def generate_model(opt):
assert opt.model in ['resnext']
assert opt.model_depth in [101]
from models.resnext import get_fine_tuning_parameters
model = resnext.resnet101(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
input_channels=opt.input_channels,
output_layers=opt.output_layers)
model = model.cuda()
model = nn.DataParallel(model)
if opt.pretrain_path:
print('loading pretrained model {}'.format(opt.pretrain_path))
pretrain = torch.load(opt.pretrain_path)
assert opt.arch == pretrain['arch']
model.load_state_dict(pretrain['state_dict'])
model.module.fc = nn.Linear(model.module.fc.in_features,
opt.n_finetune_classes)
model.module.fc = model.module.fc.cuda()
parameters = get_fine_tuning_parameters(model, opt.ft_begin_index)
return model, parameters
return model, model.parameters()
def main():
# torch.cuda.set_device(1)
os.environ["CUDA_VISIBLE_DEVICES"] = "1"
opt = parse_opts()
model = resnext.resnet101(
num_classes=opt.n_finetune_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
model.cuda()
# print(model.cuda())
model = nn.DataParallel(model, device_ids=None)
checkpoint = torch.load(
'trained_models/best-4-1.pth.tar')
model.load_state_dict(checkpoint['state_dict'])
best_score = checkpoint['best_prec1']
print(best_score)
# for param_group in optimizer['param_groups']:
# print(param_group)
# model.cpu()
# model.cuda()
model.eval()
rgb_mean = [0.485, 0.456, 0.406]
rgb_std = [0.229, 0.224, 0.225]
opt.scales = [1]
transform_val = Compose([
MultiScaleCornerCrop(opt.scales, opt.sample_size,
crop_positions=['c']),
ToTensor(),
Normalize(rgb_mean, rgb_std),
])
def generate_model(opt):
assert opt.model in ['mfnet', 'resnext', 'resnet']
opt.cbam = 0
if opt.model == 'mfnet':
if opt.mult_loss:
model = MFNET_3D_T(opt)
elif opt.time_focus:
model = MFNET_3D_C(opt)
#elif opt.mv:
# model = MFNET_MV(opt)
elif opt.small:
model = MFNET_3D_S(opt)
pretrain = torch.load(opt.pretrain_path)
compressed_dict = compress_dict(pretrain, opt)
model.cuda()
model = nn.DataParallel(model)
model.load_state_dict(compressed_dict, strict=True)
else:
model = MFNET_3D(opt.n_classes)
elif opt.model == 'resnext':
model = resnext.resnet101(opt)
elif opt.model == 'resnet':
model = resnet.resnet101(opt)
if opt.mult_loss:
param = model.student_model.parameters()
else:
param = model.parameters()
return model, param
def build_resnext():
model = resnext.resnet101(num_classes=400, shortcut_type='B', cardinality=32,
sample_size=112, sample_duration=16,
last_fc=False)
model = model.cuda()
model = nn.DataParallel(model, device_ids=None)
assert os.path.exists('data/preprocess/pretrained/resnext-101-kinetics.pth')
model_data = torch.load('data/preprocess/pretrained/resnext-101-kinetics.pth', map_location='cpu')
model.load_state_dict(model_data['state_dict'])
model.eval()
return model
def generate_model(opt):
assert opt.model in ['resnext']
assert opt.model_depth in [101]
model = resnext.resnet101(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
input_channels=opt.input_channels,
output_layers=opt.output_layers)
if opt.MARS_premodel_path != '' and opt.input_channels == 3:
print('loading pretrained model {}'.format(opt.MARS_premodel_path))
para_dict, _ = fluid.dygraph.load_dygraph(opt.MARS_premodel_path)
#设置网络模型参数为读取的模型参数
model.set_dict(para_dict)
model.fc = fluid.dygraph.Linear(
model.lastfeature_size,
opt.n_finetune_classes,
param_attr=fluid.ParamAttr(
initializer=fluid.initializer.MSRAInitializer(uniform=True)),
bias_attr=paddle.fluid.ParamAttr(initializer=None),
act="softmax")
parameters = get_fine_tuning_parameters(model, opt.ft_begin_index)
return model, parameters
elif opt.Flow_premodel_path != '' and opt.input_channels == 2:
print('loading pretrained model {}'.format(opt.Flow_premodel_path))
para_dict, _ = fluid.dygraph.load_dygraph(opt.Flow_premodel_path)
#设置网络模型参数为读取的模型参数
model.set_dict(para_dict)
model.fc = fluid.dygraph.Linear(
model.lastfeature_size,
opt.n_finetune_classes,
param_attr=fluid.ParamAttr(
initializer=fluid.initializer.MSRAInitializer(uniform=True)),
bias_attr=paddle.fluid.ParamAttr(initializer=None),
act="softmax")
parameters = get_fine_tuning_parameters(model, opt.ft_begin_index)
return model, parameters
elif opt.RGB_premodel_path != '' and opt.input_channels == 3:
print('loading pretrained model {}'.format(opt.RGB_premodel_path))
para_dict, _ = fluid.dygraph.load_dygraph(opt.RGB_premodel_path)
#设置网络模型参数为读取的模型参数
model.set_dict(para_dict)
model.fc = fluid.dygraph.Linear(
model.lastfeature_size,
opt.n_finetune_classes,
param_attr=fluid.ParamAttr(
initializer=fluid.initializer.MSRAInitializer(uniform=True)),
bias_attr=paddle.fluid.ParamAttr(initializer=None),
act="softmax")
parameters = get_fine_tuning_parameters(model, opt.ft_begin_index)
return model, parameters
return model, model.parameters()
def test_on_testset():
os.environ["CUDA_VISIBLE_DEVICES"] = "1"
args = parse_opts()
data_loader = get_iterator(args, isTrain=False)
acc_meter = tnt.meter.AverageValueMeter()
model = resnext.resnet101(num_classes=args.n_finetune_classes,
shortcut_type=args.resnet_shortcut,
cardinality=args.resnext_cardinality,
sample_size=args.sample_size,
sample_duration=args.sample_duration)
model.cuda()
model = nn.DataParallel(model, device_ids=None)
model.load_state_dict(
torch.load('trained_models/checkpoint.pth.tar')['state_dict'])
model.eval()
total = 0
result = {}
with torch.no_grad():
for data in data_loader:
input = data[0].cuda()
label = data[1].cuda()
video_id = data[2]
output = torch.sigmoid(model(input))
label_indexes = (label == 1)
acc, bt, _ = calculate_accuracy(output,
label,
video_id=video_id,
thresh_hold=0.4)
for i, vid in enumerate(video_id):
if vid not in result:
result[vid] = []
result[vid].append(
label_indexes[i].nonzero().squeeze(1).tolist())
if sum(output[i] > 0.4) > 0:
indexes = (output[i] > 0.4)
else:
indexes = (output[i] >= output[i].max(0)[0])
tmp_index = indexes.nonzero()
if len(tmp_index) <= 0:
indx = []
else:
indx = indexes.nonzero().squeeze(1).tolist()
result[vid].append(indx)
total += bt
acc_meter.add(acc, bt)
print(
'Now tested %d samples,batch Average Acc is %.4f, Average Acc is %.4f'
% (total, acc / bt, acc_meter.value()[0]))
# print(result)
torch.save(result, './result14-0.4-max.pkl')
def generate_model():
from models.resnext import get_fine_tuning_parameters
model = resnext.resnet101(num_classes=51,
shortcut_type='B',
cardinality=32,
sample_size=112,
sample_duration=64,
input_channels=3)
model = model.cuda()
model = nn.DataParallel(model)
return model
def main():
opt = parse_opts()
model = resnext.resnet101(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
model.load_state_dict(torch.load('./trained_models/best.pth.tar'))
model = model.cuda()
model = nn.DataParallel(model, device_ids=[0])
clip = video_loader(
root_path='/home/zengh/Dataset/AIChallenger/test/group0/1000007124',
frame_indices=range(16))
indexes = test(clip, model)
print(indexes)
def main(args):
device = 'cuda'
print('Loading ResNext101 model...')
model = nn.DataParallel(resnet101(sample_duration=16).cuda())
model.load_state_dict(torch.load('resnext-101-kinetics.pth')['state_dict'])
print('Loading video paths...')
if args.dataset == 'uva':
files = glob.glob(args.data_path + '/*.mp4')
data_type = 'video'
else:
raise NotImplementedError
mu, sigma = fid.calculate_activation_statistics(files, data_type, model, args.batch_size, args.size, args.length, args.dims, device)
np.savez_compressed('./stats/'+args.dataset+'.npz', mu=mu, sigma=sigma)
print('finished')
def calculate_fid_given_paths(paths, batch_size, size, length, dims, device):
"""
calculates the fid of two paths
"""
for p in paths:
if not os.path.exists(p):
raise RuntimeError('Invalid path: %s' % p)
model = nn.DataParallel(resnet101(sample_duration=16).cuda())
model.load_state_dict(torch.load('resnext-101-kinetics.pth')['state_dict'])
m1, s1 = _compute_statistics_of_path(paths[0], model, batch_size, size, length, dims, device)
m2, s2 = _compute_statistics_of_path(paths[1], model, batch_size, size, length, dims, device)
fid_value = calculate_frechet_distance(m1, s1, m2, s2)
return fid_value
def initial_model():
opt = parse_opts()
model = resnext.resnet101(num_classes=opt.n_finetune_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
model = model.cuda()
model = nn.DataParallel(model, device_ids=None)
model_path = './trained_models/best.pth10.tar'
if not os.path.exists(model_path):
print("model path is not true!!")
