def count_acc(is_crf=True):
average_acc = 0
whole_acc = 0
#box num of per image
box_num_img = 0
#box num of whole test images
box_num_imgs = 0
#right predictions num per image
right_num_img = 0
#right predictions num of whole test images
right_num_imgs = 0
#num of test images
num_imgs = 0
if is_crf:
pred_dir = crf_pred_dir
else:
pred_dir = test_pred_dir
with open(test_dir, 'r') as f_test_txt:
for img_name in f_test_txt:
img_name = img_name.rstrip()
num_imgs += 1
img = Image.open(img_dir + img_name + '.jpg')
img_w = img.size[0]
img_h = img.size[1]
pred_mask = Image.open(pred_dir + img_name + '.png')
pred_mask = np.array(pred_mask)
annpath = (anns_dir + img_name).rstrip() + '.xml'
DOMTree = parse(annpath)
collection = DOMTree.documentElement
objects = collection.getElementsByTagName('object')
if len(objects) > 0:
for object_ in objects:
bndbox = object_.getElementsByTagName('bndbox')[0]
xmin = bndbox.getElementsByTagName(
'xmin')[0].childNodes[0].nodeValue
ymin = bndbox.getElementsByTagName(
'ymin')[0].childNodes[0].nodeValue
xmax = bndbox.getElementsByTagName(
'xmax')[0].childNodes[0].nodeValue
ymax = bndbox.getElementsByTagName(
'ymax')[0].childNodes[0].nodeValue
xmin, ymin, xmax, ymax = get_int_coor(
xmin, ymin, xmax, ymax, img_w, img_h)
xmin = int(xmin * 1632 / img_w)
xmax = int(xmax * 1632 / img_w)
ymin = int(ymin * 1216 / img_h)
ymax = int(ymax * 1216 / img_h)
box_num_img += 1
box_num_imgs += 1
if np.sum(pred_mask[ymin:ymax, xmin:xmax]) != 0:
right_num_img += 1
average_acc += (right_num_img / box_num_img)
right_num_imgs += right_num_img
right_num_img = 0
box_num_img = 0
print('{} / {}'.format(num_imgs, img_name), end='\r')
average_acc = average_acc / num_imgs
whole_acc = right_num_imgs / box_num_imgs
return average_acc, whole_acc
def update_label(predict_model, device):
"""load train_pairs.txt info for check the missed diagnosis objects"""
#ann_info:[image name, image name_num_ class_id.png, bbox_ymin,
# bbox_xmin,bbox_ymax, bbox_xmax, class_name]
print('start to update...')
ANNS = {}
with open(dataset_pairs_dir, 'r') as da_p_txt:
for ann_info in da_p_txt:
# split the string line, get the list
ann_info = ann_info.rstrip().split('###')
if ann_info[0].rstrip() not in ANNS:
ANNS[ann_info[0].rstrip()] = []
ANNS[ann_info[0].rstrip()].append(ann_info)
# print('loading model...')
# predict_model = torch.load(model_path)
# device = torch.device('cuda: 3' if torch.cuda.is_available() else 'cpu')
# predict_model = predict_model.to(device)
predict_model.eval()
# define the same image transformations
transformations = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
])
update_num = 0
print('updating progress:')
with open(dataset_txt_dir, 'r') as da_txt:
# don't use the code line below
# or it will close the file and the whole programm end here (I guess)
# I debug here for two hours......
#lines = len(da_txt.readlines())
for update_name in da_txt:
update_num += 1
# in RGB [W, H, depth]
img = Image.open(os.path.join(img_dir, update_name).rstrip()+'.jpg')
img_w = img.size[0]
img_h = img.size[1]
#img = img.resize((1632, 1216), Image.LANCZOS)
# in drone_data,size-1024
img = img.resize((1024, 1024), Image.LANCZOS)
input_ = transformations(img).float()
# add batch_size dimension
#[3, H, W]-->[1, 3, H, W]
input_ = input_.unsqueeze_(0)
input_ = input_.to(device)
#pred = predict_model(input_).view([1216, 1632]).data.cpu()
# in drone data, size-1024
pred = predict_model(input_).view([1024, 1024]).data.cpu()
#pred.shape[H,W]
pred = np.array(pred)
"""crf smooth prediction"""
crf_pred = run_densecrf(img_dir, update_name, pred)
"""start to update"""
last_label = Image.open(os.path.join(label_dir, update_name).rstrip()+'.png')
#last_label = last_label.resize((1632, 1216), Image.NEAREST)
# in drone_data size-1024
last_label = last_label.resize((1024, 1024), Image.NEAREST)
last_label = np.array(last_label)
# predicted label without false-positive segments
updated_label = crf_pred + last_label
updated_label = np.where((updated_label==2), 1, 0).astype('uint8')
# predicted label with missed diagnosis
# we just use the box segments as missed diagnosis for now
info4check = ANNS[update_name.rstrip()]
# masks_missed = np.zeros((1216, 1632), np.uint8)
# for drone data size-1024
masks_missed = np.zeros((1024, 1024), np.uint8)
for box4check in info4check:
xmin = box4check[3]
ymin = box4check[2]
xmax = box4check[5]
ymax = box4check[4]
xmin, ymin, xmax, ymax = get_int_coor(xmin, ymin,
xmax, ymax, img_w, img_h)
# xmin = int(xmin * 1632 / img_w)
# xmax = int(xmax * 1632 / img_w)
# ymin = int(ymin * 1216 / img_h)
# ymax = int(ymax * 1216 / img_h)
# for drone data - size 1024
xmin = int(xmin * 1024 / img_w)
xmax = int(xmax * 1024 / img_w)
ymin = int(ymin * 1024 / img_h)
ymax = int(ymax * 1024 / img_h)
if np.sum(updated_label[ymin:ymax, xmin:xmax]) == 0:
masks_missed[ymin:ymax, xmin:xmax] = 1
updated_label = updated_label + masks_missed
scipy.misc.toimage(updated_label, cmin=0, cmax=255, pal=colors_map,
mode='P').save(os.path.join(label_dir,
update_name).rstrip()+ '.png')
print('{} / {}'.format(update_num, len(ANNS)), end='\r')
def grabcut(img_name):
masks = []
# one image has many object that need to grabcut
for i, ann_info in enumerate(ANNS[img_name], start=1):
img = cv.imread((img_dir +img_name).rstrip()+'.jpg')
grab_name = ann_info[1]
xmin = ann_info[3]
ymin = ann_info[2]
xmax = ann_info[5]
ymax = ann_info[4]
"""get int box coor"""
img_w = img.shape[1]
img_h = img.shape[0]
xmin, ymin, xmax, ymax = get_int_coor(xmin, ymin, xmax, ymax, img_w, img_h)
box_w = xmax - xmin
box_h = ymax - ymin
# cv.grabcut's para
mask = np.zeros(img.shape[:2], np.uint8)
# rect is the tuple
rect = (xmin, ymin, box_w, box_h)
bgdModel = np.zeros((1, 65), np.float64)
fgdModel = np.zeros((1, 65), np.float64)
#for small bbox:
if box_w * box_h < MINI_AREA:
img_mask = mask[ymin:ymax, xmin:xmax] = 1
# for big box that area == img.area(one object bbox is just the whole image)
elif box_w * box_h == img.shape[1] * img.shape[0]:
rect = [RECT_SHRINK, RECT_SHRINK, box_w - RECT_SHRINK * 2, box_h - RECT_SHRINK * 2]
cv.grabCut(img, mask, rect, bgdModel,fgdModel, ITER_NUM, cv.GC_INIT_WITH_RECT)
