layer_drop=0.1,
num_conv=1,
light=False)
# net = Model_dense( 20, [40,40,80,80,192,192,320,320, 512], [512], output_classes=751,
# init_points = 512, input_dims=3, dropout_prob=0.5, npart= 1, id_skip=True,
# light=True, cluster='xyz', conv='SAGEConv', use_xyz=False)
xyz = torch.FloatTensor(np.random.normal(size=(4, 6890, 3))).cuda()
rgb = torch.FloatTensor(4, 6890, 3).cuda()
net = net.cuda()
print(net)
net.proj_output = nn.Sequential()
model_parameters = filter(lambda p: p.requires_grad, net.parameters())
params = sum([np.prod(p.size()) for p in model_parameters])
print('Number of parameters: %.2f M' % (params / 1e6))
#output = net(xyz, rgb)
market_data = Market3D('./2DMarket', flip=True, slim=0.5, bg=True)
CustomDataLoader = partial(DataLoader,
num_workers=0,
batch_size=8,
shuffle=True,
drop_last=True)
query_loader = CustomDataLoader(market_data.query())
batch0, label0 = next(iter(query_loader))
batch0 = batch0[0].unsqueeze(0)
print(batch0.shape)
macs, params = get_model_complexity_info(net,
batch0.cuda(),
((round(6890 * 0.5), 3)),
as_strings=True,
print_per_layer_stat=False,
#filename = path.split('/')[-1]
filename = os.path.basename(path)
label = filename[0:4]
camera = filename.split('c')[1]
if label[0:2] == '-1':
labels.append(-1)
else:
labels.append(int(label))
camera_id.append(int(camera[0]))
return camera_id, labels
market_data = Market3D(opt.dataset_path,
flip=False,
slim=opt.slim,
norm=opt.norm,
erase=0,
channel=opt.channel,
bg=opt.bg,
D2=opt.D2)
query_loader = CustomDataLoader(market_data.query())
gallery_loader = CustomDataLoader(market_data.gallery())
gallery_path = market_data.gallery().imgs
query_path = market_data.query().imgs
gallery_cam, gallery_label = get_id(gallery_path)
query_cam, query_label = get_id(query_path)
dev = torch.device("cuda" if torch.cuda.is_available() else "cpu")
x_epoch.append(current_epoch)
ax0.plot(x_epoch, y_loss['train'], 'bo-', label='train')
ax0.plot(x_epoch, y_loss['val'], 'ro-', label='val')
ax1.plot(x_epoch, y_err['train'], 'bo-', label='train')
ax1.plot(x_epoch, y_err['val'], 'ro-', label='val')
if current_epoch == 0:
ax0.legend()
ax1.legend()
fig.savefig(os.path.join('./snapshot', opt.name, 'train.png'))
market_data = Market3D(opt.dataset_path,
flip=opt.flip,
slim=opt.slim,
norm=opt.norm,
scale=opt.scale,
erase=opt.erase,
rotate=opt.rotate,
channel=opt.channel,
bg=opt.bg,
D2=opt.D2)
train_loader = CustomDataLoader(market_data.train())
if opt.train_all:
train_loader = CustomDataLoader(market_data.train_all())
valid_loader = CustomDataLoader(market_data.valid())
dataset_sizes = {}
dataset_sizes['train'] = market_data.train().img_num
dataset_sizes['val'] = market_data.valid().img_num
dev = torch.device("cuda" if torch.cuda.is_available() else "cpu")