return
model.load_state_dict(
torch.load('./trained_models/best.pth10.tar')['state_dict'])
model.eval()
return model
def get_model():
# os.environ["CUDA_VISIBLE_DEVICES"] = "1"
opt = parse_opts()
model = resnext.resnet101(
num_classes=opt.n_finetune_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
model.cuda()
# print(model.cuda())
model = nn.DataParallel(model, device_ids=None)
model.load_state_dict(torch.load(
'./trained_models/best.pth10.tar')['state_dict'])
model.cpu()
# model.cuda()
model.eval()
rgb_mean = [0.485, 0.456, 0.406]
rgb_std = [0.229, 0.224, 0.225]
opt.scales = [1]
return model
def generate_model(opt):
load_device = 'cuda' if torch.cuda.is_available() else 'cpu'
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
assert opt.model in ['resnext']
assert opt.model_depth in [101]
#########################
# Define the model
#########################
model = resnext.resnet101(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality, # resnet cardinality
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
input_channels=opt.input_channels,
output_layers=opt.output_layers)
model = model.to(device)
model = nn.DataParallel(model)
### If use pretrained
if opt.pretrain_path:
from models.resnext import get_fine_tuning_parameters
print('loading pretrained model {}'.format(opt.pretrain_path))
pretrain = torch.load(opt.pretrain_path, map_location=load_device)
assert opt.arch == pretrain['arch']
model.load_state_dict(pretrain['state_dict'])
model.module.fc = nn.Linear(model.module.fc.in_features,
opt.n_finetune_classes)
model.module.fc = model.module.fc.to(device)
parameters = get_fine_tuning_parameters(model, opt.ft_begin_index)
return model, parameters
# print("!"*50, '\n', model, '\n', "!"*50)
return model, model.parameters()
def predict(model, sindex):
start_time = time.time()
opt = parse_opts()
model = resnext.resnet101(num_classes=opt.n_finetune_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
model = model.cuda()
model = nn.DataParallel(model, device_ids=None)
model.load_state_dict(
torch.load('./trained_models/best.pth.tar')['state_dict'])
duration = (time.time() - start_time) * 1000
print('restore time %.3f ms' % duration)
model.eval()
rgb_mean = [0.485, 0.456, 0.406]
rgb_std = [0.229, 0.224, 0.225]
opt.scales = [1]
transform_val = Compose([
MultiScaleCornerCrop(opt.scales, opt.sample_size,
crop_positions=['c']),
ToTensor(),
Normalize(rgb_mean, rgb_std),
])
start_time = time.time()
clip = video_loader(
root_path='/home/zengh/Dataset/AIChallenger/train/group5/567700300',
frame_indices=range(3, 19),
transform=transform_val)
clip = clip.unsqueeze(0)
#print("clip",clip)
duration = (time.time() - start_time) * 1000
print('pic time %.3f ms' % duration)
#print("clip",clip.shape)
start_time = time.time()
indexes = test(clip, model)
duration = (time.time() - start_time) * 1000
print('pre time %.3f ms' % duration)
def generate_model(opt):
assert opt.model in ['resnet', 'resnext']
if opt.model == 'resnet':
assert opt.model_depth in [10, 18, 34, 50, 101, 152, 200]
from models.resnet import get_fine_tuning_parameters
if opt.model_depth == 10:
model = resnet.resnet10(opt=opt)
elif opt.model_depth == 18:
model = resnet.resnet18(opt=opt)
elif opt.model_depth == 34:
model = resnet.resnet34(opt=opt)
elif opt.model_depth == 50:
model = resnet.resnet50(opt=opt)
elif opt.model_depth == 101:
model = resnet.resnet101(opt=opt)
elif opt.model_depth == 152:
model = resnet.resnet152(opt=opt)
elif opt.model_depth == 200:
model = resnet.resnet200(opt=opt)
elif opt.model == 'resnext':
assert opt.model_depth in [50, 101, 152]
from models.resnext import get_fine_tuning_parameters
if opt.model_depth == 50:
model = resnext.resnet50(opt=opt)
elif opt.model_depth == 101:
model = resnext.resnet101(opt=opt)
elif opt.model_depth == 152:
model = resnext.resnet152(opt=opt)
if not opt.no_cuda:
model = model.cuda()
return model, model.parameters()
def load_pretrained_resnet101(opt):
# construct model architecture
model = resnext.resnet101(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
model = model.cuda()
# wrap the current model again in nn.DataParallel / or we can just remove the .module keys.
model = nn.DataParallel(model, device_ids=None)
# Note: please ccustomize the pretrained model path
pretrain = torch.load(opt.pretrained_model_path)
pretrain_dict = pretrain['state_dict']
# do not load the last layer
pretrain_dict.pop('module.fc.weight')
pretrain_dict.pop('module.fc.bias')
model_dict = model.state_dict()
model_dict.update(pretrain_dict)
model.load_state_dict(model_dict)
return model
import paddle.fluid as fluid
from collections import OrderedDict
torch_weight = torch.load('RGB_Kinetics_16f.pth',map_location=torch.device('cpu'))#这里需要改成你下载的torch的权重的位置!!
for torch_key in torch_weight['state_dict'].keys():
print(torch_key)
from models import resnext
with fluid.dygraph.guard():
# 这里提供的参数示例是从Kinetics400预训练模型转化,下面三个分别是对RGB stream、Flow stream、MARS stream进行转化
# paddle_model = resnext.resnet101(num_classes=400,shortcut_type='B',cardinality=32,
# sample_size=112,sample_duration=16,input_channels=3,output_layers=[],curr_mode='RGB'
# paddle_model = resnext.resnet101(num_classes=400,shortcut_type='B',cardinality=32,
# sample_size=112,sample_duration=16,input_channels=2,output_layers=[],curr_mode='Flow'
# paddle_model = resnext.resnet101(num_classes=400,shortcut_type='B',cardinality=32,
# sample_size=112,sample_duration=16,input_channels=3,output_layers=[],curr_mode='MARS'
paddle_model = resnext.resnet101(parameter) # 这里需要对照训练过程传入的参数进行设置
paddle_weight = paddle_model.state_dict()
for paddle_key in paddle_weight:
print(paddle_key)
paddle_weight = paddle_model.state_dict()
new_weight_dict = OrderedDict()
for torch_key, paddle_key in zip(torch_weight['state_dict'].keys(), paddle_weight.keys()):
if torch_key.find('fc') > -1:
# paddle的fc层的weight与竞品不太一致，需要转置一下
new_weight_dict[paddle_key] = torch_weight['state_dict'][torch_key].detach().numpy().T
else:
new_weight_dict[paddle_key] = torch_weight['state_dict'][torch_key].detach().numpy()
paddle_model.set_dict(new_weight_dict)
fluid.dygraph.save_dygraph(paddle_model.state_dict(),"RGB_Kinetics_16f")#修改成自己的预训练模型
print('OK!!!')
