import data
import loss
import torch
import model
from trainer import Trainer
from option import args
import utils.utility as utility
ckpt = utility.checkpoint(args)
loader = data.Data(args)
model = model.Model(args, ckpt)
loss = loss.Loss(args, ckpt) if not args.test_only else None
trainer = Trainer(args, model, loss, loader, ckpt)
n = 200
while not trainer.terminate():
n += 1
trainer.train()
if args.test_every != 0 and n % args.test_every == 0:
trainer.test()
import data
import loss
import torch
import model
from trainer import Trainer
from option import args
import utils.utility as utility
ckpt = utility.checkpoint(args) #一个class，load，save，写日志
loader = data.Data(args)
model = model.Model(args, ckpt)
loss = loss.Loss(args, ckpt) if not args.test_only else None
trainer = Trainer(args, model, loss, loader, ckpt)
n = 0
while not trainer.terminate():
n += 1
trainer.train()
# if args.test_every!=0 and n%args.test_every==0:
# trainer.test()
if n % 10 == 0: #每10个epoach保存下模型
model.save("result/", n)
def main():
# parser = argparse.ArgumentParser()
# parser.add_argument('--root', type=str)
# parser.add_argument('-d', '--dataset', type=str, default='market1501')
# parser.add_argument('-m', '--model', type=str, default='osnet_x1_0')
# parser.add_argument('--weights', type=str)
# parser.add_argument('--save-dir', type=str, default='log')
# parser.add_argument('--height', type=int, default=256)
# parser.add_argument('--width', type=int, default=128)
# args = parser.parse_args()
if args.config != '':
with open(args.config, 'r') as f:
config = yaml.load(f)
for op in config:
setattr(args, op, config[op])
# loader = data.Data(args)
ckpt = utility.checkpoint(args)
loader = data_v2.ImageDataManager(args)
model = Model(args, ckpt)
optimzer = optim.make_optimizer(args, model)
# loss = loss.make_loss(args, ckpt) if not args.test_only else None
start = -1
if args.load != '':
start = ckpt.resume_from_checkpoint(
osp.join(ckpt.dir, 'model-latest.pth'), model, optimzer) - 1
if args.pre_train != '':
ckpt.load_pretrained_weights(model, args.pre_train)
scheduler = optim.make_scheduler(args, optimzer, start)
# print('[INFO] System infomation: \n {}'.format(get_pretty_env_info()))
ckpt.write_log('[INFO] Model parameters: {com[0]} flops: {com[1]}'.format(
com=compute_model_complexity(model, (1, 3, args.height, args.width))))
use_gpu = torch.cuda.is_available()
# datamanager = torchreid.data.ImageDataManager(
# root=args.root,
# sources=args.dataset,
# height=args.height,
# width=args.width,
# batch_size_train=100,
# batch_size_test=100,
# transforms=None,
# train_sampler='SequentialSampler'
# )
# test_loader = loader.testloader
test_loader = loader.test_loader
query_loader = loader.query_loader
query_dataset = loader.queryset.query
gallery_dataset = loader.galleryset.gallery
# model = torchreid.models.build_model(
# name=args.model,
# num_classes=datamanager.num_train_pids,
# use_gpu=use_gpu
# )
if use_gpu:
model = model.cuda()
device = torch.device('cuda' if use_gpu else 'cpu')
model.eval()
# self.ckpt.add_log(torch.zeros(1, 6))
# qf = self.extract_feature(self.query_loader,self.args).numpy()
# gf = self.extract_feature(self.test_loader,self.args).numpy()
with torch.no_grad():
qf, query_ids, query_cams = extract_feature(
model, device, query_loader, args)
gf, gallery_ids, gallery_cams = extract_feature(
model, device, test_loader, args)
if args.re_rank:
q_g_dist = np.dot(qf, np.transpose(gf))
q_q_dist = np.dot(qf, np.transpose(qf))
g_g_dist = np.dot(gf, np.transpose(gf))
dist = re_ranking(q_g_dist, q_q_dist, g_g_dist)
else:
# dist = cdist(qf, gf,metric='cosine')
# cosine distance
dist =1- torch.mm(qf, gf.t()).cpu().numpy()
# if args.weights and check_isfile(args.weights):
# load_pretrained_weights(model, args.weights)
save_dir = ckpt.dir
visualize_ranked_results(
dist,
query_dataset,
gallery_dataset,
loader.data_type,
width=loader.width,
height=loader.height,
save_dir=osp.join(save_dir, 'visrank'),
# topk=visrank_topk)
)
import data
import loss
import torch
import model
from trainer import Trainer
from option import args
import utils.utility as utility
import os
# os.environ['CUDA_VISIBLE_DEVICES']='0' # 指定GPU
# print(args) # after run option.py can get these 参数
ckpt = utility.checkpoint(args) # args,log,dir,log_file...functions...
# print(ckpt)
# 以下3步可单独测试
loader = data.Data(args)
model = model.Model(args, ckpt)
loss = loss.Loss(args, ckpt) if not args.test_only else None # if没有冒号
# print(1) if not True else None # if没有冒号 output:
# print(2) if not False else None # if没有冒号 output: 2
trainer = Trainer(args, model, loss, loader, ckpt)
n = 0
while not trainer.terminate():
n += 1
trainer.train()
def main():
# parser = argparse.ArgumentParser()
# parser.add_argument('--root', type=str)
# parser.add_argument('-d', '--dataset', type=str, default='market1501')
# parser.add_argument('-m', '--model', type=str, default='osnet_x1_0')
# parser.add_argument('--weights', type=str)
# parser.add_argument('--save-dir', type=str, default='log')
# parser.add_argument('--height', type=int, default=256)
# parser.add_argument('--width', type=int, default=128)
# args = parser.parse_args()
if args.config != '':
with open(args.config, 'r') as f:
config = yaml.load(f)
for op in config:
setattr(args, op, config[op])
# loader = data.Data(args)
ckpt = utility.checkpoint(args)
loader = data_v2.ImageDataManager(args)
model = Model(args, ckpt)
optimzer = optim.make_optimizer(args, model)
# loss = loss.make_loss(args, ckpt) if not args.test_only else None
start = -1
if args.load != '':
start = ckpt.resume_from_checkpoint(
osp.join(ckpt.dir, 'model-latest.pth'), model, optimzer) - 1
if args.pre_train != '':
ckpt.load_pretrained_weights(model, args.pre_train)
scheduler = optim.make_scheduler(args, optimzer, start)
# print('[INFO] System infomation: \n {}'.format(get_pretty_env_info()))
ckpt.write_log('[INFO] Model parameters: {com[0]} flops: {com[1]}'.format(
com=compute_model_complexity(model, (1, 3, args.height, args.width))))
use_gpu = torch.cuda.is_available()
# datamanager = torchreid.data.ImageDataManager(
# root=args.root,
# sources=args.dataset,
# height=args.height,
# width=args.width,
# batch_size_train=100,
# batch_size_test=100,
# transforms=None,
# train_sampler='SequentialSampler'
# )
test_loader = loader.testloader
# model = torchreid.models.build_model(
# name=args.model,
# num_classes=datamanager.num_train_pids,
# use_gpu=use_gpu
# )
if use_gpu:
model = model.cuda()
# if args.weights and check_isfile(args.weights):
# load_pretrained_weights(model, args.weights)
save_dir = ckpt.dir
visactmap(model, test_loader, save_dir, args.width, args.height, use_gpu)