def demo_cv2(img_id=0):
net = build_ssd('test', 512, 5) # initialize SSD
print(net)
net.load_weights(
'/media/sunwl/Datum/Projects/GraduationProject/Fused_concat_SSD_VHR_512/weights/v2_rosd.pth'
)
testset = ROSDDetection(ROSDroot, ['test'], None, AnnotationTransform_ROSD)
image = testset.pull_image(img_id)
# image = cv2.imread('demos/oiltank_1.jpg')
rgb_image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
x = cv2.resize(rgb_image, (512, 512)).astype(np.float32)
x -= (104.0, 117.0, 123.0)
x = x.astype(np.float32)
x = x[:, :, ::-1].copy()
x = torch.from_numpy(x).permute(2, 0, 1)
xx = Variable(x.unsqueeze(0)) # wrap tensor in Variable
if torch.cuda.is_available():
xx = xx.cuda()
y = net(xx)
colors = plt.cm.hsv(np.linspace(0, 1, 5)).tolist()
detections = y.data
# scale each detection back up to the image
scale = torch.Tensor(rgb_image.shape[1::-1]).repeat(2)
bgr_image = cv2.cvtColor(rgb_image, cv2.COLOR_BGR2RGB)
im2show = np.copy(bgr_image)
for i in range(detections.size(1)):
j = 0
while detections[0, i, j, 0] >= 0.6:
score = detections[0, i, j, 0]
label_name = labels[i - 1]
display_txt = '%s: %.2f' % (label_name, score)
pt = (detections[0, i, j, 1:] * scale).cpu().numpy()
color = colors[i]
color = [int(c * 255) for c in color[:3]]
coords = pt[0], pt[1], pt[2], pt[3]
cv2.rectangle(im2show,
coords[0:2],
coords[2:4],
color,
thickness=2)
cv2.putText(im2show,
display_txt, (int(coords[0]), int(coords[1]) - 3),
cv2.FONT_HERSHEY_PLAIN,
1.0,
color,
thickness=1)
j += 1
cv2.imshow('original', bgr_image)
cv2.imshow('demo', im2show)
cv2.imwrite(
os.path.join(
'/media/sunwl/Datum/Projects/GraduationProject/Fused_concat_SSD_VHR_512',
"outputs", "rosd_{:03d}.jpg".format(img_id)), im2show)
cv2.waitKey(0)
def train():
net.train()
# loss counters
loc_loss = 0 # epoch
conf_loss = 0
epoch = 0
print('Loading Dataset...')
dataset = ROSDDetection(args.rosd_root, train_sets, SSDAugmentation(
ssd_dim, means), AnnotationTransform_ROSD())
epoch_size = len(dataset) // args.batch_size
print('Training SSD on', dataset.name)
step_index = 0
if args.visdom:
# initialize visdom loss plot
lot = viz.line(
X=torch.zeros((1,)).cpu(),
Y=torch.zeros((1, 3)).cpu(),
opts=dict(
xlabel='Iteration',
ylabel='Loss',
title='Current SSD Training Loss',
legend=['Loc Loss', 'Conf Loss', 'Loss']
)
)
epoch_lot = viz.line(
X=torch.zeros((1,)).cpu(),
Y=torch.zeros((1, 3)).cpu(),
opts=dict(
xlabel='Epoch',
ylabel='Loss',
title='Epoch SSD Training Loss',
legend=['Loc Loss', 'Conf Loss', 'Loss']
)
)
batch_iterator = None
data_loader = data.DataLoader(dataset, batch_size, num_workers=args.num_workers,
shuffle=True, collate_fn=detection_collate_ROSD, pin_memory=True)
for iteration in range(args.start_iter, max_iter):
if (not batch_iterator) or (iteration % epoch_size == 0):
# create batch iterator
batch_iterator = iter(data_loader)
if iteration in stepvalues:
step_index += 1
adjust_learning_rate(optimizer, args.gamma, step_index)
if args.visdom:
viz.line(
X=torch.ones((1, 3)).cpu() * epoch,
Y=torch.Tensor([loc_loss, conf_loss,
loc_loss + conf_loss]).unsqueeze(0).cpu() / epoch_size,
win=epoch_lot,
update='append'
)
# reset epoch loss counters
loc_loss = 0
conf_loss = 0
epoch += 1
# load train data
images, targets = next(batch_iterator)
if args.cuda:
images = Variable(images.cuda())
targets = [Variable(anno.cuda(), volatile=True) for anno in targets]
else:
images = Variable(images)
targets = [Variable(anno, volatile=True) for anno in targets]
# forward
t0 = time.time()
out = net(images)
# backprop
optimizer.zero_grad()
loss_l, loss_c = criterion(out, targets)
loss = loss_l + loss_c
loss.backward()
optimizer.step()
t1 = time.time()
loc_loss += loss_l.data[0]
conf_loss += loss_c.data[0]
if iteration % 10 == 0:
print('Timer: %.4f sec.' % (t1 - t0))
print('iter ' + repr(iteration) + ' || Loss: %.4f ||' % (loss.data[0]), end=' ')
if args.visdom and args.send_images_to_visdom:
random_batch_index = np.random.randint(images.size(0))
viz.image(images.data[random_batch_index].cpu().numpy())
if args.visdom:
viz.line(
X=torch.ones((1, 3)).cpu() * iteration,
Y=torch.Tensor([loss_l.data[0], loss_c.data[0],
loss_l.data[0] + loss_c.data[0]]).unsqueeze(0).cpu(),
win=lot,
update='append'
)
# hacky fencepost solution for 0th epoch plot
if iteration == 0:
viz.line(
X=torch.zeros((1, 3)).cpu(),
Y=torch.Tensor([loc_loss, conf_loss,
loc_loss + conf_loss]).unsqueeze(0).cpu(),
win=epoch_lot,
update=True
)
if iteration % 5000 == 0:
print('Saving state, iter:', iteration)
torch.save(ssd_net.state_dict(),
'weights/fused_concat_ssd512_rosd_' +
repr(iteration) + '.pth')
torch.save(ssd_net.state_dict(), args.save_folder + '' + args.version + '_rosd.pth')
coords = (pt[0], pt[1], pt[2], pt[3])
pred_num += 1
with open(filename, mode='a') as f:
f.write(
str(pred_num) + ' label: ' + label_name + ' score: ' +
str(score) + ' ' + ' || '.join(str(c)
for c in coords) + '\n')
j += 1
if __name__ == '__main__':
# load net
num_classes = len(ROSD_CLASSES) + 1 # +1 background
net = build_ssd('test', 512, num_classes) # initialize SSD
net.load_state_dict(torch.load(args.trained_model))
net.eval()
print('Finished loading model!')
