def main():
"""Create the model and start the evaluation process."""
args = get_arguments()
gpu0 = args.gpu
if not os.path.exists(args.save):
os.makedirs(args.save)
model = Res_Deeplab(num_classes=args.num_classes)
#model = getVGG(num_classes=args.num_classes)
if args.restore_from[:4] == 'http':
saved_state_dict = model_zoo.load_url(args.restore_from)
else:
saved_state_dict = torch.load(args.restore_from)
model.load_state_dict(saved_state_dict)
model.eval()
model.cuda(gpu0)
testloader = data.DataLoader(cityscapesDataSet(args.data_dir,
args.data_list,
crop_size=(1024, 512),
mean=IMG_MEAN,
scale=False,
mirror=False,
set=args.set),
batch_size=1,
shuffle=False,
pin_memory=True)
#testloader = data.DataLoader(GTA5DataSet(args.data_dir, args.data_list, crop_size=(1024, 512), mean=IMG_MEAN, scale=False, mirror=False), batch_size=1, shuffle=False, pin_memory=True)
interp = nn.Upsample(size=(1024, 2048), mode='bilinear')
for index, batch in enumerate(testloader):
if index % 100 == 0:
print '%d processd' % index
image, _, name = batch
#image, _, _, name = batch
output1, output2 = model(Variable(image, volatile=True).cuda(gpu0))
#import torch.nn.functional as F
#output2 = F.avg_pool2d(output2, (4, 4))
#print(output1.shape)
#print(output2.shape)
#exit()
output = interp(output2).cpu().data[0].numpy()
output = output.transpose(1, 2, 0)
output = np.asarray(np.argmax(output, axis=2), dtype=np.uint8)
output_col = colorize_mask(output)
output = Image.fromarray(output)
name = name[0].split('/')[-1]
output.save('%s/%s' % (args.save, name))
output_col.save('%s/%s_color.png' % (args.save, name.split('.')[0]))
def main():
"""Create the model and start the evaluation process."""
args = get_arguments()
gpu0 = args.gpu
for iter in range(ITER_START, ITER_END + 1, SPAN):
print('{0} /{1} processed'.format(iter, ITER_END))
if not os.path.exists(args.save.format(iter)):
os.makedirs(args.save.format(iter))
model = Res_Deeplab(num_classes=args.num_classes)
saved_state_dict = torch.load(args.restore_from.format(iter))
for k, v in saved_state_dict.items():
if k.count('num_batches_tracked'):
del saved_state_dict[k]
model.load_state_dict(saved_state_dict)
model.eval()
model.cuda(gpu0)
testloader = data.DataLoader(cityscapesDataSet(args.data_dir,
args.data_list,
crop_size=(1024, 512),
mean=IMG_MEAN,
scale=False,
mirror=False,
set=args.set),
batch_size=1,
shuffle=False,
pin_memory=True)
interp = nn.Upsample(size=(1024, 2048), mode='bilinear')
for index, batch in enumerate(testloader):
if index % 100 == 0:
print '%d processd of %d' % (index, len(testloader))
image, _, name = batch
output1, output2 = model(Variable(image, volatile=True).cuda(gpu0))
output = interp(output2).cpu().data[0].numpy()
output = output.transpose(1, 2, 0)
output = np.asarray(np.argmax(output, axis=2), dtype=np.uint8)
output_col = colorize_mask(output)
# output = Image.fromarray(output)
name = name[0].split('/')[-1]
# output.save('%s/%s' % (args.save, name))
output_col.save('%s/%s_color.png' %
(args.save.format(iter), name.split('.')[0]))
def show_val(seg_state_dict, save_dir, gpu_id):
"""Create the model and start the evaluation process."""
# args = get_arguments()
# save_dir=save_path.format(iter)
gpu0 = gpu_id
if not os.path.exists(save_dir):
os.makedirs(save_dir)
model = Res_Deeplab(num_classes=NUM_CLASSES)
model = nn.DataParallel(model, device_ids=device_ids)
model.load_state_dict(seg_state_dict)
model.eval()
model.cuda(gpu0)
testloader = data.DataLoader(cityscapesDataSet(DATA_DIRECTORY,
DATA_LIST_PATH,
crop_size=(1024, 512),
mean=IMG_MEAN,
scale=False,
mirror=False,
set=SET),
batch_size=1,
shuffle=False,
pin_memory=True)
# interp = nn.Upsample(size=(1024, 2048), mode='bilinear')
# 作者建议：
interp = nn.Upsample(size=(1024, 2048),
mode='bilinear',
align_corners=True)
for index, batch in enumerate(testloader):
image, _, name = batch
with torch.no_grad():
output1, output2 = model(Variable(image).cuda(gpu0))
output = interp(output2).cpu().data[0].numpy()
output = output.transpose(1, 2, 0)
output = np.asarray(np.argmax(output, axis=2), dtype=np.uint8)
output_col = colorize_mask(output)
name = name[0].split('/')[-1]
output_col.save('%s/%s.png' % (save_dir, name.split('.')[0]))
print('colored pictures saving is done')
mIoUs = compute_mIoU(gtDir, save_dir, devkitDir)
return mIoUs
def show_val(seg_state_dict, show_pred_sv_dir, city='ROME'):
"""Create the model and start the evaluation process."""