def generate_model(opt):
assert opt.model in [
'resnet', 'preresnet', 'wideresnet', 'resnext', 'resnext_fa', 'densenet', 'p3d'
]
if opt.model == 'resnet':
assert opt.model_depth in [10, 18, 34, 50, 101, 152, 200]
from models.resnet import get_fine_tuning_parameters
if opt.model_depth == 10:
model = resnet.resnet10(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 18:
model = resnet.resnet18(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 34:
model = resnet.resnet34(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 50:
model = resnet.resnet50(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 101:
model = resnet.resnet101(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 152:
model = resnet.resnet152(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 200:
model = resnet.resnet200(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'wideresnet':
assert opt.model_depth in [50]
from models.wide_resnet import get_fine_tuning_parameters
if opt.model_depth == 50:
model = wide_resnet.resnet50(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
k=opt.wide_resnet_k,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'p3d':
assert opt.model_depth in [50, 101, 152]
if opt.model_depth == 50:
model = p3d.P3D63(num_classes=opt.n_classes)
elif opt.model_depth == 101:
model = p3d.P3D131(num_classes=opt.n_classes)
elif opt.model_depth == 152:
model = p3d.P3D199(num_classes=opt.n_classes)
elif opt.model == 'resnext':
assert opt.model_depth in [50, 101, 152]
from models.resnext_fa import get_fine_tuning_parameters
if opt.model_depth == 50:
model = resnext.resnet50(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 101:
model = resnext.resnet101(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 152:
model = resnext.resnet152(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'resnext_fa':
assert opt.model_depth in [50, 101, 152]
from models.resnext_fa import get_fine_tuning_parameters, get_fine_tuning_parameters_fa
if opt.model_depth == 50:
model = resnext_fa.resnet50(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 101:
model = resnext_fa.resnet101(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 152:
model = resnext_fa.resnet152(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'preresnet':
assert opt.model_depth in [18, 34, 50, 101, 152, 200]
from models.pre_act_resnet import get_fine_tuning_parameters
if opt.model_depth == 18:
model = pre_act_resnet.resnet18(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 34:
model = pre_act_resnet.resnet34(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 50:
model = pre_act_resnet.resnet50(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 101:
model = pre_act_resnet.resnet101(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 152:
model = pre_act_resnet.resnet152(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 200:
model = pre_act_resnet.resnet200(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'densenet':
assert opt.model_depth in [121, 169, 201, 264]
from models.densenet import get_fine_tuning_parameters
if opt.model_depth == 121:
model = densenet.densenet121(
num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 169:
model = densenet.densenet169(
num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 201:
model = densenet.densenet201(
num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 264:
model = densenet.densenet264(
num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
if not opt.no_cuda:
model = model.cuda()
model = nn.DataParallel(model, device_ids=None)
if opt.pretrain_path:
print('loading pretrained model {}'.format(opt.pretrain_path))
pretrain = torch.load(opt.pretrain_path)
#pdb.set_trace();
#assert opt.arch == pretrain['arch']
model_dict = model.state_dict();
#pdb.set_trace();
model_dict.update(pretrain['state_dict']);
model.load_state_dict(model_dict);
#model.load_state_dict(pretrain['state_dict'])
if opt.model == 'densenet':
model.module.classifier = nn.Linear(
model.module.classifier.in_features, opt.n_finetune_classes)
model.module.classifier = model.module.classifier.cuda()
# do not need to add new fc layer when finetuning model has the same class num
elif (opt.n_classes != opt.n_finetune_classes):
model.module.fc = nn.Linear(model.module.fc.in_features,
opt.n_finetune_classes)
model.module.fc = model.module.fc.cuda()
if (opt.model == 'resnext_fa'):
parameters = get_fine_tuning_parameters_fa(model, opt.learning_rate)
else:
parameters = get_fine_tuning_parameters(model, opt.ft_begin_index)
return model, parameters
else:
if opt.pretrain_path:
print('loading pretrained model {}'.format(opt.pretrain_path))
pretrain = torch.load(opt.pretrain_path)
assert opt.arch == pretrain['arch']
model.load_state_dict(pretrain['state_dict'])
if opt.model == 'densenet':
model.classifier = nn.Linear(
model.classifier.in_features, opt.n_finetune_classes)
else:
model.fc = nn.Linear(model.fc.in_features,
opt.n_finetune_classes)
parameters = get_fine_tuning_parameters(model, opt.ft_begin_index)
return model, parameters
return model, model.parameters()
def get_model(config):
assert config.model in [
'i3d', 'resnet', 'preresnet', 'wideresnet', 'resnext', 'densenet'
]
print('Initializing {} model (num_classes={})...'.format(
config.model, config.num_classes))
if config.model == 'i3d':
from models.i3d import get_fine_tuning_parameters
model = InceptionI3D(num_classes=config.num_classes,
spatial_squeeze=True,
final_endpoint='logits',
in_channels=3,
dropout_keep_prob=config.dropout_keep_prob)
elif config.model == 'resnet':
assert config.model_depth in [10, 18, 34, 50, 101, 152, 200]
from models.resnet import get_fine_tuning_parameters
if config.model_depth == 10:
model = resnet.resnet10(num_classes=config.num_classes,
shortcut_type=config.resnet_shortcut,
spatial_size=config.spatial_size,
sample_duration=config.sample_duration)
elif config.model_depth == 18:
model = resnet.resnet18(num_classes=config.num_classes,
shortcut_type=config.resnet_shortcut,
spatial_size=config.spatial_size,
sample_duration=config.sample_duration)
elif config.model_depth == 34:
model = resnet.resnet34(num_classes=config.num_classes,
shortcut_type=config.resnet_shortcut,
spatial_size=config.spatial_size,
sample_duration=config.sample_duration)
elif config.model_depth == 50:
model = resnet.resnet50(num_classes=config.num_classes,
shortcut_type=config.resnet_shortcut,
spatial_size=config.spatial_size,
sample_duration=config.sample_duration)
elif config.model_depth == 101:
model = resnet.resnet101(num_classes=config.num_classes,
shortcut_type=config.resnet_shortcut,
spatial_size=config.spatial_size,
sample_duration=config.sample_duration)
elif config.model_depth == 152:
model = resnet.resnet152(num_classes=config.num_classes,
shortcut_type=config.resnet_shortcut,
spatial_size=config.spatial_size,
sample_duration=config.sample_duration)
elif config.model_depth == 200:
model = resnet.resnet200(num_classes=config.num_classes,
shortcut_type=config.resnet_shortcut,
spatial_size=config.spatial_size,
sample_duration=config.sample_duration)
elif config.model == 'wideresnet':
assert config.model_depth in [50]
from models.wide_resnet import get_fine_tuning_parameters
if config.model_depth == 50:
model = wide_resnet.resnet50(
num_classes=config.num_classes,
shortcut_type=config.resnet_shortcut,
k=config.wide_resnet_k,
spatial_size=config.spatial_size,
sample_duration=config.sample_duration)
elif config.model == 'resnext':
assert config.model_depth in [50, 101, 152]
from models.resnext import get_fine_tuning_parameters
if config.model_depth == 50:
model = resnext.resnet50(num_classes=config.num_classes,
shortcut_type=config.resnet_shortcut,
cardinality=config.resnext_cardinality,
spatial_size=config.spatial_size,
sample_duration=config.sample_duration)
elif config.model_depth == 101:
model = resnext.resnet101(num_classes=config.num_classes,
shortcut_type=config.resnet_shortcut,
cardinality=config.resnext_cardinality,
spatial_size=config.spatial_size,
sample_duration=config.sample_duration)
elif config.model_depth == 152:
model = resnext.resnet152(num_classes=config.num_classes,
shortcut_type=config.resnet_shortcut,
cardinality=config.resnext_cardinality,
spatial_size=config.spatial_size,
sample_duration=config.sample_duration)
elif config.model == 'densenet':
assert config.model_depth in [121, 169, 201, 264]
from models.densenet import get_fine_tuning_parameters
if config.model_depth == 121:
model = densenet.densenet121(
num_classes=config.num_classes,
spatial_size=config.spatial_size,
sample_duration=config.sample_duration)
elif config.model_depth == 169:
model = densenet.densenet169(
num_classes=config.num_classes,
spatial_size=config.spatial_size,
sample_duration=config.sample_duration)
elif config.model_depth == 201:
model = densenet.densenet201(
num_classes=config.num_classes,
spatial_size=config.spatial_size,
sample_duration=config.sample_duration)
elif config.model_depth == 264:
model = densenet.densenet264(
num_classes=config.num_classes,
spatial_size=config.spatial_size,
sample_duration=config.sample_duration)
if 'cuda' in config.device:
print('Moving model to CUDA device...')
# Move model to the GPU
model = model.cuda()
if config.model != 'i3d':
model = nn.DataParallel(model, device_ids=None)
if config.checkpoint_path:
print('Loading pretrained model {}'.format(config.checkpoint_path))
assert os.path.isfile(config.checkpoint_path)
checkpoint = torch.load(config.checkpoint_path)
if config.model == 'i3d':
pretrained_weights = checkpoint
else:
pretrained_weights = checkpoint['state_dict']
model.load_state_dict(pretrained_weights)
# Setup finetuning layer for different number of classes
# Note: the DataParallel adds 'module' dict to complicate things...
print('Replacing model logits with {} output classes.'.format(
config.finetune_num_classes))
if config.model == 'i3d':
model.replace_logits(config.finetune_num_classes)
elif config.model == 'densenet':
model.module.classifier = nn.Linear(
model.module.classifier.in_features,
config.finetune_num_classes)
model.module.classifier = model.module.classifier.cuda()
else:
model.module.fc = nn.Linear(model.module.fc.in_features,
config.finetune_num_classes)
model.module.fc = model.module.fc.cuda()
# Setup which layers to train
assert config.model in (
'i3d', 'resnet'), 'finetune params not implemented...'
finetune_criterion = config.finetune_prefixes if config.model in (
'i3d', 'resnet') else config.finetune_begin_index
parameters_to_train = get_fine_tuning_parameters(
model, finetune_criterion)
return model, parameters_to_train
else:
raise ValueError('CPU training not supported.')