# load data
testset = ROSDDetection(args.rosd_root, ['test'], None,
AnnotationTransform_ROSD())
if args.cuda:
net = net.cuda()
cudnn.benchmark = True
# evaluation
test_net(args.save_folder,
net,
args.cuda,
testset,
BaseTransform(net.size, (104, 117, 123)),
thresh=args.visual_threshold)
def evaluate_detections(box_list, output_dir, dataset):
write_vhr_results_file(box_list, dataset)
do_python_eval(output_dir)
if __name__ == '__main__':
# load net
num_classes = len(ROSD_CLASSES) + 1 # +1 background
net = build_ssd('test', 512, num_classes) # initialize SSD
net.load_state_dict(torch.load(args.trained_model))
net.eval()
print('Finished loading model!')
print(net)
# load data
dataset = ROSDDetection(args.ROSD_root, ['test'],
BaseTransform(512, dataset_mean),
AnnotationTransform_ROSD())
print(dataset)
if args.cuda:
net = net.cuda()
cudnn.benchmark = True
# evaluation
test_net(args.save_folder,
net,
args.cuda,
dataset,
BaseTransform(net.size, dataset_mean),
args.top_k,
512,
thresh=args.confidence_threshold)
def demo_plt(img_id=0):
net = build_ssd('test', 512, 5) # initialize SSD
print(net)
net.load_weights(
'/media/sunwl/Datum/Projects/GraduationProject/Fused_concat_SSD_VHR_512/weights/v2_rosd.pth'
)
testset = ROSDDetection(ROSDroot, ['test'], None, AnnotationTransform_ROSD)
image = testset.pull_image(img_id)
# image = cv2.imread('demos/047.jpg')
rgb_image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
# View the sampled input image before transform
plt.figure(figsize=(10, 10))
plt.imshow(rgb_image)
x = cv2.resize(rgb_image, (512, 512)).astype(np.float32)
x -= (104.0, 117.0, 123.0)
x = x.astype(np.float32)
x = x[:, :, ::-1].copy()
x = torch.from_numpy(x).permute(2, 0, 1)
xx = Variable(x.unsqueeze(0)) # wrap tensor in Variable
if torch.cuda.is_available():
xx = xx.cuda()
y = net(xx)
#
plt.figure(figsize=(10, 10))
colors = plt.cm.hsv(np.linspace(0, 1, 5)).tolist()
plt.imshow(rgb_image.astype(np.uint8)) # plot the image for matplotlib
currentAxis = plt.gca()
detections = y.data
# scale each detection back up to the image
scale = torch.Tensor(rgb_image.shape[1::-1]).repeat(2)
for i in range(detections.size(1)):
j = 0
while detections[0, i, j, 0] >= 0.6:
score = detections[0, i, j, 0]
label_name = labels[i - 1]
display_txt = '%s: %.2f' % (label_name, score)
pt = (detections[0, i, j, 1:] * scale).cpu().numpy()
color = colors[i]
coords = (pt[0], pt[1]), pt[2] - pt[0] + 1, pt[3] - pt[1] + 1
currentAxis.add_patch(
plt.Rectangle(*coords,
fill=False,
edgecolor=color,
linewidth=2))
currentAxis.text(pt[0],
pt[1],
display_txt,
bbox={
'facecolor': color,
'alpha': 0.5
})
j += 1
plt.savefig(
'/media/sunwl/Datum/Projects/GraduationProject/Fused_concat_SSD_VHR_512/outputs/rosd_{:03}.png'
.format(img_id))
plt.xticks([])
plt.yticks([])
plt.show()
def evaluate_detections(box_list, output_dir, dataset):
write_voc_results_file(box_list, dataset)
do_python_eval(output_dir)
if __name__ == '__main__':
# load net
num_classes = len(ROSD_CLASSES) + 1 # +1 background
net = build_ssd('test', 300, num_classes) # initialize SSD
net.load_state_dict(torch.load(args.trained_model))
net.eval()
print('Finished loading model!')
print(net)
# load data
dataset = ROSDDetection(args.rosd_root, [set_type],
BaseTransform(300, dataset_mean),
AnnotationTransform_ROSD())
if args.cuda:
net = net.cuda()
cudnn.benchmark = True
# evaluation
test_net(args.save_folder,
net,
args.cuda,
dataset,
BaseTransform(net.size, dataset_mean),
args.top_k,
300,
thresh=args.confidence_threshold)