# args = get_arguments()
save_dir=show_pred_sv_dir
gpu0 = 0
if not os.path.exists(save_dir):
os.makedirs(save_dir)
model = Res_Deeplab(num_classes=NUM_CLASSES)
model.load_state_dict(seg_state_dict)
model.eval()
model.cuda(gpu0)
testloader = data.DataLoader(MixedDataSet(DATA_DIRECTORY, DATA_LIST_PATH, crop_size=(1024, 512), mean=IMG_MEAN, scale=False, mirror=False, set=SET),
batch_size=1, shuffle=False, pin_memory=True)
interp = nn.Upsample(size=(1024, 2048), mode='bilinear')
# n=0
for index, batch in enumerate(testloader):
# n+=1
# if n>3:
# continue
image, _, name = batch
# _, output1, output2 = model(Variable(image, requires_grad=True).cuda(gpu0)) #ada_deeplab_multi
output1, output2 = model(Variable(image, requires_grad=True).cuda(gpu0))
output = interp(output2).cpu().data[0].numpy()
output = output.transpose(1,2,0)
output = np.asarray(np.argmax(output, axis=2), dtype=np.uint8)
output_col = colorize_mask(output)
name = name[0].split('/')[-1]
output_col.save('%s/%s.png' % (save_dir, name.split('.')[0]))
print('colored pictures saving is done')
mIoUs, syn_mIoUs=compute_mIoU(gtDir, save_dir, devkitDir)
return mIoUs, syn_mIoUs
def main():
"""Create the model and start the evaluation process."""
import warnings
if not sys.warnoptions:
warnings.simplefilter("ignore")
args = get_arguments()
gpu0 = args.gpu
if not os.path.exists(args.save):
os.makedirs(args.save)
model = Res_Deeplab(num_classes=args.num_classes)
#from pytorchgo.model.MyFCN8s import MyFCN8s
#model = MyFCN8s(n_class=NUM_CLASSES)
if args.restore_from[:4] == 'http' :
saved_state_dict = model_zoo.load_url(args.restore_from)
else:
saved_state_dict = torch.load(args.restore_from)
model.load_state_dict(saved_state_dict['model_state_dict'])
model.eval()
model.cuda(gpu0)
image_size = (1024, 512)#(1280,720) #(2048, 1024)
cityscape_image_size = (2048, 1024)
print ("evaluating {}".format(args.restore_from))
print ("************ best mIoU:{} *******".format(saved_state_dict['best_mean_iu']))
print("evaluation image size: {}, please make sure this image size is equal to your training image size, this is important for your final mIoU!".format(image_size))
testloader = data.DataLoader(cityscapesDataSet( crop_size=(image_size[0], image_size[1]), mean=IMG_MEAN, scale=False, mirror=False, set=args.set),
batch_size=1, shuffle=False, pin_memory=True)
interp = nn.Upsample(size=(cityscape_image_size[1], cityscape_image_size[0]), mode='bilinear')
from tensorpack.utils.stats import MIoUStatistics
stat = MIoUStatistics(NUM_CLASSES)
for index, batch in tqdm(enumerate(testloader)):
image,label, _, name = batch
image, label = Variable(image, volatile=True), Variable(label)
#output2 = model(image.cuda(gpu0))
output1, output2 = model(image.cuda(gpu0))
output = interp(output2).cpu().data[0].numpy()
output = output.transpose(1,2,0)
output = np.asarray(np.argmax(output, axis=2), dtype=np.uint8)
output_col = colorize_mask(output)
name = name[0].split('/')[-1]
output_col.save('%s/%s_color.png' % (args.save, name.split('.')[0]))
stat.feed(output, label.data.cpu().numpy().squeeze())
print("tensorpack IoU: {}".format(stat.mIoU_beautify))
print("tensorpack class16 IoU: {}".format(np.sum(stat.IoU)/16))
print("tensorpack mIoU: {}".format(stat.mIoU))
print("tensorpack mean_accuracy: {}".format(stat.mean_accuracy))
print("tensorpack accuracy: {}".format(stat.accuracy))
def main():
"""Create the model and start the evaluation process."""