return model, model.parameters()
def generate_model(opt):
assert opt.model in [
'resnet', 'preresnet', 'wideresnet', 'resnext', 'densenet'
]
if opt.model == 'resnet':
assert opt.model_depth in [10, 18, 34, 50, 101, 152, 200]
from models.my_resnet_v2 import get_fine_tuning_parameters
if opt.model_depth == 10:
model = resnet.resnet10(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 18:
model = resnet.resnet18(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 34:
model = resnet.resnet34(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 50:
model = resnet.resnet50(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 101:
model = resnet.resnet101(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 152:
model = resnet.resnet152(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 200:
model = resnet.resnet200(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'wideresnet':
assert opt.model_depth in [50]
from models.wide_resnet import get_fine_tuning_parameters
if opt.model_depth == 50:
model = wide_resnet.resnet50(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
k=opt.wide_resnet_k,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'resnext':
assert opt.model_depth in [50, 101, 152]
from models.resnext import get_fine_tuning_parameters
if opt.model_depth == 50:
model = resnext.resnet50(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 101:
model = resnext.resnet101(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 152:
model = resnext.resnet152(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'preresnet':
assert opt.model_depth in [18, 34, 50, 101, 152, 200]
from models.pre_act_resnet import get_fine_tuning_parameters
if opt.model_depth == 18:
model = pre_act_resnet.resnet18(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 34:
model = pre_act_resnet.resnet34(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 50:
model = pre_act_resnet.resnet50(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 101:
model = pre_act_resnet.resnet101(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 152:
model = pre_act_resnet.resnet152(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 200:
model = pre_act_resnet.resnet200(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'densenet':
assert opt.model_depth in [121, 169, 201, 264]
from models.densenet import get_fine_tuning_parameters
if opt.model_depth == 121:
model = densenet.densenet121(
num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 169:
model = densenet.densenet169(
num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 201:
model = densenet.densenet201(
num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 264:
model = densenet.densenet264(
num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
if not opt.no_cuda:
model = model.cuda()
model = nn.DataParallel(model, device_ids=None)
if opt.pretrain_path:
print('loading pretrained model {}'.format(opt.pretrain_path))
pretrain = torch.load(opt.pretrain_path)
assert opt.arch == pretrain['arch']
pretrain_dict = pretrain['state_dict']
model_dict = model.state_dict()
pretrain_dict = {k: v for k, v in pretrain_dict.items() if k in model_dict}
# print(pretrain_dict.keys())
model_dict.update(pretrain_dict)
model.load_state_dict(model_dict)
# model.load_state_dict(pretrain['state_dict']
# if opt.model == 'densenet':
# model.module.classifier = nn.Linear(
# model.module.classifier.in_features, opt.n_finetune_classes)
# model.module.classifier = model.module.classifier.cuda()
# else:
# model.module.fc = nn.Linear(model.module.fc.in_features,
# opt.n_finetune_classes)
# model.module.fc = model.module.fc.cuda()
parameters = get_fine_tuning_parameters(model, opt.ft_begin_index)
return model, parameters
else:
if opt.pretrain_path:
print('loading pretrained model {}'.format(opt.pretrain_path))
pretrain = torch.load(opt.pretrain_path)
assert opt.arch == pretrain['arch']
pretrain_dict = pretrain['state_dict']
model_dict = model.state_dict()
pretrain_dict = {k: v for k, v in pretrain_dict.items() if k in model_dict}
model_dict.update(pretrain_dict)
model.load_state_dict(model_dict)
# model.load_state_dict(pretrain['state_dict']
# if opt.model == 'densenet':
# model.classifier = nn.Linear(
# model.classifier.in_features, opt.n_finetune_classes)
# else:
# model.fc = nn.Linear(model.fc.in_features,
# opt.n_finetune_classes)
parameters = get_fine_tuning_parameters(model, opt.ft_begin_index)
return model, parameters
return model, model.parameters()#如果没有pretrain_path就输出模型的所有参数
def generate_C3D_model(opt):
assert opt.mode in ['score', 'feature']
if opt.mode == 'score':
last_fc = True
elif opt.mode == 'feature':
last_fc = False
assert opt.c3d_model_name in ['resnet', 'preresnet', 'wideresnet', 'resnext', 'densenet']
if opt.c3d_model_name == 'resnet':
assert opt.c3d_model_depth in [10, 18, 34, 50, 101, 152, 200]
if opt.c3d_model_depth == 10:
model = resnet.resnet10(num_classes=opt.n_classes, shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size, sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.c3d_model_depth == 18:
model = resnet.resnet18(num_classes=opt.n_classes, shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size, sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.c3d_model_depth == 34:
model = resnet.resnet34(num_classes=opt.n_classes, shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size, sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.c3d_model_depth == 50:
model = resnet.resnet50(num_classes=opt.n_classes, shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size, sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.c3d_model_depth == 101:
model = resnet.resnet101(num_classes=opt.n_classes, shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size, sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.c3d_model_depth == 152:
model = resnet.resnet152(num_classes=opt.n_classes, shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size, sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.c3d_model_depth == 200:
model = resnet.resnet200(num_classes=opt.n_classes, shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size, sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.c3d_model_name == 'wideresnet':
assert opt.c3d_model_depth in [50]
if opt.c3d_model_depth == 50:
model = wide_resnet.resnet50(num_classes=opt.n_classes, shortcut_type=opt.resnet_shortcut, k=opt.wide_resnet_k,
sample_size=opt.sample_size, sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.c3d_model_name == 'resnext':
assert opt.c3d_model_depth in [50, 101, 152]
if opt.c3d_model_depth == 50:
model = resnext.resnet50(num_classes=opt.n_classes, shortcut_type=opt.resnet_shortcut, cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size, sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.c3d_model_depth == 101:
model = resnext.resnet101(num_classes=opt.n_classes, shortcut_type=opt.resnet_shortcut, cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size, sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.c3d_model_depth == 152:
model = resnext.resnet152(num_classes=opt.n_classes, shortcut_type=opt.resnet_shortcut, cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size, sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.c3d_model_name == 'preresnet':
assert opt.c3d_model_depth in [18, 34, 50, 101, 152, 200]
if opt.c3d_model_depth == 18:
model = pre_act_resnet.resnet18(num_classes=opt.n_classes, shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size, sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.c3d_model_depth == 34:
model = pre_act_resnet.resnet34(num_classes=opt.n_classes, shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size, sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.c3d_model_depth == 50:
model = pre_act_resnet.resnet50(num_classes=opt.n_classes, shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size, sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.c3d_model_depth == 101:
model = pre_act_resnet.resnet101(num_classes=opt.n_classes, shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size, sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.c3d_model_depth == 152:
model = pre_act_resnet.resnet152(num_classes=opt.n_classes, shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size, sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.c3d_model_depth == 200:
model = pre_act_resnet.resnet200(num_classes=opt.n_classes, shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size, sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.c3d_model_name == 'densenet':
assert opt.c3d_model_depth in [121, 169, 201, 264]
if opt.c3d_model_depth == 121:
model = densenet.densenet121(num_classes=opt.n_classes,
sample_size=opt.sample_size, sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.c3d_model_depth == 169:
model = densenet.densenet169(num_classes=opt.n_classes,
sample_size=opt.sample_size, sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.c3d_model_depth == 201:
model = densenet.densenet201(num_classes=opt.n_classes,
sample_size=opt.sample_size, sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.c3d_model_depth == 264:
model = densenet.densenet264(num_classes=opt.n_classes,
sample_size=opt.sample_size, sample_duration=opt.sample_duration,
last_fc=last_fc)
# print(model)
print('loading c3d model from: {}'.format(opt.c3d_model_checkpoint))
model_data = torch.load(opt.c3d_model_checkpoint)
print(model_data['arch'])
assert opt.arch == model_data['arch']
model_state_dict = {}
for k, v in model_data['state_dict'].items():
model_state_dict[k[k.index('.') + 1:]] = v
model.load_state_dict(model_state_dict)
if not opt.no_cuda:
model = model.to(opt.device)
# model = nn.DataParallel(model, device_ids=None)
# print(model)
return model
def generate_model(opt):
assert opt.model in [
'resnet', 'preresnet', 'wideresnet', 'resnext', 'densenet'
]
if opt.model == 'resnet':
assert opt.model_depth in [10, 18, 34, 50, 101, 152, 200]
from models.resnet import get_fine_tuning_parameters
if opt.model_depth == 10:
model = resnet.resnet10(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 18:
model = resnet.resnet18(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 34:
model = resnet.resnet34(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 50:
model = resnet.resnet50(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 101:
model = resnet.resnet101(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 152:
model = resnet.resnet152(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 200:
model = resnet.resnet200(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'wideresnet':
assert opt.model_depth in [50]
from models.wide_resnet import get_fine_tuning_parameters
if opt.model_depth == 50:
model = wide_resnet.resnet50(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
k=opt.wide_resnet_k,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'resnext':
assert opt.model_depth in [50, 101, 152]
from models.resnext import get_fine_tuning_parameters
if opt.model_depth == 50:
model = resnext.resnet50(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 101:
model = resnext.resnet101(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 152:
model = resnext.resnet152(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'preresnet':
assert opt.model_depth in [18, 34, 50, 101, 152, 200]
from models.pre_act_resnet import get_fine_tuning_parameters
if opt.model_depth == 18:
model = pre_act_resnet.resnet18(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 34:
model = pre_act_resnet.resnet34(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 50:
model = pre_act_resnet.resnet50(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 101:
model = pre_act_resnet.resnet101(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 152:
model = pre_act_resnet.resnet152(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 200:
model = pre_act_resnet.resnet200(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'densenet':
assert opt.model_depth in [121, 169, 201, 264]
from models.densenet import get_fine_tuning_parameters
if opt.model_depth == 121:
model = densenet.densenet121(num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 169:
model = densenet.densenet169(num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 201:
model = densenet.densenet201(num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 264:
model = densenet.densenet264(num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
if not opt.no_cuda:
model = model.cuda()
model = nn.DataParallel(model, device_ids=None)
if opt.pretrain_path:
print('loading pretrained model {}'.format(opt.pretrain_path))
pretrain = torch.load(opt.pretrain_path)
assert opt.arch == pretrain['arch']
model.load_state_dict(pretrain['state_dict'])
if opt.model == 'densenet':
model.module.classifier = nn.Linear(
model.module.classifier.in_features,
opt.n_finetune_classes)
model.module.classifier = model.module.classifier.cuda()
else:
model.module.fc = nn.Linear(model.module.fc.in_features,
opt.n_finetune_classes)
model.module.fc = model.module.fc.cuda()
parameters = get_fine_tuning_parameters(model, opt.ft_begin_index)
return model, parameters
else:
if opt.pretrain_path:
print('loading pretrained model {}'.format(opt.pretrain_path))
pretrain = torch.load(opt.pretrain_path, map_location='cpu')
assert opt.arch == pretrain['arch']
from collections import OrderedDict
new_state_dict = OrderedDict()
for k, v in pretrain['state_dict'].items():
name = k[7:] # remove `module.`
new_state_dict[name] = v
# load params
model.load_state_dict(new_state_dict)
#model.load_state_dict(pretrain['state_dict'])
if opt.model == 'densenet':
model.classifier = nn.Linear(model.classifier.in_features,
opt.n_finetune_classes)
else:
model.fc = nn.Linear(model.fc.in_features,
opt.n_finetune_classes)
parameters = get_fine_tuning_parameters(model, opt.ft_begin_index)
return model, parameters
return model, model.parameters()
def generate_model(opt):
assert opt.model in ['resnet', 'resnetl', 'resnext', 'c3d']
if opt.model == 'resnet':
assert opt.model_depth in [10]
from models.resnet import get_fine_tuning_parameters
if opt.model_depth == 10:
model = resnet.resnet10(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'resnetl':
assert opt.model_depth in [10]
from models.resnetl import get_fine_tuning_parameters
if opt.model_depth == 10:
model = resnetl.resnetl10(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'resnext':
assert opt.model_depth in [101]
from models.resnext import get_fine_tuning_parameters
if opt.model_depth == 101:
model = resnext.resnet101(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'c3d':
assert opt.model_depth in [10]
from models.c3d import get_fine_tuning_parameters
if opt.model_depth == 10:
model = c3d.c3d_v1(sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
num_classes=opt.n_classes)
if not opt.no_cuda:
model = model.cuda()
model = nn.DataParallel(model, device_ids=None)
if opt.pretrain_path:
print('loading pretrained model {}'.format(opt.pretrain_path))
pretrain = torch.load(opt.pretrain_path)
assert opt.arch == pretrain['arch']
model.load_state_dict(pretrain['state_dict'])
if opt.model == 'c3d': # CHECK HERE
model.module.fc = nn.Linear(model.module.fc[0].in_features,
opt.n_finetune_classes)
else:
model.module.fc = nn.Linear(model.module.fc.in_features,
opt.n_finetune_classes)
model.module.fc = model.module.fc.cuda()
if opt.modality == 'RGB' and opt.model != 'c3d':
print("[INFO]: RGB model is used for init model")
model = _modify_first_conv_layer(
model, 3, 3) ##### Check models trained (3,7,7) or (7,7,7)
elif opt.modality == 'Depth':
print(
"[INFO]: Converting the pretrained model to Depth init model")
model = _construct_depth_model(model)
print("[INFO]: Done. Flow model ready.")
elif opt.modality == 'RGB-D':
print(
"[INFO]: Converting the pretrained model to RGB+D init model")
model = _construct_rgbdepth_model(model)
print("[INFO]: Done. RGB-D model ready.")
modules = list(model.modules())
first_conv_idx = list(
filter(lambda x: isinstance(modules[x], nn.Conv3d),
list(range(len(modules)))))[0]
conv_layer = modules[first_conv_idx]
if conv_layer.kernel_size[0] > opt.sample_duration:
model = _modify_first_conv_layer(model,
int(opt.sample_duration / 2), 1)
parameters = get_fine_tuning_parameters(model, opt.ft_begin_index)
return model, parameters
else:
if opt.pretrain_path:
print('loading pretrained model {}'.format(opt.pretrain_path))
pretrain = torch.load(opt.pretrain_path)
assert opt.arch == pretrain['arch']
model.load_state_dict(pretrain['state_dict'])
if opt.modality == 'RGB' and opt.model != 'c3d':
print("[INFO]: RGB model is used for init model")
model = _modify_first_conv_layer(model, 3, 3)
elif opt.modality == 'Depth':
print(
"[INFO]: Converting the pretrained model to Depth init model")
model = _construct_depth_model(model)
print("[INFO]: Deoth model ready.")
elif opt.modality == 'RGB-D':
print(
"[INFO]: Converting the pretrained model to RGB-D init model")
model = _construct_rgbdepth_model(model)
print("[INFO]: Done. RGB-D model ready.")
modules = list(model.modules())
first_conv_idx = list(
filter(lambda x: isinstance(modules[x], nn.Conv3d),
list(range(len(modules)))))[0]
conv_layer = modules[first_conv_idx]
if conv_layer.kernel_size[0] > opt.sample_duration:
print("[INFO]: RGB model is used for init model")
model = _modify_first_conv_layer(model,
int(opt.sample_duration / 2), 1)
if opt.model == 'c3d': # CHECK HERE
model.fc = nn.Linear(model.fc[0].in_features,
model.fc[0].out_features)
else:
model.fc = nn.Linear(model.fc.in_features, opt.n_finetune_classes)
parameters = get_fine_tuning_parameters(model, opt.ft_begin_index)
return model, parameters
def generate_model(opt):
assert opt.model in [
'c3d', 'squeezenet', 'mobilenet', 'resnext', 'resnet', 'resnetl',
'shufflenet', 'mobilenetv2', 'shufflenetv2'
]
if opt.model == 'c3d':
from models.c3d import get_fine_tuning_parameters
model = c3d.get_model(num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'squeezenet':
from models.squeezenet import get_fine_tuning_parameters
model = squeezenet.get_model(version=opt.version,
num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'shufflenet':
from models.shufflenet import get_fine_tuning_parameters
model = shufflenet.get_model(groups=opt.groups,
width_mult=opt.width_mult,
num_classes=opt.n_classes)
elif opt.model == 'shufflenetv2':
from models.shufflenetv2 import get_fine_tuning_parameters
model = shufflenetv2.get_model(num_classes=opt.n_classes,
sample_size=opt.sample_size,
width_mult=opt.width_mult)
elif opt.model == 'mobilenet':
from models.mobilenet import get_fine_tuning_parameters
model = mobilenet.get_model(num_classes=opt.n_classes,
sample_size=opt.sample_size,
width_mult=opt.width_mult)
elif opt.model == 'mobilenetv2':
from models.mobilenetv2 import get_fine_tuning_parameters
model = mobilenetv2.get_model(num_classes=opt.n_classes,
sample_size=opt.sample_size,
width_mult=opt.width_mult)
elif opt.model == 'resnext':
assert opt.model_depth in [50, 101, 152]
from models.resnext import get_fine_tuning_parameters
if opt.model_depth == 50:
model = resnext.resnet50(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 101:
model = resnext.resnet101(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 152:
model = resnext.resnet152(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'resnetl':
assert opt.model_depth in [10]
from models.resnetl import get_fine_tuning_parameters
if opt.model_depth == 10:
model = resnetl.resnetl10(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'resnet':
assert opt.model_depth in [10, 18, 34, 50, 101, 152, 200]
from models.resnet import get_fine_tuning_parameters
if opt.model_depth == 10:
model = resnet.resnet10(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 18:
model = resnet.resnet18(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 34:
model = resnet.resnet34(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 50:
model = resnet.resnet50(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 101:
model = resnet.resnet101(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 152:
