def __init__(self, opt):
super(MorphTestData, self).__init__(opt)
from data.custom_dataset_data_loader import CustomDatasetDataLoader
data_loader_test = CustomDatasetDataLoader(self._opt,
is_for_train=False)
self.data_loader_test = data_loader_test.load_data()
def __init__(self):
self._opt = TrainOptions().parse()
data_loader_train = CustomDatasetDataLoader(self._opt, is_for_train=True)
data_loader_test = CustomDatasetDataLoader(self._opt, is_for_train=False)
self._dataset_train = data_loader_train.load_data()
self._dataset_test = data_loader_test.load_data()
self._dataset_train_size = len(data_loader_train)
self._dataset_test_size = len(data_loader_test)
print('#train images = %d' % self._dataset_train_size)
print('#test images = %d' % self._dataset_test_size)
self._model = ModelsFactory.get_by_name(self._opt.model, self._opt)
self._tb_visualizer = TBVisualizer(self._opt)
self._train()
def __init__(self):
self._opt = TrainOptions().parse()
data_loader_train = CustomDatasetDataLoader(self._opt, is_for_train=True)
data_loader_test = CustomDatasetDataLoader(self._opt, is_for_train=False)
self._dataset_train = data_loader_train.load_data()
self._dataset_test = data_loader_test.load_data()
self._dataset_train_size = len(data_loader_train)
self._dataset_test_size = len(data_loader_test)
print('#train images = %d' % self._dataset_train_size)
print('#test images = %d' % self._dataset_test_size)
self._model = ModelsFactory.get_by_name(self._opt.model, self._opt)
self._tb_visualizer = TBVisualizer(self._opt)
self._train()
def __init__(self):
self._opt = TrainOptions().parse()
data_loader_train = CustomDatasetDataLoader(self._opt,
is_for_train=True)
data_loader_test = CustomDatasetDataLoader(self._opt,
is_for_train=False)
self._dataset_train = data_loader_train.load_data()
self._dataset_test = data_loader_test.load_data()
self._dataset_train_size = len(data_loader_train)
self._dataset_test_size = len(data_loader_test)
print('#train video clips = %d' % self._dataset_train_size)
print('#test video clips = %d' % self._dataset_test_size)
self._model = Impersonator(self._opt)
self._tb_visualizer = TBVisualizer(self._opt)
self._train()
def __init__(self):
self._opt = TrainOptions().parse()
self._model = ModelsFactory.get_by_name(self._opt.model, self._opt)
self._tb_visualizer = TBVisualizer(self._opt)
data_loader_train = CustomDatasetDataLoader(self._opt, mode='train')
data_loader_val = CustomDatasetDataLoader(self._opt, mode='val')
#data_loader_train = CustomDatasetDataLoader(self._opt, mode='test')
#data_loader_val = CustomDatasetDataLoader(self._opt, mode='test')
self._dataset_train = data_loader_train.load_data()
self._dataset_val = data_loader_val.load_data()
self._dataset_train_size = len(data_loader_train)
self._dataset_val_size = len(data_loader_val)
print('#train images = %d' % self._dataset_train_size)
print('#val images = %d' % self._dataset_val_size)
self._train()
def __init__(self):
self._opt = TrainOptions().parse()
data_loader_train = CustomDatasetDataLoader(self._opt,
is_for_train=True)
data_loader_test = CustomDatasetDataLoader(self._opt,
is_for_train=False)
self._dataset_train = data_loader_train.load_data()
self._dataset_test = data_loader_test.load_data()
self._dataset_train_size = len(data_loader_train)
self._dataset_test_size = len(data_loader_test)
print('#train images = %d' % self._dataset_train_size)
print('#test images = %d' % self._dataset_test_size)
print('TRAIN IMAGES FOLDER = %s' %
data_loader_train._dataset._imgs_dir)
print('TEST IMAGES FOLDER = %s' % data_loader_test._dataset._imgs_dir)
self._model = ModelsFactory.get_by_name(self._opt.model, self._opt)
self._tb_visualizer = TBVisualizer(self._opt)