args = get_arguments()
gpu0 = args.gpu
if not os.path.exists(args.save):
os.makedirs(args.save)
model = Res_Deeplab(num_classes=args.num_classes)
if args.restore_from[:4] == 'http':
saved_state_dict = model_zoo.load_url(args.restore_from)
else:
saved_state_dict = torch.load(args.restore_from)
model.load_state_dict(saved_state_dict)
model.eval()
model.cuda(gpu0)
if os.path.isfile(citys_feat_distr_path) == False:
testloader = data.DataLoader(cityscapesDataSet(args.data_dir,
args.data_list,
crop_size=(1024, 512),
mean=CITY_IMG_MEAN,
scale=False,
mirror=False,
set=args.set),
batch_size=1,
shuffle=False,
pin_memory=True)
# interp = nn.Upsample(size=(1024, 2048), mode='bilinear', align_corners=True)
interp_down = nn.Upsample(size=(16, 32),
mode='bilinear',
align_corners=True)
citys_feat_distrs = []
citys_img_paths = []
for index, batch in enumerate(testloader):
if index % 100 == 0:
print('%d processd of %d' % (index, len(testloader)))
image, _, name = batch
output1, output2 = model(Variable(image, volatile=True).cuda(gpu0))
output = interp_down(output2).cpu().data[0].numpy()
output = output.transpose(1, 2, 0)
output = output[np.newaxis, :] # add a dim
citys_feat_distrs.extend(output)
citys_img_paths.extend(name)
#name: 'frankfurt/frankfurt_000001_007973_leftImg8bit.png'
# name = name[0].split('/')[-1]
citys_feat_distrs_np = np.array(citys_feat_distrs)
citys_img_paths_np = np.array(citys_img_paths)
np.save(citys_feat_distr_path, citys_feat_distrs_np)
np.save(citys_imgpaths_path, citys_img_paths_np)
else:
citys_feat_distrs_np = np.load(citys_feat_distr_path)
citys_img_paths_np = np.load(citys_imgpaths_path)
if os.path.isfile(gta_feat_distr_path) == False:
gtaloader = data.DataLoader(GTA5DataSet(GTA_DATA_DIRECTORY,
GTA_DATA_LIST_PATH,
crop_size=(1024, 512),
mean=GTA_IMG_MEAN,
scale=False,
mirror=False),
batch_size=1,
shuffle=False,
pin_memory=True)
interp_down = nn.Upsample(size=(16, 32),
mode='bilinear',
align_corners=True)
gta_feat_distrs = []
gta_img_paths = []
for index, batch in enumerate(gtaloader):
if index % 100 == 0:
print('%d processd of %d' % (index, len(gtaloader)))
image, _, _, name = batch
output1, output2 = model(Variable(image, volatile=True).cuda(gpu0))
output = interp_down(output2).cpu().data[0].numpy()
output = output.transpose(1, 2, 0)
output = output[np.newaxis, :] # add a dim
gta_feat_distrs.extend(output)
gta_img_paths.extend(name)
gta_feat_distrs_np = np.array(gta_feat_distrs)
gta_img_paths_np = np.array(gta_img_paths)
np.save(gta_feat_distr_path, gta_feat_distrs_np)
np.save(gta_imgpaths_path, gta_img_paths_np)
else:
gta_feat_distrs_np = np.load(gta_feat_distr_path)
gta_img_paths_np = np.load(gta_imgpaths_path)
if os.path.isfile(closest_imgs_path) == False:
temp_feat = citys_feat_distrs_np[0, :]
# [m,n,c]=temp_feat.shape
pixel_amount = temp_feat.size
closest_imgs_locs = []
for i in range(citys_img_paths_np.shape[0]):
cur_citys_feat = citys_feat_distrs_np[i, :]
distances = []
if i % 10 == 0:
print(i)
for j in range(gta_img_paths_np.shape[0]):
cur_gta_feat = gta_feat_distrs_np[j, :]
dist_abs = abs(cur_citys_feat - cur_gta_feat)
# e_dist = np.sqrt(np.square(dist_abs).sum(axis=1))
dist_mean = np.sum(dist_abs) / pixel_amount
distances.append(dist_mean)
min_loc = np.argsort(distances)
# need to check overlap
top_ord = 3
closest_imgs_loc = min_loc[:top_ord]
intersect_imgs = np.intersect1d(closest_imgs_loc,
closest_imgs_locs)
while intersect_imgs.size:
inters_num = len(intersect_imgs)
closest_imgs_loc_confirm = np.setdiff1d(
closest_imgs_loc, intersect_imgs) # find the difference
closest_imgs_loc_candi = min_loc[top_ord:top_ord + inters_num]
top_ord = top_ord + inters_num
closest_imgs_loc_confirm = np.concatenate(
[closest_imgs_loc_confirm, closest_imgs_loc_candi])
closest_imgs_loc = closest_imgs_loc_confirm
intersect_imgs = np.intersect1d(closest_imgs_loc,
closest_imgs_locs)
closest_imgs_locs.extend(closest_imgs_loc)
np.save(closest_imgs_path, closest_imgs_locs)
else:
closest_imgs_locs = np.load(closest_imgs_path)
closest_imgs_locs_uni = np.unique(closest_imgs_locs)
zq = 1
# get file_names
with open(src_train_imgs_txt, 'w') as f_train:
for img_num in closest_imgs_locs_uni:
line = gta_img_paths_np[img_num] + '\n'
f_train.write(line)
def main():
"""Create the model and start the training."""