model = resnet.resnet152(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 200:
model = resnet.resnet200(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
if not opt.no_cuda:
model = model.cuda()
model = nn.DataParallel(model, device_ids=None)
pytorch_total_params = sum(p.numel() for p in model.parameters()
if p.requires_grad)
print("Total number of trainable parameters: ", pytorch_total_params)
if opt.pretrain_path:
print('loading pretrained model {}'.format(opt.pretrain_path))
pretrain = torch.load(opt.pretrain_path,
map_location=torch.device('cpu'))
# print(opt.arch)
# print(pretrain['arch'])
# assert opt.arch == pretrain['arch']
model.load_state_dict(pretrain['state_dict'])
if opt.model in [
'mobilenet', 'mobilenetv2', 'shufflenet', 'shufflenetv2'
]:
model.module.classifier = nn.Sequential(
nn.Dropout(0.5),
nn.Linear(model.module.classifier[1].in_features,
opt.n_finetune_classes))
model.module.classifier = model.module.classifier.cuda()
elif opt.model == 'squeezenet':
model.module.classifier = nn.Sequential(
nn.Dropout(p=0.5),
nn.Conv3d(model.module.classifier[1].in_channels,
opt.n_finetune_classes,
kernel_size=1), nn.ReLU(inplace=True),
nn.AvgPool3d((1, 4, 4), stride=1))
model.module.classifier = model.module.classifier.cuda()
else:
model.module.fc = nn.Linear(model.module.fc.in_features,
opt.n_finetune_classes)
model.module.fc = model.module.fc.cuda()
# model = _modify_first_conv_layer(model)
# model = model.cuda()
parameters = get_fine_tuning_parameters(model, opt.ft_portion)
return model, parameters
else:
if opt.pretrain_path:
print('loading pretrained model {}'.format(opt.pretrain_path))
pretrain = torch.load(opt.pretrain_path)
assert opt.arch == pretrain['arch']
model.load_state_dict(pretrain['state_dict'])
if opt.model in [
'mobilenet', 'mobilenetv2', 'shufflenet', 'shufflenetv2'
]:
model.module.classifier = nn.Sequential(
nn.Dropout(0.9),
nn.Linear(model.module.classifier[1].in_features,
opt.n_finetune_classes))
elif opt.model == 'squeezenet':
model.module.classifier = nn.Sequential(
nn.Dropout(p=0.5),
nn.Conv3d(model.module.classifier[1].in_channels,
opt.n_finetune_classes,
kernel_size=1), nn.ReLU(inplace=True),
nn.AvgPool3d((1, 4, 4), stride=1))
else:
model.module.fc = nn.Linear(model.module.fc.in_features,
opt.n_finetune_classes)
parameters = get_fine_tuning_parameters(model, opt.ft_begin_index)
return model, parameters
return model, model.parameters()
def generate_model(opt):
assert opt.mode in ['score', 'feature']
if opt.mode == 'score':
last_fc = True
elif opt.mode == 'feature':
last_fc = False
assert opt.model_name in [
'resnet', 'preresnet', 'wideresnet', 'resnext', 'densenet'
]
if opt.model_name == 'resnet':
assert opt.model_depth in [10, 18, 34, 50, 101, 152, 200]
if opt.model_depth == 10:
model = resnet.resnet10(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.model_depth == 18:
model = resnet.resnet18(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.model_depth == 34:
model = resnet.resnet34(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.model_depth == 50:
model = resnet.resnet50(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.model_depth == 101:
model = resnet.resnet101(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.model_depth == 152:
model = resnet.resnet152(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.model_depth == 200:
model = resnet.resnet200(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.model_name == 'wideresnet':
assert opt.model_depth in [50]
if opt.model_depth == 50:
model = wide_resnet.resnet50(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
k=opt.wide_resnet_k,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.model_name == 'resnext':
assert opt.model_depth in [50, 101, 152]
if opt.model_depth == 50:
model = resnext.resnet50(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.model_depth == 101:
model = resnext.resnet101(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.model_depth == 152:
model = resnext.resnet152(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.model_name == 'preresnet':
assert opt.model_depth in [18, 34, 50, 101, 152, 200]
if opt.model_depth == 18:
model = pre_act_resnet.resnet18(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.model_depth == 34:
model = pre_act_resnet.resnet34(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.model_depth == 50:
model = pre_act_resnet.resnet50(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.model_depth == 101:
model = pre_act_resnet.resnet101(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.model_depth == 152:
model = pre_act_resnet.resnet152(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.model_depth == 200:
model = pre_act_resnet.resnet200(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.model_name == 'densenet':
assert opt.model_depth in [121, 169, 201, 264]
if opt.model_depth == 121:
model = densenet.densenet121(num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.model_depth == 169:
model = densenet.densenet169(num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.model_depth == 201:
model = densenet.densenet201(num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
last_fc=last_fc)
elif opt.model_depth == 264:
model = densenet.densenet264(num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
last_fc=last_fc)
if not opt.no_cuda:
model = model.cuda()
model = nn.DataParallel(model, device_ids=None)
return model
def generate_model(opt):
assert opt.model in [
'resnet', 'preresnet', 'wideresnet', 'resnext', 'densenet', 'i3d',
'i3dv2'
]
if opt.model == 'resnet':
assert opt.model_depth in [10, 18, 34, 50, 101, 152, 200]
from models.resnet import get_fine_tuning_parameters
if opt.model_depth == 10:
model = resnet.resnet10(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 18:
model = resnet.resnet18(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 34:
model = resnet.resnet34(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 50:
model = resnet.resnet50(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 101:
model = resnet.resnet101(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 152:
model = resnet.resnet152(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 200:
model = resnet.resnet200(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'wideresnet':
assert opt.model_depth in [50]
from models.wide_resnet import get_fine_tuning_parameters
if opt.model_depth == 50:
model = wide_resnet.resnet50(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
k=opt.wide_resnet_k,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'resnext':
assert opt.model_depth in [50, 101, 152]
from models.resnext import get_fine_tuning_parameters
if opt.model_depth == 50:
model = resnext.resnet50(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 101:
model = resnext.resnet101(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 152:
model = resnext.resnet152(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'preresnet':
assert opt.model_depth in [18, 34, 50, 101, 152, 200]
from models.pre_act_resnet import get_fine_tuning_parameters
if opt.model_depth == 18:
model = pre_act_resnet.resnet18(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 34:
model = pre_act_resnet.resnet34(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 50:
model = pre_act_resnet.resnet50(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 101:
model = pre_act_resnet.resnet101(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 152:
model = pre_act_resnet.resnet152(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 200:
model = pre_act_resnet.resnet200(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'densenet':
assert opt.model_depth in [121, 169, 201, 264]
from models.densenet import get_fine_tuning_parameters
if opt.model_depth == 121:
model = densenet.densenet121(num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 169:
model = densenet.densenet169(num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 201:
model = densenet.densenet201(num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 264:
model = densenet.densenet264(num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == "i3d":
from models.i3dpt import get_fine_tuning_parameters
model = i3dpt.I3D(num_classes=opt.n_classes, dropout_prob=0.5)
elif opt.model == "i3dv2":
from models.I3D_Pytorch import get_fine_tuning_parameters
model = I3D_Pytorch.I3D(num_classes=opt.n_classes,
dropout_keep_prob=0.5)
if not opt.no_cuda:
model = model.cuda()
model = nn.DataParallel(model, device_ids=None)
if opt.pretrain_path:
print('loading pretrained model {}'.format(opt.pretrain_path))
pretrain = torch.load(opt.pretrain_path)
if opt.model != "i3d" and opt.model != "i3dv2":
assert opt.arch == pretrain['arch']
model.load_state_dict(pretrain['state_dict'])
else:
pretrain = {"module." + k: v for k, v in pretrain.items()}
model_dict = model.state_dict()
model_dict.update(pretrain)
model.load_state_dict(model_dict)
if opt.model == 'densenet':
model.module.classifier = nn.Linear(
model.module.classifier.in_features,
opt.n_finetune_classes)
model.module.classifier = model.module.classifier.cuda()
else:
model.module.fc = nn.Linear(model.module.fc.in_features,
opt.n_finetune_classes)
model.module.fc = model.module.fc.cuda()
parameters = get_fine_tuning_parameters(model, opt.ft_begin_index)
return model, parameters
else:
if opt.pretrain_path:
print('loading pretrained model {}'.format(opt.pretrain_path))
pretrain = torch.load(opt.pretrain_path)
assert opt.arch == pretrain['arch']
model.load_state_dict(pretrain['state_dict'])
if opt.model == 'densenet':
model.classifier = nn.Linear(model.classifier.in_features,
opt.n_finetune_classes)
else:
model.fc = nn.Linear(model.fc.in_features,
opt.n_finetune_classes)
parameters = get_fine_tuning_parameters(model, opt.ft_begin_index)
return model, parameters
return model, model.parameters()
def main():
#994513477.mp4 995153247.mp4 996259932.mp4
start_time = time.time()
video_path = '/home/zengh/Dataset/AIChallenger/group5/995153247.mp4'
if os.path.exists(video_path):
print("exists!")