self._writer = SummaryWriter()
self._input_imgs = torch.empty(0, 3, self._opt.image_size,
self._opt.image_size)
self._fake_imgs = torch.empty(0, 3, self._opt.image_size,
self._opt.image_size)
self._rec_real_imgs = torch.empty(0, 3, self._opt.image_size,
self._opt.image_size)
self._fake_imgs_unmasked = torch.empty(0, 3, self._opt.image_size,
self._opt.image_size)
self._fake_imgs_mask = torch.empty(0, 3, self._opt.image_size,
self._opt.image_size)
self._rec_real_imgs_mask = torch.empty(0, 3, self._opt.image_size,
self._opt.image_size)
self._cyc_imgs_unmasked = torch.empty(0, 3, self._opt.image_size,
self._opt.image_size)
self._real_conds = list()
self._desired_conds = list()
self._train()
#!/usr/bin/env python
# coding=utf-8
import time
from options.train_options import TrainOptions # finish
from data.custom_dataset_data_loader import CustomDatasetDataLoader # finish
from models.models import create_model # finish
from util.visualizer import Visualizer # finish
from util.recorder import Recorder # finish
opt = TrainOptions().parse()
train_loader = CustomDatasetDataLoader(opt, 'train')
#val_loader = CustomDatasetDataLoader(opt, 'val')
train_dataset = train_loader.load_data()
#val_dataset = val_loader.load_data()
dataset_size = len(train_loader)
print(('#training images = %d' % dataset_size))
model = create_model(opt)
visualizer = Visualizer(opt)
recorder = Recorder()
total_steps = 0
for epoch in range(opt.epoch_count, opt.schedule_max + 1):
epoch_start_time = time.time()
epoch_iter = 0
for i, data in enumerate(train_dataset):
iter_start_time = time.time()
total_steps += opt.batchSize
epoch_iter += opt.batchSize
def __init__(self):
# TO GET THEM:
# clusters_pose_map, clusters_rot_map, clusters_root_rot = self.get_rot_map(self._model.clusters_tensor, torch.zeros((25, 3)).cuda())
#for i in range(25):
# import matplotlib.pyplot
# from mpl_toolkits.mplot3d import Axes3D
# ax = matplotlib.pyplot.figure().add_subplot(111, projection='3d')
# #i = 0
# add_group_meshs(ax, cluster_verts[i].cpu().data.numpy(), hand_faces, c='b')
# cam_equal_aspect_3d(ax, cluster_verts[i].cpu().data.numpy())
# print(i)
# matplotlib.pyplot.pause(1)
# matplotlib.pyplot.close()
# FINGER LIMIT ANGLE:
#self.limit_bigfinger = torch.FloatTensor([1.0222, 0.0996, 0.7302]) # 36:39
#self.limit_bigfinger = torch.FloatTensor([1.2030, 0.12, 0.25]) # 36:39
#self.limit_bigfinger = torch.FloatTensor([1.2, -0.4, 0.25]) # 36:39
self.limit_bigfinger = torch.FloatTensor([1.2, -0.6, 0.25]) # 36:39
self.limit_index = torch.FloatTensor([-0.0827, -0.4389, 1.5193]) # 0:3
self.limit_middlefinger = torch.FloatTensor(
[-2.9802e-08, -7.4506e-09, 1.4932e+00]) # 9:12
self.limit_fourth = torch.FloatTensor([0.1505, 0.3769,
1.5090]) # 27:30
self.limit_small = torch.FloatTensor([-0.6235, 0.0275,
1.0519]) # 18:21
if torch.cuda.is_available():
self.limit_bigfinger = self.limit_bigfinger.cuda()
self.limit_index = self.limit_index.cuda()
self.limit_middlefinger = self.limit_middlefinger.cuda()
self.limit_fourth = self.limit_fourth.cuda()
self.limit_small = self.limit_small.cuda()
self._bigfinger_vertices = [
697, 698, 699, 700, 701, 702, 703, 704, 705, 706, 707, 708, 709,
710, 711, 712, 713, 714, 715, 716, 717, 718, 719, 720, 721, 722,
723, 724, 725, 726, 727, 728, 729, 730, 731, 732, 733, 734, 735,
736, 737, 738, 739, 740, 741, 742, 743, 744, 745, 746, 747, 748,
749, 750, 751, 752, 753, 754, 755, 756, 757, 758, 759, 760, 761,
762, 763, 764, 765, 766, 767, 768
]
self._indexfinger_vertices = [
46, 47, 48, 49, 56, 57, 58, 59, 86, 87, 133, 134, 155, 156, 164,
165, 166, 167, 174, 175, 189, 194, 195, 212, 213, 221, 222, 223,
224, 225, 226, 237, 238, 272, 273, 280, 281, 282, 283, 294, 295,