h, w = map(int, args.input_size.split(','))
input_size = (h, w)
h, w = map(int, args.com_size.split(','))
com_size = (h, w)
h, w = map(int, args.input_size_target.split(','))
input_size_target = (h, w)
cudnn.enabled = True
gpu = args.gpu
torch.cuda.set_device(args.gpu)
# Create network
if args.model == 'DeepLab':
model = Res_Deeplab(num_classes=args.num_classes)
saved_state_dict = torch.load(
args.restore_from,
map_location=lambda storage, loc: storage.cuda(args.gpu))
model.load_state_dict(saved_state_dict)
# Create network
# if args.model == 'DeepLab':
# model = Res_Deeplab(num_classes=args.num_classes)
# # saved_state_dict = torch.load(args.restore_from, map_location=lambda storage, loc: storage.cuda(args.gpu))
# saved_state_dict = torch.loa
model.train()
model.cuda(args.gpu)
cudnn.benchmark = True
if not os.path.exists(args.snapshot_dir):
os.makedirs(args.snapshot_dir)
print("amy", torch.cuda.current_device())
############################
#validation data
testloader = data.DataLoader(dataset.cityscapes_dataset.cityscapesDataSet(
args.data_dir_target,
args.data_list_target_val,
crop_size=input_size_target,
mean=IMG_MEAN,
scale=False,
mirror=False,
set=args.set_val),
batch_size=1,
shuffle=False,
pin_memory=True)
with open('./dataset/cityscapes_list/info.json', 'r') as fp:
info = json.load(fp)
mapping = np.array(info['label2train'], dtype=np.int)
label_path_list = './dataset/cityscapes_list/label.txt'
gt_imgs = open(label_path_list, 'r').read().splitlines()
gt_imgs = [join('./data/Cityscapes/data/gtFine/val', x) for x in gt_imgs]
interp_val = nn.Upsample(size=(com_size[1], com_size[0]), mode='bilinear')
############################
trainloader = data.DataLoader(GTA5DataSet(args.data_dir,
args.data_list,
max_iters=args.num_steps *
args.iter_size * args.batch_size,
crop_size=input_size,
scale=args.random_scale,
mirror=args.random_mirror,
mean=IMG_MEAN),
batch_size=args.batch_size,
shuffle=True,
num_workers=args.num_workers,
pin_memory=True)
trainloader_iter = enumerate(trainloader)
targetloader = data.DataLoader(cityscapesDataSet(
args.data_dir_target,
args.data_list_target,
max_iters=args.num_steps * args.iter_size * args.batch_size,
crop_size=input_size_target,
scale=False,
mirror=args.random_mirror,
mean=IMG_MEAN,
set=args.set),
batch_size=args.batch_size,
shuffle=True,
num_workers=args.num_workers,
pin_memory=True)
targetloader_iter = enumerate(targetloader)
# implement model.optim_parameters(args) to handle different models' lr setting
optimizer = optim.SGD(model.optim_parameters(args),
lr=args.learning_rate,
momentum=args.momentum,
weight_decay=args.weight_decay)
optimizer.zero_grad()
bce_loss = torch.nn.BCEWithLogitsLoss()
interp = nn.Upsample(size=(input_size[1], input_size[0]), mode='bilinear')
# interp_target = nn.UpsamplingBilinear2d(size=(input_size_target[1], input_size_target[0]))
Softmax = torch.nn.Softmax()
bce_loss = torch.nn.BCEWithLogitsLoss()
for i_iter in range(args.num_steps):
# loss_seg_value1 = 0
loss_seg_value = 0
loss_weak_value = 0
loss_neg_value = 0
loss_lse_source_value = 0
loss_lse_target_value = 0
entropy_samples_value = 0
model.train()
optimizer.zero_grad()
adjust_learning_rate(optimizer, i_iter)
for sub_i in range(args.iter_size):
# train with source
# _, batch = next(trainloader_iter)
# images, labels, class_label_source, mask_weakly, _, name = batch
# images = Variable(images).cuda(args.gpu)
# pred = model(images)
# pred = interp(pred)
# loss_seg = loss_calc(pred, labels, args.gpu)
# num = torch.sum(mask_weakly[0][0]).data.item()
# class_label_source_lse = class_label_source.type(torch.FloatTensor)
# exp_source = torch.min(torch.exp(1*pred), Variable(torch.exp(torch.tensor(40.0))).cuda(args.gpu))
# lse = (1.0/1) * torch.log( (512*256/num) * AvePool(torch.exp(1*pred) * mask_weakly.type(torch.FloatTensor).cuda(args.gpu)))
# loss_lse_source = bce_loss(lse, Variable(class_label_source_lse.reshape(lse.
_, batch = next(targetloader_iter)
images, class_label, _, _ = batch
images = Variable(images).cuda(args.gpu)
_, pred_target = model(images)
# optimizer.step()
del pred_target, batch, images
print('exp = {}'.format(args.snapshot_dir))
print(
'iter = {0:8d}/{1:8d}, loss_seg = {2:.3f} loss_lse_source = {3:.3f} loss_lse_target = {4:.3f}'
.format(i_iter, args.num_steps, loss_seg_value,
loss_lse_source_value, loss_lse_target_value))
if i_iter >= args.num_steps_stop - 1:
print('save model ...')
torch.save(
model.state_dict(),
osp.join(args.snapshot_dir, 'GTA5_' + str(i_iter) + '.pth'))
break
if i_iter % args.save_pred_every == 0 and i_iter != 0:
print('taking snapshot ...')