cap = cv2.VideoCapture(video_path) #15ms
duration = (time.time() - start_time) * 1000
print('1 time %.3f ms' % duration)
start_time = time.time()
print(id(cv2.CAP_PROP_POS_FRAMES))
#cap.set(cv2.CAP_PROP_POS_FRAMES,50) #40ms
#print("id",id(cv2.CAP_PROP_POS_FRAMES))
duration = (time.time() - start_time) * 1000
print('2 time %.3f ms' % duration)
start_time = time.time()
ret, frame = cap.read() #1ms
duration = (time.time() - start_time) * 1000
#print("ret",ret)
print('3 time %.3f ms' % duration)
'''
count = 1
frames = []
while(1):
ret, frame = cap.read()
if frame is None:
break
if count % 5 == 0:
frames.append(frame)
count = count + 1'''
#v = pims.Video('/home/zengh/Dataset/AIChallenger/group5/982006190.mp4')
#duration = (time.time() - start_time) * 1000
#print('cv video time %.3f ms' % duration)
opt = parse_opts()
start_time = time.time()
model = resnext.resnet101(num_classes=opt.n_finetune_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
model = model.cuda()
model = nn.DataParallel(model, device_ids=None)
model.load_state_dict(
torch.load('./trained_models/best.pth10.tar')['state_dict'])
duration = (time.time() - start_time) * 1000
print('restore time %.3f ms' % duration)
#model = nn.DataParallel(model)
model.eval()
rgb_mean = [0.485, 0.456, 0.406]
rgb_std = [0.229, 0.224, 0.225]
opt.scales = [1]
transform_val = Compose([
MultiScaleCornerCrop(opt.scales, opt.sample_size,
crop_positions=['c']),
ToTensor(),
Normalize(rgb_mean, rgb_std),
])
start_time = time.time()
clip = video_loader(
root_path='/home/zengh/Dataset/AIChallenger/train/group5/567700300',
frame_indices=range(3, 19),
transform=transform_val)
clip = clip.unsqueeze(0)
print("clip", clip)
duration = (time.time() - start_time) * 1000
print('pic time %.3f ms' % duration)
#print("clip",clip.shape)
start_time = time.time()
indexes = test(clip, model)
duration = (time.time() - start_time) * 1000
print('pre time %.3f ms' % duration)
def generate_model(opt):
assert opt.model in [
'resnet', 'preresnet', 'wideresnet', 'resnext', 'densenet'
]
if opt.model == 'resnet':
assert opt.model_depth in [10, 18, 34, 50, 101, 152, 200]
from models.resnet import get_fine_tuning_parameters
if opt.model_depth == 10:
model = resnet.resnet10(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 18:
model = resnet.resnet18(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 34:
model = resnet.resnet34(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 50:
model = resnet.resnet50(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
model_type=opt.model_type)
elif opt.model_depth == 101:
model = resnet.resnet101(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
model_type=opt.model_type)
elif opt.model_depth == 152:
model = resnet.resnet152(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
model_type=opt.model_type)
elif opt.model_depth == 200:
model = resnet.resnet200(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
model_type=opt.model_type)
elif opt.model == 'wideresnet':
assert opt.model_depth in [50]
from models.wide_resnet import get_fine_tuning_parameters
if opt.model_depth == 50:
model = wide_resnet.resnet50(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
k=opt.wide_resnet_k,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'resnext':
assert opt.model_depth in [50, 101, 152]
from models.resnext import get_fine_tuning_parameters
if opt.model_depth == 50:
model = resnext.resnet50(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 101:
model = resnext.resnet101(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 152:
model = resnext.resnet152(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'preresnet':
assert opt.model_depth in [18, 34, 50, 101, 152, 200]
from models.pre_act_resnet import get_fine_tuning_parameters
if opt.model_depth == 18:
model = pre_act_resnet.resnet18(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 34:
model = pre_act_resnet.resnet34(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 50:
model = pre_act_resnet.resnet50(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 101:
model = pre_act_resnet.resnet101(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 152:
model = pre_act_resnet.resnet152(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 200:
model = pre_act_resnet.resnet200(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'densenet':
assert opt.model_depth in [121, 169, 201, 264]
from models.densenet import get_fine_tuning_parameters
if opt.model_depth == 121:
model = densenet.densenet121(num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 169:
model = densenet.densenet169(num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 201:
model = densenet.densenet201(num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 264:
model = densenet.densenet264(num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
if not opt.no_cuda:
import os
# os.environ['CUDA_VISIBLE_DEVICES'] = f'{opt.cuda_id}'
model = model.cuda(device=opt.cuda_id)
model = nn.DataParallel(model, device_ids=[0]) # CUDA change
if opt.pretrain_path:
print('loading pretrained model {}'.format(opt.pretrain_path))
pretrain = torch.load(opt.pretrain_path)
print(pretrain['arch'])
arch = f'{opt.model}-{opt.model_depth}'
# arch = opt.model + '-' + opt.model_depth
print(arch)
assert arch == pretrain['arch']
model.load_state_dict(pretrain['state_dict'])
if opt.model == 'densenet':
model.module.classifier = nn.Linear(
model.module.classifier.in_features,
opt.n_finetune_classes)
model.module.classifier = model.module.classifier.cuda(
device=opt.cuda_id)
# elif opt.use_quadriplet:
# model = EmbeddingModel(model, opt.n_finetune_classes, not opt.no_cuda, opt.cuda_id)
else:
model.module.fc = nn.Sequential(
nn.Dropout(0.4),
nn.Linear(model.module.fc.in_features, 512), nn.ReLU6(),
nn.Dropout(0.4), nn.Linear(512, 128), nn.ReLU6(),
nn.Linear(128,
opt.n_finetune_classes)).cuda(device=opt.cuda_id)
# model.module.fc = nn.Linear(model.module.fc.in_features,
# opt.n_finetune_classes)
# model.module.fc = model.module.fc.cuda(device=opt.cuda_id)
parameters = get_fine_tuning_parameters(model, opt.ft_begin_index)
print(len(list(parameters)), 'params to fine tune')
return model, parameters
else:
if opt.pretrain_path:
print('loading pretrained model {}'.format(opt.pretrain_path))
pretrain = torch.load(opt.pretrain_path)
assert opt.arch == pretrain['arch']
model.load_state_dict(pretrain['state_dict'])
if opt.model == 'densenet':
model.classifier = nn.Linear(model.classifier.in_features,
opt.n_finetune_classes)
else:
model.fc = nn.Linear(model.fc.in_features,
opt.n_finetune_classes)
parameters = get_fine_tuning_parameters(model, opt.ft_begin_index)
return model, parameters
return model, model.parameters()
def generate_model(opt):
assert opt.model in [
'resnet', 'preresnet', 'wideresnet', 'resnext', 'densenet',
'mobilenet', 'mobilenetv2'
]
if opt.model == 'resnet':
assert opt.model_depth in [10, 18, 34, 50, 101, 152, 200]
from models.resnet import get_fine_tuning_parameters
if opt.model_depth == 10:
model = resnet.resnet10(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 18:
model = resnet.resnet18(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 34:
model = resnet.resnet34(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 50:
model = resnet.resnet50(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 101:
model = resnet.resnet101(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 152:
model = resnet.resnet152(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 200:
model = resnet.resnet200(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'wideresnet':
assert opt.model_depth in [50]
from models.wide_resnet import get_fine_tuning_parameters
if opt.model_depth == 50:
model = wide_resnet.resnet50(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
k=opt.wide_resnet_k,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'resnext':
assert opt.model_depth in [50, 101, 152]
from models.resnext import get_fine_tuning_parameters
if opt.model_depth == 50:
model = resnext.resnet50(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 101:
model = resnext.resnet101(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 152:
model = resnext.resnet152(num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'preresnet':
assert opt.model_depth in [18, 34, 50, 101, 152, 200]
from models.pre_act_resnet import get_fine_tuning_parameters
if opt.model_depth == 18:
model = pre_act_resnet.resnet18(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 34:
model = pre_act_resnet.resnet34(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 50:
model = pre_act_resnet.resnet50(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 101:
model = pre_act_resnet.resnet101(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 152:
model = pre_act_resnet.resnet152(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 200:
model = pre_act_resnet.resnet200(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'densenet':
assert opt.model_depth in [121, 169, 201, 264]
from models.densenet import get_fine_tuning_parameters
if opt.model_depth == 121:
model = densenet.densenet121(num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 169:
model = densenet.densenet169(num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 201:
model = densenet.densenet201(num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 264:
model = densenet.densenet264(num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'mobilenet':
from models.mobilenet import get_fine_tuning_parameters
model = mobilenet.get_model(num_classes=opt.n_classes,
sample_size=opt.sample_size,
width_mult=opt.width_mult)
elif opt.model == 'mobilenetv2':
from models.mobilenetv2 import get_fine_tuning_parameters
model = mobilenetv2.get_model(num_classes=opt.n_classes,
sample_size=opt.sample_size,
width_mult=opt.width_mult)
if not opt.no_cuda:
if not opt.no_cuda_predict:
model = model.cuda()
model = nn.DataParallel(model, device_ids=None)
if opt.pretrain_path:
print('loading pretrained model {}'.format(opt.pretrain_path))
pretrain = torch.load(opt.pretrain_path)
print("Pretrain arch", pretrain['arch'])
assert opt.arch == pretrain['arch']
model.load_state_dict(pretrain['state_dict'])
ft_begin_index = opt.ft_begin_index
if opt.model in [
'mobilenet', 'mobilenetv2', 'shufflenet', 'shufflenetv2'
