "result/view"
#result_dir = "ningbo_validation"
mkdir_p(result_dir)
i = 0
for ims, labels in ds.get_data():
for im, label in zip(ims, labels):
#aa = visualize_label(label)
#pass
#cv2.imshow("im", im / 255.0)
#cv2.imshow("raw-label", label)
#cv2.imshow("color-label", visualize_label(label))
cv2.imwrite(os.path.join(result_dir, "{}.png".format(i)),
np.concatenate((im, visualize_label(label)), axis=1))
#cv2.waitKey(0)
i += 1
print i
image -= self.mean
image = image.transpose((2, 0, 1))
return image.copy(), label.copy(), np.array(size), name
if __name__ == '__main__':
import matplotlib.pyplot as plt
dst = SynthiaDataSet(
root="../data/SYNTHIA",
list_path="synthia_list/SYNTHIA_imagelist_train.txt",
label_list_path="synthia_list/SYNTHIA_labellist_train.txt")
trainloader = data.DataLoader(dst, batch_size=4)
for i, data in enumerate(trainloader):
imgs, labels, size, name = data
import cv2
from tensorpack.utils.segmentation.segmentation import predict_slider, visualize_label, predict_scaler
img = torchvision.utils.make_grid(imgs).numpy()
img = np.transpose(img, (1, 2, 0))
img = img[:, :, ::-1] + 128
label = torchvision.utils.make_grid(labels.unsqueeze(1)).numpy()
label = np.transpose(label, (1, 2, 0))
#plt.imshow(img)
#plt.show()
cv2.imshow("source image", img.astype(np.uint8))
cv2.imshow("source label", visualize_label(label[:, :, 0]))
cv2.waitKey(10000)
else:
im = im.resize((data_size[0], data_size[1]), Image.LANCZOS)
im_ = np.array(im, dtype=np.float64)
label_= np.array(label, dtype=np.int32)
return im_, label_
if __name__ == '__main__':
from tensorpack.utils.segmentation.segmentation import predict_slider, visualize_label, predict_scaler
def get_data(ds, idx):
data_file = ds.files[ds.split][idx]
img, label = ds.image_label_loader(data_file['img'], data_file['lbl'], ds.image_size, random_crop=True)
return img, label
dataset = SYNTHIA('SYNTHIA', '/home/hutao/lab/pytorchgo/example/LSD-seg/data', split='train', transform=True, image_size=[640, 320])
cs = CityScapes('cityscapes', '/home/hutao/lab/pytorchgo/example/LSD-seg/data', split='train', transform=True,
image_size=[640, 320])
for i in range(len(dataset)):
img,label = get_data(dataset, i)
cs_img, cs_label= get_data(cs, i)
print np.unique(label)
cv2.imshow("source image",img.astype(np.uint8))
cv2.imshow("source label",visualize_label(label))
cv2.imshow("target image",cs_img.astype(np.uint8))
cv2.imshow("target label", visualize_label(cs_label))
cv2.waitKey(10000)