model.eval()
hist = np.zeros((19, 19))
f = open(args.results_dir, 'a')
for index, batch in enumerate(testloader):
print(index)
image, _, name = batch
_, output = model(
Variable(image, volatile=True).cuda(args.gpu))
pred = interp_val(output)
pred = pred[0].permute(1, 2, 0)
pred = torch.max(pred, 2)[1].byte()
pred_cpu = pred.data.cpu().numpy()
del pred, output
label = Image.open(gt_imgs[index])
label = np.array(label.resize(com_size, Image.NEAREST))
label = label_mapping(label, mapping)
hist += fast_hist(label.flatten(), pred_cpu.flatten(), 19)
mIoUs = per_class_iu(hist)
mIoU = round(np.nanmean(mIoUs) * 100, 2)
print(mIoU)
f.write('i_iter:{:d}, miou:{:0.5f} \n'.format(i_iter, mIoU))
f.close()
def main():
"""Create the model and start the evaluation process."""
args = get_arguments()
gpu0 = args.gpu
if not os.path.exists(args.save):
os.makedirs(args.save)
model = Res_Deeplab(num_classes=args.num_classes)
if args.restore_from[:4] == 'http':
saved_state_dict = model_zoo.load_url(args.restore_from)
else:
saved_state_dict = torch.load(args.restore_from)
model.load_state_dict(saved_state_dict)
model.eval()
model.cuda(gpu0)
#testloader = data.DataLoader(cityscapesDataSet(args.data_dir, args.data_list, crop_size=(1024, 512), mean=IMG_MEAN, scale=False, mirror=False, set=args.set),
# batch_size=1, shuffle=False, pin_memory=True)
interp = nn.Upsample(size=(1024, 2048), mode='bilinear')
'''
for index, batch in enumerate(testloader):
if index % 100 == 0:
print '%d processd' % index
image, _, name = batch
output1, output2 = model(Variable(image, volatile=True).cuda(gpu0))
output = interp(output2).cpu().data[0].numpy()
output = output.transpose(1,2,0)
output = np.asarray(np.argmax(output, axis=2), dtype=np.uint8)
output_col = colorize_mask(output)
output = Image.fromarray(output)
name = name[0].split('/')[-1]
output.save('%s/%s' % (args.save, name))
output_col.save('%s/%s_color.png' % (args.save, name.split('.')[0]))
'''
filee = open('val3.txt')
for linee in filee:
linee = linee.rstrip('\n')
image = Image.open(linee).convert('RGB')
crop_size = (1024, 512)
image = image.resize(crop_size, Image.BICUBIC)
image = np.asarray(image, np.float32)
size = image.shape
image = image[:, :, ::-1] # change to BGR
mean = (128, 128, 128)
image -= mean
image = image.transpose((2, 0, 1))
image = image.copy()
image = np.reshape(image, [1, 3, 512, 1024])
#image = data.DataLoader(image)
name = linee
image = torch.from_numpy(image)
output1, output2 = model(Variable(image, volatile=True).cuda(gpu0))
output = interp(output2).cpu().data[0].numpy()
output = output.transpose(1, 2, 0)
output = np.asarray(np.argmax(output, axis=2), dtype=np.uint8)
output_col = colorize_mask(output)
output = Image.fromarray(output)
#output = image
name = name.split('/')[-1]
print name
output.save('%s/%s' % (args.save, name))
output_col.save('%s/%s_color.png' % (args.save, name.split('.')[0]))
def main():
"""Create the model and start the training."""
w, h = map(int, args.input_size.split(','))
input_size = (w, h)
w, h = map(int, args.input_size_target.split(','))
input_size_target = (w, h)
h, w = map(int, args.com_size.split(','))
com_size = (h, w)
############################
#validation data
testloader = data.DataLoader(cityscapesDataSet(args.data_dir_target, args.data_list_target_val, crop_size=input_size, mean=IMG_MEAN, scale=False, mirror=False, set=args.set_val),
batch_size=1, shuffle=False, pin_memory=True)
with open('./dataset/cityscapes_list/info.json', 'r') as fp:
info = json.load(fp)
mapping = np.array(info['label2train'], dtype=np.int)
label_path_list = './dataset/cityscapes_list/label.txt'
gt_imgs = open(label_path_list, 'r').read().splitlines()
gt_imgs = [osp.join('./data/Cityscapes/data/gtFine/val', x) for x in gt_imgs]
interp_val = nn.UpsamplingBilinear2d(size=(com_size[1], com_size[0]))