296, 297, 298, 299, 300, 301, 302, 303, 304, 305, 306, 307, 308,
309, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321,
322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 333, 334,
335, 336, 337, 338, 339, 340, 341, 342, 343, 344, 345, 346, 347,
348, 349, 350, 351, 352, 353, 354, 355
]
self._middlefinger_vertices = [
356, 357, 358, 359, 360, 361, 362, 363, 364, 365, 366, 367, 372,
373, 374, 375, 376, 377, 381, 382, 385, 386, 387, 388, 389, 390,
391, 392, 393, 394, 395, 396, 397, 398, 400, 401, 402, 403, 404,
405, 406, 407, 408, 409, 410, 411, 412, 413, 414, 415, 416, 417,
418, 419, 420, 421, 422, 423, 424, 425, 426, 427, 428, 429, 430,
431, 432, 433, 434, 435, 436, 437, 438, 439, 440, 441, 442, 443,
444, 445, 446, 447, 448, 449, 450, 451, 452, 453, 454, 455, 456,
457, 458, 459, 460, 461, 462, 463, 464, 465, 466, 467
]
self._fourthfinger_vertices = [
468, 469, 470, 471, 472, 473, 474, 475, 476, 477, 478, 479, 482,
483, 484, 485, 486, 487, 491, 492, 495, 496, 497, 498, 499, 500,
501, 502, 503, 504, 505, 506, 507, 508, 511, 512, 513, 514, 515,
516, 517, 518, 519, 520, 521, 522, 523, 524, 525, 526, 527, 528,
529, 530, 531, 532, 533, 534, 535, 536, 537, 538, 539, 540, 541,
542, 543, 544, 545, 546, 547, 548, 549, 550, 551, 552, 553, 554,
555, 556, 557, 558, 559, 560, 561, 562, 563, 564, 565, 566, 567,
568, 569, 570, 571, 572, 573, 574, 575, 576, 577, 578
]
self._smallfinger_vertices = [
580, 581, 582, 583, 584, 585, 586, 587, 588, 589, 590, 591, 598,
599, 600, 601, 602, 603, 609, 610, 613, 614, 615, 616, 617, 618,
619, 620, 621, 622, 623, 624, 625, 626, 628, 629, 630, 631, 632,
633, 634, 635, 636, 637, 638, 639, 640, 641, 642, 643, 644, 645,
646, 647, 648, 649, 650, 651, 652, 653, 654, 655, 656, 657, 658,
659, 660, 661, 662, 663, 664, 665, 666, 667, 668, 669, 670, 671,
672, 673, 674, 675, 676, 677, 678, 679, 680, 681, 682, 683, 684,
685, 686, 687, 688, 689, 690, 691, 692, 693, 694, 695
]
self._opt = TestOptions().parse()
#assert self._opt.load_epoch > 0, 'Use command --load_epoch to indicate the epoch you want to load - and choose a trained model'
# Let's set batch size at 2 since we're only getting one image so far
self._opt.batch_size = 1
self._opt.n_threads_train = self._opt.n_threads_test
data_loader_test = CustomDatasetDataLoader(self._opt, mode='test')
self._dataset_test = data_loader_test.load_data()
self._dataset_test_size = len(data_loader_test)
print('#test images = %d' % self._dataset_test_size)
self._model = ModelsFactory.get_by_name(self._opt.model, self._opt)
self._tb_visualizer = TBVisualizer(self._opt)
self._total_steps = self._dataset_test_size
self._display_visualizer_test(20, self._total_steps)
from tqdm import tqdm
import numpy as np
import torch
from models.base_model import BaseModel
opt = TestOptions().parse()
opt.nThreads = 1
opt.batchSize = 1
opt.serial_batches = True
opt.no_flip = True
opt.isTrain = False
opt.max_dataset_size = float("inf")
data_loader = CustomDatasetDataLoader(opt)
dataset = data_loader.load_data()
model = BaseModel(opt)
L1s = []
SSIMs = []
with torch.no_grad():
for idx, data in enumerate(tqdm(dataset)):
ida = data['id_a'][0].split('_')
idb = data['id_b'][0].split('_')
assert (ida[0] == idb[0])
model_id = ida[0]
ida = '_'.join(ida[1:])
idb = '_'.join(idb[1:])
def main_task():
# define params
opt = BaseOptions().parse()
iter_path = os.path.join(opt.checkpoints_dir, 'iter.txt')
ioupath_path = os.path.join(opt.checkpoints_dir, 'MIoU.txt')
# load training data
if opt.continue_train:
try:
start_epoch, epoch_iter = np.loadtxt(iter_path,
delimiter=',',
dtype=int)
except:
start_epoch, epoch_iter = 1, 0
try:
best_iou = np.loadtxt(ioupath_path, dtype=float)
except:
best_iou = 0.