# astype('uint8') keep the image pixel in range[0,255]
img_mask = np.where((mask == 0) | (mask == 2), 0, 1).astype('uint8')
# for normal bbox:
else:
cv.grabCut(img, mask, rect, bgdModel,fgdModel, ITER_NUM, cv.GC_INIT_WITH_RECT)
img_mask = np.where((mask == 0) | (mask == 2), 0, 1).astype('uint8')
# if the grabcut output is just background(it happens in my dataset)
if np.sum(img_mask) == 0:
img_mask = np.where((mask == 0), 0, 1).astype('uint8')
# couting IOU
# if the grabcut output too small region, it need reset to bbox mask
box_mask = np.zeros((img.shape[0], img.shape[1]))
box_mask[ymin:ymax, xmin:xmax] = 1
sum_area = box_mask + img_mask
intersection = np.where((sum_area==2), 1, 0).astype('uint8')
union = np.where((sum_area==0), 0, 1).astype('uint8')
IOU = np.sum(intersection) / np.sum(union)
if IOU <= IOU_THRESHOLD:
img_mask = box_mask
# for draw mask on the image later
img = cv.cvtColor(img, cv.COLOR_BGR2RGB)
masks.append([img_mask, grab_name, rect])
num_object = i
"""for multi-objects intersection and fix the label """
masks.sort(key=lambda mask: np.sum(mask[0]), reverse=True)
for j in range(num_object):
for k in range(j+1, num_object):
masks[j][0] = masks[j][0] - masks[k][0]
masks[j][0] = np.where((masks[j][0]==1), 1, 0).astype('uint8')
"""get class name id"""
grab_name = masks[j][1]
class_id = grab_name.split('_')[-1]
class_id = int(class_id.split('.')[0])
#set the numpy value to class_id
masks[j][0] = np.where((masks[j][0]==1), class_id, 0).astype('uint8')
# save grabcut_inst(one object in a image)
scipy.misc.toimage(masks[j][0], cmin=0, cmax=255, pal=tbvoc_info.colors_map,
mode='P' ).save((grabcut_dir).rstrip()+masks[j][1])
"""merge masks"""
# built array(img.shape size)
mask_ = np.zeros(img.shape[:2])
for mask in masks:
mask_ = mask_ + mask[0]
# save segmetation_label(every object in a image)
scipy.misc.toimage(mask_, cmin=0, cmax=255, pal=tbvoc_info.colors_map,
mode='P').save((segmentation_label_dir+img_name).rstrip()+'.png')
"""create figure with masks and bbox in a image"""
fig = plt.figure()
# covert to inch
# dpi: dot per inch
W = img.shape[1] / float(fig.get_dpi())
H = img.shape[0] / float(fig.get_dpi())
# set fig size
fig.set_size_inches(W, H)
for mask in masks:
rect = mask[2]
mask = mask[0]
color = tbvoc_info.colors[np.amax(mask)]
# add one dimension mask[H,W,1]
mask = mask[:, :, np.newaxis]
# draw mask in image(RGB)
for c in range(3):
img[:, :, c] = np.where((mask[:, :, 0] != 0),
img[:, :, c]*0.2+0.8*color[c], img[:, :, c])
#compute bbox coordinates
#reference: https://www.cnblogs.com/xiaopengli/p/8058408.html
# use axes, so the coordinates is relative
left = rect[0] / img.shape[1]
bottom = 1- (rect[1] + rect[3]) / img.shape[0]
ax_w = (rect[0] + rect[2]) / img.shape[1] - left
ax_h = 1 - rect[1] / img.shape[0] - bottom
# draw bbox
ax = fig.add_axes([left, bottom, ax_w, ax_h])
ax.xaxis.set_visible(False)
ax.yaxis.set_visible(False)
ax.patch.set_fill(False)
ax.patch.set_linewidth(5)
ax.patch.set_color('b')
# add a non-resampled image to the figure
# add the axes to the figure
plt.figimage(img)
# save img_grabcuts(bbox+mask)
fig.savefig((img_grabcuts_dir+img_name).rstrip()+'.png')
"""
plt.cla() : clear local activate axes, others keep constant
plt.clf() : clear all axex in the figure, but don't shutdown the figure window
plt.close(): close the figure window
"""
plt.cla()
plt.clf()
plt.close()