############################
cudnn.enabled = True
# Create network
# if args.model == 'DeepLab':
# model = Res_Deeplab(num_classes=args.num_classes)
# if args.restore_from[:4] == 'http' :
# saved_state_dict = model_zoo.load_url(args.restore_from)
# else:
# saved_state_dict = torch.load(args.restore_from)
# new_params = model.state_dict().copy()
# for i in saved_state_dict:
# # Scale.layer5.conv2d_list.3.weight
# i_parts = i.split('.')
# # print i_parts
# if not args.num_classes == 19 or not i_parts[1] == 'layer5':
# new_params['.'.join(i_parts[1:])] = saved_state_dict[i]
# # print i_parts
# model.load_state_dict(new_params)
if args.model == 'DeepLab':
model = Res_Deeplab(num_classes=args.num_classes)
saved_state_dict = torch.load(args.restore_from)
model.load_state_dict(saved_state_dict)
model.train()
model.cuda(args.gpu)
cudnn.benchmark = True
# init D
model_D1 = FCDiscriminator(num_classes=args.num_classes)
model_D2 = FCDiscriminator(num_classes=args.num_classes)
model_D1.train()
model_D1.cuda(args.gpu)
model_D2.train()
model_D2.cuda(args.gpu)
if not os.path.exists(args.snapshot_dir):
os.makedirs(args.snapshot_dir)
trainloader = data.DataLoader(
GTA5DataSet(args.data_dir, args.data_list, max_iters=args.num_steps * args.iter_size * args.batch_size,
crop_size=input_size,
scale=args.random_scale, mirror=args.random_mirror, mean=IMG_MEAN),
batch_size=args.batch_size, shuffle=True, num_workers=args.num_workers, pin_memory=True)
trainloader_iter = enumerate(trainloader)
targetloader = data.DataLoader(cityscapesDataSet(args.data_dir_target, args.data_list_target,
max_iters=args.num_steps * args.iter_size * args.batch_size,
crop_size=input_size_target,
scale=False, mirror=args.random_mirror, mean=IMG_MEAN,
set=args.set),
batch_size=args.batch_size, shuffle=True, num_workers=args.num_workers,
pin_memory=True)
targetloader_iter = enumerate(targetloader)
# implement model.optim_parameters(args) to handle different models' lr setting
optimizer = optim.SGD(model.optim_parameters(args),
lr=args.learning_rate, momentum=args.momentum, weight_decay=args.weight_decay)
optimizer.zero_grad()
optimizer_D1 = optim.Adam(model_D1.parameters(), lr=args.learning_rate_D, betas=(0.9, 0.99))
optimizer_D1.zero_grad()
optimizer_D2 = optim.Adam(model_D2.parameters(), lr=args.learning_rate_D, betas=(0.9, 0.99))
optimizer_D2.zero_grad()
bce_loss = torch.nn.BCEWithLogitsLoss()
interp = nn.Upsample(size=(input_size[1], input_size[0]), mode='bilinear')
interp_target = nn.Upsample(size=(input_size_target[1], input_size_target[0]), mode='bilinear')
# labels for adversarial training
source_label = 0
target_label = 1
AvePool = torch.nn.AvgPool2d(kernel_size=(512,1024))
for i_iter in range(args.num_steps):
model.train()
loss_lse_target_value = 0
loss_seg_value1 = 0
loss_adv_target_value1 = 0
loss_D_value1 = 0
loss_seg_value2 = 0
loss_adv_target_value2 = 0
loss_D_value2 = 0
optimizer.zero_grad()
adjust_learning_rate(optimizer, i_iter)
optimizer_D1.zero_grad()
optimizer_D2.zero_grad()
adjust_learning_rate_D(optimizer_D1, i_iter)
adjust_learning_rate_D(optimizer_D2, i_iter)
for sub_i in range(args.iter_size):
# train G
# don't accumulate grads in D
for param in model_D1.parameters():
param.requires_grad = False
for param in model_D2.parameters():
param.requires_grad = False
# train with source
_, batch = next(trainloader_iter)
images, labels, class_label_source, mask_weakly, _, name = batch
images = Variable(images).cuda(args.gpu)
pred1, pred2 = model(images)
pred1 = interp(pred1)
pred2 = interp(pred2)
loss_seg1 = loss_calc(pred1, labels, args.gpu)
loss_seg2 = loss_calc(pred2, labels, args.gpu)
loss = loss_seg2 + args.lambda_seg * loss_seg1
# proper normalization
loss = loss / args.iter_size
loss.backward()
loss_seg_value1 += loss_seg1.data.item() / args.iter_size
loss_seg_value2 += loss_seg2.data.item() / args.iter_size
# train with target
_, batch = next(targetloader_iter)
images, class_label, _, _ = batch
images = Variable(images).cuda(args.gpu)
pred_target1, pred_target2 = model(images)
pred_target1 = interp_target(pred_target1)
pred_target2 = interp_target(pred_target2)
class_label_target_lse = class_label.type(torch.FloatTensor)