else:
start_epoch, epoch_iter = 1, 0
best_iou = 0.
os.environ["CUDA_VISIBLE_DEVICES"] = str(opt.gpu_ids[0])
# define data mode
data_loader = CustomDatasetDataLoader()
data_loader.initialize(opt)
dataset, dataset_val = data_loader.load_data()
dataset_size = len(dataset)
# define model
model = Deeplab_Solver(opt)
total_steps = (start_epoch - 1) * dataset_size + epoch_iter
print("starting training model......")
for epoch in range(start_epoch, opt.nepochs):
if epoch != start_epoch:
epoch_iter = epoch_iter % dataset_size
# for train
opt.isTrain = True
model.model.train()
for i, data in enumerate(dataset, start=epoch_iter):
total_steps += opt.batchSize
epoch_iter += opt.batchSize
# keep time to watch how times each one epoch
epoch_start_time = time.time()
# forward and backward pass
model.forward(data, isTrain=True)
model.backward(total_steps,
opt.nepochs * dataset_size * opt.batchSize + 1)
# save latest model
if total_steps % opt.save_latest_freq == 0:
print('saving the latest model (epoch %d, total_steps %d)' %
(epoch, total_steps))
model.save('latest')
np.savetxt(iter_path, (epoch, epoch_iter),
delimiter=',',
fmt='%d')
if model.trainingavgloss < 0.010:
break
# for eval
opt.isTrain = False
model.model.eval()
if dataset_val != None:
label_trues, labels_preds = [], []
for i, data in enumerate(dataset_val):
seggt, segpred = model.forward(data, isTrain=False)
seggt = seggt.data.cpu().numpy()
segpred = segpred.data.cpu().numpy()
label_trues.append(seggt)
labels_preds.append(segpred)
metrics = util.label_accuracy_score(label_trues,
labels_preds,
n_class=opt.label_nc)
metrics *= 100
print('''\
Validation:
Accuracy: {0}
AccuracyClass: {1}
MeanIOU: {2}
FWAVAccuracy: {3}
'''.format(*metrics))
# save model for best
if metrics[2] > best_iou:
best_iou = metrics[2]
model.save('best')
print('end of epoch %d / %d \t Time Taken: %d sec' %
(epoch + 1, opt.nepochs, time.time() - epoch_start_time))
from options.train_options import TrainOptions
from data.custom_dataset_data_loader import CustomDatasetDataLoader
from util.visualizer import Visualizer
import copy
from tqdm import tqdm
import numpy as np
import torch
from models.base_model import BaseModel
torch.manual_seed(0)
opt = TrainOptions().parse()
data_loader = CustomDatasetDataLoader(opt)
dataset = data_loader.load_data()
opt_for_eval = copy.deepcopy(opt)
opt_for_eval.isTrain = False
opt_for_eval.max_dataset_size = 1000
val_loader = CustomDatasetDataLoader(opt_for_eval)
valset = val_loader.load_data()
dataset_size = len(data_loader)
print('#training samples = %d' % dataset_size)
model = BaseModel(opt)
visualizer = Visualizer(opt)
total_steps = 0