]:
model.module.classifier = nn.Sequential(
nn.Dropout(0.9),
nn.Linear(model.module.classifier[1].in_features,
opt.n_finetune_classes))
model.module.classifier = model.module.classifier.cuda()
ft_begin_index = 'complete' if ft_begin_index == 0 else 'last_layer'
elif opt.model == 'densenet':
model.module.classifier = nn.Linear(
model.module.classifier.in_features,
opt.n_finetune_classes)
model.module.classifier = model.module.classifier.cuda()
else:
model.module.fc = nn.Linear(model.module.fc.in_features,
opt.n_finetune_classes)
model.module.fc = model.module.fc.cuda()
print("Finetuning at:", ft_begin_index)
parameters = get_fine_tuning_parameters(model, ft_begin_index)
return model, parameters
else:
if opt.pretrain_path:
print('loading pretrained model {}'.format(opt.pretrain_path))
pretrain = torch.load(opt.pretrain_path)
assert opt.arch == pretrain['arch']
model.load_state_dict(pretrain['state_dict'])
ft_begin_index = opt.ft_begin_index
if opt.model in [
'mobilenet', 'mobilenetv2', 'shufflenet', 'shufflenetv2'
]:
model.module.classifier = nn.Sequential(
nn.Dropout(0.9),
nn.Linear(model.module.classifier[1].in_features,
opt.n_finetune_classes))
model.module.classifier = model.module.classifier.cuda()
ft_begin_index = 'complete' if ft_begin_index == 0 else 'last_layer'
elif opt.model == 'densenet':
model.classifier = nn.Linear(model.classifier.in_features,
opt.n_finetune_classes)
else:
model.fc = nn.Linear(model.fc.in_features,
opt.n_finetune_classes)
print("Finetuning at:", ft_begin_index)
parameters = get_fine_tuning_parameters(model, ft_begin_index)
return model, parameters
return model, model.parameters()
def generate_model(opt):
assert opt.model in [
'resnet', 'resnext'
]
if opt.model == 'resnet':
assert opt.model_depth in [10, 18, 34, 50, 101, 152, 200]
from models.resnet import get_fine_tuning_parameters
if opt.model_depth == 10:
model = resnet.resnet10(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
isSource = opt.isSource,
transfer_module = opt.transfer_module,
sourceKind = opt.sourceKind,
layer_num = opt.layer_num,
multi_source = opt.multi_source)
elif opt.model_depth == 18:
model = resnet.resnet18(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
isSource = opt.isSource,
transfer_module = opt.transfer_module,
sourceKind = opt.sourceKind,
layer_num = opt.layer_num,
multi_source = opt.multi_source)
elif opt.model_depth == 34:
model = resnet.resnet34(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
isSource = opt.isSource,
transfer_module = opt.transfer_module,
sourceKind = opt.sourceKind,
layer_num = opt.layer_num,
multi_source = opt.multi_source)
elif opt.model_depth == 50:
model = resnet.resnet50(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
isSource = opt.isSource,
transfer_module = opt.transfer_module,
sourceKind = opt.sourceKind,
layer_num = opt.layer_num,
multi_source = opt.multi_source)
elif opt.model_depth == 101:
model = resnet.resnet101(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
isSource = opt.isSource,
transfer_module = opt.transfer_module,
sourceKind = opt.sourceKind,
layer_num = opt.layer_num,
multi_source = opt.multi_source)
elif opt.model_depth == 152:
model = resnet.resnet152(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
isSource = opt.isSource,
transfer_module = opt.transfer_module,
sourceKind = opt.sourceKind,
layer_num = opt.layer_num,
multi_source = opt.multi_source)
elif opt.model_depth == 200:
model = resnet.resnet200(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
isSource = opt.isSource,
transfer_module = opt.transfer_module,
sourceKind = opt.sourceKind,
layer_num = opt.layer_num,
multi_source = opt.multi_source)
elif opt.model == 'resnext':
assert opt.model_depth in [50, 101, 152]
from models.resnext import get_fine_tuning_parameters
if opt.model_depth == 50:
model = resnext.resnet50(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
isSource = opt.isSource,
transfer_module = opt.transfer_module,
sourceKind = opt.sourceKind,
layer_num = opt.layer_num,
multi_source = opt.multi_source)
elif opt.model_depth == 101:
model = resnext.resnet101(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
isSource = opt.isSource,
transfer_module = opt.transfer_module,
sourceKind = opt.sourceKind,
layer_num = opt.layer_num,
multi_source = opt.multi_source)
elif opt.model_depth == 152:
model = resnext.resnet152(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration,
isSource = opt.isSource,
transfer_module = opt.transfer_module,
sourceKind = opt.sourceKind,
layer_num = opt.layer_num,
multi_source = opt.multi_source)
print(opt.no_cuda)
print(type(opt.no_cuda))
if not opt.no_cuda:
if opt.pretrain_path:
print('loading pretrained model {}'.format(opt.pretrain_path))
pretrain = torch.load(opt.pretrain_path)
print('loading pretrained model arch', pretrain['arch'], opt.arch)
assert opt.arch == pretrain['arch']
pretrained_dict = pretrain['state_dict']
model_dict = model.state_dict()
# pretrained_dict = {k: v for k, v in pretrained_dict.items() if k in model_dict}
pretrained_dict = {str.replace(k,'module.',''): v for k,v in pretrained_dict.items()}
model_dict.update(pretrained_dict)
model.load_state_dict(model_dict)
model = model.cuda()
model = nn.DataParallel(model, device_ids=None)
if opt.inference == False:
model.module.fc = nn.Linear(model.module.fc.in_features,
opt.n_finetune_classes)
model.module.fc = model.module.fc.cuda()
parameters = get_fine_tuning_parameters(model, opt.ft_begin_index)
print(model)
return model, parameters
elif opt.inference:
model = model.cuda()
model = nn.DataParallel(model, device_ids=None)
return model, model.parameters()
else:
if opt.pretrain_path:
print('loading pretrained model {}'.format(opt.pretrain_path))
print('loading pretrained model arch', pretrain['arch'])
pretrain = torch.load(opt.pretrain_path)
assert opt.arch == pretrain['arch']
model.load_state_dict(pretrain['state_dict'])
parameters = get_fine_tuning_parameters(model, opt.ft_begin_index)
model = model.cuda()
model = nn.DataParallel(model, device_ids=None)
return model, parameters
return model, model.parameters()
def generate_model(opt):
assert opt.model in [
'resnet', 'preresnet', 'wideresnet', 'resnext', 'densenet'
]
if opt.model == 'resnet':
assert opt.model_depth in [10, 18, 34, 50, 101, 152, 200]
from models.resnet import get_fine_tuning_parameters
if opt.model_depth == 10:
model = resnet.resnet10(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 18:
model = resnet.resnet18(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 34:
model = resnet.resnet34(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 50:
model = resnet.resnet50(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 101:
model = resnet.resnet101(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 152:
model = resnet.resnet152(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 200:
model = resnet.resnet200(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'wideresnet':
assert opt.model_depth in [50]
from models.wide_resnet import get_fine_tuning_parameters
if opt.model_depth == 50:
model = wide_resnet.resnet50(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
k=opt.wide_resnet_k,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'resnext':
assert opt.model_depth in [50, 101, 152]
from models.resnext import get_fine_tuning_parameters
if opt.model_depth == 50:
model = resnext.resnet50(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 101:
model = resnext.resnet101(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 152:
model = resnext.resnet152(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
cardinality=opt.resnext_cardinality,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'preresnet':
assert opt.model_depth in [18, 34, 50, 101, 152, 200]
from models.pre_act_resnet import get_fine_tuning_parameters
if opt.model_depth == 18:
model = pre_act_resnet.resnet18(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 34:
model = pre_act_resnet.resnet34(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 50:
model = pre_act_resnet.resnet50(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 101:
model = pre_act_resnet.resnet101(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 152:
model = pre_act_resnet.resnet152(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 200:
model = pre_act_resnet.resnet200(
num_classes=opt.n_classes,
shortcut_type=opt.resnet_shortcut,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model == 'densenet':
assert opt.model_depth in [121, 169, 201, 264]
from models.densenet import get_fine_tuning_parameters
if opt.model_depth == 121:
model = densenet.densenet121(
num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 169:
model = densenet.densenet169(
num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 201:
model = densenet.densenet201(
num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
elif opt.model_depth == 264:
model = densenet.densenet264(
num_classes=opt.n_classes,
sample_size=opt.sample_size,
sample_duration=opt.sample_duration)
if not opt.no_cuda:
model = model.cuda()
model = nn.DataParallel(model, device_ids=None)
if opt.pretrain_path:
print('loading pretrained model {}'.format(opt.pretrain_path))
pretrain = torch.load(opt.pretrain_path)
assert opt.arch == pretrain['arch']
model.load_state_dict(pretrain['state_dict'])
if opt.model == 'densenet':
model.module.classifier = nn.Linear(
model.module.classifier.in_features, opt.n_finetune_classes)
model.module.classifier = model.module.classifier.cuda()
else:
model.module.fc = nn.Linear(model.module.fc.in_features,
opt.n_finetune_classes)
model.module.fc = model.module.fc.cuda()
parameters = get_fine_tuning_parameters(model, opt.ft_begin_index)
return model, parameters
else:
if opt.pretrain_path:
print('loading pretrained model {}'.format(opt.pretrain_path))
pretrain = torch.load(opt.pretrain_path)
assert opt.arch == pretrain['arch']
model.load_state_dict(pretrain['state_dict'])
if opt.model == 'densenet':
model.classifier = nn.Linear(
model.classifier.in_features, opt.n_finetune_classes)
else:
model.fc = nn.Linear(model.fc.in_features,
opt.n_finetune_classes)
parameters = get_fine_tuning_parameters(model, opt.ft_begin_index)
return model, parameters
return model, model.parameters()