exp_target = torch.min(torch.exp(1*pred_target2), Variable(torch.exp(torch.tensor(40.0))).cuda(args.gpu))
lse = (1.0/1) * torch.log(AvePool(exp_target))
loss_lse_target = bce_loss(lse, Variable(class_label_target_lse.reshape(lse.size())).cuda(args.gpu))
D_out1 = model_D1(F.softmax(pred_target1))
D_out2 = model_D2(F.softmax(pred_target2))
loss_adv_target1 = bce_loss(D_out1,
Variable(torch.FloatTensor(D_out1.data.size()).fill_(source_label)).cuda(
args.gpu))
loss_adv_target2 = bce_loss(D_out2,
Variable(torch.FloatTensor(D_out2.data.size()).fill_(source_label)).cuda(
args.gpu))
loss = args.lambda_adv_target1 * loss_adv_target1 + args.lambda_adv_target2 * loss_adv_target2 + 0.2 * loss_lse_target
loss = loss / args.iter_size
loss.backward()
loss_adv_target_value1 += loss_adv_target1.data.item() / args.iter_size
loss_adv_target_value2 += loss_adv_target2.data.item() / args.iter_size
loss_lse_target_value += loss_lse_target.data.item() / args.iter_size
# train D
# bring back requires_grad
for param in model_D1.parameters():
param.requires_grad = True
for param in model_D2.parameters():
param.requires_grad = True
# train with source
pred1 = pred1.detach()
pred2 = pred2.detach()
D_out1 = model_D1(F.softmax(pred1))
D_out2 = model_D2(F.softmax(pred2))
loss_D1 = bce_loss(D_out1,
Variable(torch.FloatTensor(D_out1.data.size()).fill_(source_label)).cuda(args.gpu))
loss_D2 = bce_loss(D_out2,
Variable(torch.FloatTensor(D_out2.data.size()).fill_(source_label)).cuda(args.gpu))
loss_D1 = loss_D1 / args.iter_size / 2
loss_D2 = loss_D2 / args.iter_size / 2
loss_D1.backward()
loss_D2.backward()
loss_D_value1 += loss_D1.data.item()
loss_D_value2 += loss_D2.data.item()
# train with target
pred_target1 = pred_target1.detach()
pred_target2 = pred_target2.detach()
D_out1 = model_D1(F.softmax(pred_target1))
D_out2 = model_D2(F.softmax(pred_target2))
loss_D1 = bce_loss(D_out1,
Variable(torch.FloatTensor(D_out1.data.size()).fill_(target_label)).cuda(args.gpu))
loss_D2 = bce_loss(D_out2,
Variable(torch.FloatTensor(D_out2.data.size()).fill_(target_label)).cuda(args.gpu))
loss_D1 = loss_D1 / args.iter_size / 2
loss_D2 = loss_D2 / args.iter_size / 2
loss_D1.backward()
loss_D2.backward()
loss_D_value1 += loss_D1.data.item()
loss_D_value2 += loss_D2.data.item()
optimizer.step()
optimizer_D1.step()
optimizer_D2.step()
del D_out1, D_out2, pred1, pred2, pred_target1, pred_target2, images, labels
print('exp = {}'.format(args.snapshot_dir))
print(
'iter = {0:8d}/{1:8d}, loss_seg1 = {2:.3f} loss_seg2 = {3:.3f} loss_adv1 = {4:.3f}, loss_adv2 = {5:.3f} loss_D1 = {6:.3f} loss_D2 = {7:.3f} loss_lse_target = {8:.3f}'.format(i_iter, args.num_steps, loss_seg_value1, loss_seg_value2, loss_adv_target_value1, loss_adv_target_value2, loss_D_value1, loss_D_value2, loss_lse_target_value))
if i_iter >= args.num_steps_stop - 1:
print('save model ...')
torch.save(model.state_dict(), osp.join(args.snapshot_dir, 'GTA5_' + str(args.num_steps_stop) + '.pth'))
torch.save(model_D1.state_dict(), osp.join(args.snapshot_dir, 'GTA5_' + str(args.num_steps_stop) + '_D1.pth'))
torch.save(model_D2.state_dict(), osp.join(args.snapshot_dir, 'GTA5_' + str(args.num_steps_stop) + '_D2.pth'))
break
if i_iter % args.save_pred_every == 0 and i_iter != 0:
print('taking snapshot ...')
torch.save(model.state_dict(), osp.join(args.snapshot_dir, 'GTA5_' + str(i_iter) + '.pth'))
hist = np.zeros((19, 19))
# model.cuda(0)
model.eval()
f = open(args.results_dir, 'a')
for index, batch in enumerate(testloader):
print(index)
image, _, _, name = batch
output1, output2 = model(Variable(image, volatile=True).cuda(args.gpu))
pred = interp_val(output2)
pred = pred[0].permute(1,2,0)
pred = torch.max(pred, 2)[1].byte()
pred_cpu = pred.data.cpu().numpy()
del pred, output1, output2
label = Image.open(gt_imgs[index])
label = np.array(label.resize(com_size, Image.NEAREST))
label = label_mapping(label, mapping)
hist += fast_hist(label.flatten(), pred_cpu.flatten(), 19)
# model.cuda(args.gpu)
mIoUs = per_class_iu(hist)
mIoU = round(np.nanmean(mIoUs) * 100, 2)
print(mIoU)
f.write('i_iter:{:d}, miou:{:0.5f} \n'.format(i_iter,mIoU))
f.close()
def main():
"""Create the model and start the evaluation process."""
args = get_arguments()
if not os.path.exists(args.save):
os.makedirs(args.save)
gpu0 = args.gpu
model = Res_Deeplab(num_classes=args.num_classes)
if args.restore_from[:4] == 'http':
saved_state_dict = model_zoo.load_url(args.restore_from)
else:
saved_state_dict = torch.load(args.restore_from)
model.load_state_dict(saved_state_dict)
model.eval()
model.cuda(gpu0)
#===========load discriminator model====begin===
model_d2 = FCDiscriminator(num_classes=args.num_classes)
d2_state_dict = torch.load(args.dis_restore_from)
model_d2.load_state_dict(d2_state_dict)
model_d2.eval()
model_d2.cuda(gpu0)
#===========load discriminator model====end===
testloader = data.DataLoader(cityscapesDataSet(args.data_dir,
args.data_list,
crop_size=(1024, 512),
mean=IMG_MEAN,
scale=False,
mirror=False,
set=args.set),
batch_size=1,
shuffle=False,
pin_memory=True)
interp = nn.Upsample(size=(1024, 2048),
mode='bilinear',
align_corners=True)
# interp_target = nn.Upsample(size=(input_size_target[1], input_size_target[0]), mode='bilinear')
out_values = []
fine_out_values = []
retrain_list = []
file = open(CITYS_RETRAIN_TXT, 'w')
for index, batch in enumerate(testloader):
if index % 20 == 0:
print('%d processd of %d' % (index, len(testloader)))
image, _, name = batch
output1, output2 = model(Variable(image, volatile=True).cuda(gpu0))
ini_output = interp(output2)
d2_out1 = model_d2(F.softmax(ini_output,
dim=1)) #.cpu().data[0].numpy()
out_valu = d2_out1.mean()
out_valu_img = np.array([[name[0]], out_valu.cpu().data.numpy()])
out_values.extend(out_valu_img)
if out_valu.cpu().data.numpy() > 0.64:
fine_out_valu_img = np.array([[name[0]],
out_valu.cpu().data.numpy()])
fine_out_values.extend(fine_out_valu_img)
file.write(name[0] + '\n')
output = interp(output2).cpu().data[0].numpy()
output = output.transpose(1, 2, 0)
output = np.asarray(np.argmax(output, axis=2), dtype=np.uint8)
output_col = colorize_mask(output)
name = name[0].split('/')[-1]
# output_col.save('%s/%s_color.png' % (args.save, name.split('.')[0]))
output_col.save('%s/%s.png' % (args.save, name.split('.')[0]))
# print('its confidence value is %f' % out_valu)
# plt.imshow(output_col)
# plt.title(str(out_valu))
# plt.show()
# output = Image.fromarray(output)
# output.save('%s/%s' % (args.save, name))
out_values = np.array(out_values)
np.save(CITYS_VALUES_SV_PATH, out_values)
np.save(CITYS_FINE_VALUES_SV_PATH, fine_out_values)
file.close()
def main():
city = np.load("dump_cityscape5.npy")
gta = np.load("dump_gta5.npy")
city_scape = city[:1000, :]
gta5 = gta[:1000, :]
combined = np.concatenate((city[1000:, :], gta[1000:, :]))
np.save('source.npy', gta5)
np.save('target.npy', city_scape)
np.save('mixed.npy', combined)
print(city_scape.shape)
print(gta5.shape)
print(combined.shape)
exit()
print(type(dump))
print(dump.shape)
b = dump
print(type(dump))
print(dump.shape)
import random
a = np.stack(random.sample(a, 500))
b = np.stack(random.sample(b, 500))
dump = np.concatenate((a, b))
print(dump.shape)
arr = np.arange(10)
#print(dump)
exit()
"""Create the model and start the evaluation process."""
args = get_arguments()
gpu0 = args.gpu
if not os.path.exists(args.save):
os.makedirs(args.save)
model = Res_Deeplab(num_classes=args.num_classes)
#model = getVGG(num_classes=args.num_classes)
if args.restore_from[:4] == 'http':
saved_state_dict = model_zoo.load_url(args.restore_from)
else:
saved_state_dict = torch.load(args.restore_from)
model.load_state_dict(saved_state_dict)
model.eval()
model.cuda(gpu0)
#trainloader = data.DataLoader(cityscapesDataSet(args.data_dir, args.data_list, crop_size=(1024, 512), mean=IMG_MEAN, scale=False, mirror=False, set=args.set), batch_size=1, shuffle=False, pin_memory=True)
trainloader = data.DataLoader(GTA5DataSet(args.data_dir,
args.data_list,
crop_size=(1024, 512),
mean=IMG_MEAN,
scale=False,
mirror=False),
batch_size=1,
shuffle=False,
pin_memory=True)
trainloader_iter = enumerate(trainloader)
interp = nn.Upsample(size=(1024, 2048), mode='bilinear')
dump_array = np.array((1, 2))
for itr in xrange(2000):
print(itr)
_, batch = trainloader_iter.next()
images, labels, _, _ = batch
#images, _, _ = batch
output1, output2 = model(Variable(images, volatile=True).cuda(gpu0))
import torch.nn.functional as F
output2 = F.avg_pool2d(output2, (4, 4))
output2 = output2.data.cpu().numpy()
output2 = np.reshape(output2, (1, -1))
if dump_array.shape == (2, ):
dump_array = output2
else:
dump_array = np.concatenate((dump_array, output2))
np.save('dump_gta5.npy', dump_array)