luni/cvpr_2023
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

remove long edges in post

Browse Source
This commit is contained in:
luni
2023-07-04 23:52:13 +02:00
parent 80f244b69b
commit 37ad3a3f43
4 changed files with 151 additions and 319 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/cvae_pyramid.py
+25 -312
View File
@@ -238,8 +238,6 @@ def train_step(batch):
res_modifier = '_' + str(res) if res != 512 else ''
pred, mean, logvar = out_levels[i]
l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((uv_orig - pred) ** 2), dim=-1), dim=[1, 2]))
kl = kl_loss(mean, logvar)
@@ -251,16 +249,16 @@ def train_step(batch):
gender = torch.greater_equal(shape[:, 10] , 0.5).to(dtype=torch.int64)
shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])])
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None]
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_fix']['mesh_mask'][:,:,None]
mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0]
else:
mesh_pred_posed = mesh_pred
e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_fix']['mesh_mask']))
c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_fix']['mesh_mask'])
c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio)
n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, dim=-1), dim=-1))
n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_fix']['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_fix']['mesh_mask'][:,:,None] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, dim=-1), dim=-1))
reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss)
if not config['is_cape']:
@@ -290,19 +288,19 @@ def train_step(batch):
gender = torch.greater_equal(shape[:, 10] , 0.5).to(dtype=torch.int64)
shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])])
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None]
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_fix']['mesh_mask'][:,:,None]
mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0]
else:
mesh_pred_posed = mesh_pred
e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_fix']['mesh_mask']))
c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_fix']['mesh_mask'])
c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio)
l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, dim=-1), dim=-1))
n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_fix']['mesh_mask'][:,:,None] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, dim=-1), dim=-1))
n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_fix']['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
ms_ssim = torch.mean(_MSSSIM(pred + 1, batch['uv_static'] + 1))
metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred.detach()) ** 2, axis=-1))) / torch.sum(batch['mesh_mask'])
metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_fix']['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred.detach()) ** 2, axis=-1))) / torch.sum(batch['mesh_fix']['mesh_mask'])
output = { **output, **{ 'train/edge_loss' + res_modifier: e_loss, 'train/collision_loss' + res_modifier: c_loss,'train/euclid_error' + res_modifier: metric,
'train/mean' + res_modifier: mean, 'train/logvar' + res_modifier: logvar, 'train/kl_loss' + res_modifier: kl,
@@ -343,18 +341,18 @@ def valid_step(batch):
gender = torch.greater_equal(shape[:, 10] , 0.5).to(dtype=torch.int64)
shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])])
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None]
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_fix']['mesh_mask'][:,:,None]
mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0]
else:
mesh_pred_posed = mesh_pred
e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_fix']['mesh_mask']))
c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_fix']['mesh_mask'])
c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio)
l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_fix']['mesh_mask'][:,:,None] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, dim=-1), dim=-1))
n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_fix']['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((uv_orig - pred) ** 2), dim=-1), dim=[1, 2]))
l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, dim=-1), dim=-1))
n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
kl = kl_loss(mean, logvar)
if config['use_extra_losses']:
@@ -373,7 +371,7 @@ def valid_step(batch):
logvar = torch.mean(logvar)
ms_ssim = torch.mean(_MSSSIM(pred + 1, batch['uv_static'] + 1))
metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred.detach()) ** 2, axis=-1))) / torch.sum(batch['mesh_mask'])
metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_fix']['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / torch.sum(batch['mesh_fix']['mesh_mask'])
output = { **output, **{ 'valid/edge_loss' + res_modifier: e_loss, 'valid/collision_loss' + res_modifier: c_loss,'valid/euclid_error' + res_modifier: metric,
'valid/mean' + res_modifier: mean, 'valid/logvar' + res_modifier: logvar, 'valid/kl_loss' + res_modifier: kl,
@@ -385,63 +383,6 @@ def valid_step(batch):
return { **{ 'valid/loss': loss, 'valid/reconstr_loss_total': reconstr_loss_total, 'valid/kl_total': kl_total }, **output }
def test_step(batch):
levels_input, conds = group_inputs_for_levels(batch, config)
out_levels = model([levels_input, conds], training=False)
shape = batch['pose_shape'][:, 72:]
gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, dim=0) for i in range(shape.shape[0])])
mesh_orig = batch['mesh_unposed']
output = dict()
reconstr_loss_total = 0
kl_total = 0
#for i, res in enumerate(config['pyramid']['resolutions']):
i = -1
res = config['pyramid']['resolutions'][-1]
res_modifier = '_' + str(res) if res != 512 else ''
pred, mean, logvar = out_levels[i]
mesh_pred = uv2mesh(pred)
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None]
mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
# is the output already masked?
e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio)
l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((batch['uv_unposed'] - pred) ** 2), dim=-1), dim=[1, 2]))
l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred) ** 2, dim=-1), dim=-1))
# ms_ssim = torch.mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
# ms_ssim = torch.mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3))
kl = kl_loss(mean, logvar)
reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss)
if not config['is_cape']:
reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff']
# reconstr_loss_total += config['pyramid']['loss_weights'][i] * (l2_loss + (e_loss + c_loss) * config['reg_loss_coeff'])
kl_total += kl
mean = torch.mean(mean)
logvar = torch.mean(logvar)
metric = torch.sum(tf.math.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred) ** 2, dim=-1))) / torch.sum(batch['mesh_mask'])
euclid_error_per_garment = torch.sum(tf.math.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred) ** 2, dim=-1)), dim=1) / torch.sum(batch['mesh_mask'], dim=1)
output = { **output, **{ 'test/edge_loss' + res_modifier: e_loss, 'test/collision_loss' + res_modifier: c_loss,'test/euclid_error' + res_modifier: metric,
'test/mean' + res_modifier: mean, 'test/logvar' + res_modifier: logvar, 'test/kl_loss' + res_modifier: kl,
'test/var' + res_modifier: np.e ** logvar, 'test/l2_loss' + res_modifier: l2_loss,
'test/euclid_error': metric, 'test/collision_ratio' + res_modifier: c_ratio } }
loss = reconstr_loss_total + balancing_coeff * kl_total
return { **{ 'test/loss': loss, 'test/reconstr_loss_total': reconstr_loss_total, 'test/kl_total': kl_total }, **output }, euclid_error_per_garment
def plot_everything(batch: dict, type: str):
if config['use_skinning']:
mesh_orig, uv_orig = batch['mesh_unposed'].cpu().numpy(), batch['uv_unposed']
@@ -473,8 +414,11 @@ def plot_everything(batch: dict, type: str):
imgs = [wandb.Image(img[i].cpu().numpy()) for i in range(4)]
_F = np.load("smpl/smpl_faces" + skirt_modifier + ("_orig" if config['is_cape'] else "") + ".npy")
mask = batch['mesh_mask'].cpu().numpy().astype(bool)
_, faces = maskFacesBatch(np.ones_like(mesh_orig), _F, mask)
mask = batch['mesh_fix']['mesh_mask'].cpu().numpy().astype(bool)
if 'mesh_fix' in batch:
faces = [np.load( (dataset_train if type == 'train' else dataset_valid).folder + "/mesh_fixed/" + batch['id'][i] + '_' + batch['garment'][i] + ".npz" )['faces'] for i in range(len(batch['id']))]
else:
_, faces = maskFacesBatch(np.ones_like(mesh_orig), _F, mask)
if config['use_skinning']:
shape = batch['pose_shape'][:, 72:]
@@ -543,237 +487,6 @@ def plot_everything(batch: dict, type: str):
return { **figs, **figs_coll, **{ type + '/images': imgs, }, **{ f'{type}/batch_info': batch_info }, }
def sample(folder):
# run = wandb.init(project='vae_plots', name=folder.split('/')[-1])
load_model(model,folder)
count = 0
for batch in dataset_train:
batch = static_dataset_train.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
uv_curvature = tf.one_hot(batch['uv_curvature'], 7)
nr_of_samples=2
pred = model.sample(batch['uv_static'][0], batch['uv_body_posed'][0], uv_curvature[0], batch['uv_mask'][0], nr_of_samples=nr_of_samples)
pose, shape = batch['pose_shape'][0, :72], batch['pose_shape'][0, 72:]
pose, shape = tf.tile(pose[None,:], [nr_of_samples,1]), tf.tile(shape[None,:], [nr_of_samples,1])
mesh_pred = uv2mesh(tf.transpose(pred, [0,3,1,2]))
mesh_posed = smpl.run_garment(pose, shape, mesh_pred).numpy()
mesh_orig = batch['mesh_posed'][0].numpy()
mesh_orig_reposed = smpl.run_garment(pose[:1], shape[:1], batch['mesh_unposed'][:1]).numpy()[0]
body = batch['mesh_body_posed'][0].numpy()
body_color = np.ones_like(body, dtype=np.int32)*100
F = np.load("custom_utils/smpl_faces.npy")
mask = batch['mesh_mask'].numpy().astype(bool)[0]
_, faces = _maskFaces(np.ones((14475, 3)), F, mask)
pred_zero = model.sample(batch['uv_static'][0], batch['uv_body_posed'][0], uv_curvature[0], batch['uv_mask'][0], nr_of_samples=nr_of_samples, zero_latent=True)
mesh_pred_zero = uv2mesh(tf.transpose(pred_zero, [0,3,1,2]))
mesh_posed_zero = smpl.run_garment(pose, shape, mesh_pred_zero).numpy()
meshes = []
meshes.append(go.Mesh3d(
# 8 vertices of a cube
x=mesh_orig_reposed[mask,0],
y=mesh_orig_reposed[mask,2],
z=mesh_orig_reposed[mask,1],
# i, j and k give the vertices of triangles
i = faces[:,0],
j = faces[:,1],
k = faces[:,2]
))
for i in range(nr_of_samples):
x = mesh_posed[i][mask, :].copy()
# x[:, 2] += 1 * (i + 1)
x[:, 2] += 1
meshes.append(go.Mesh3d(
# 8 vertices of a cube
x=x[:,0],
y=x[:,2],
z=x[:,1],
# i, j and k give the vertices of triangles
i = faces[:,0],
j = faces[:,1],
k = faces[:,2]
))
for i in range(nr_of_samples):
x = mesh_posed_zero[i][mask, :].copy()
# x[:, 2] += 1 * (i + 1)
x[:, 2] += 2
meshes.append(go.Mesh3d(
# 8 vertices of a cube
x=x[:,0],
y=x[:,2],
z=x[:,1],
# i, j and k give the vertices of triangles
i = faces[:,0],
j = faces[:,1],
k = faces[:,2]
))
# for i in range(5):
# x = body.copy()
# x[:, 2] += 1 * i
# meshes.append(go.Mesh3d(
# # 8 vertices of a cube
# x=x[:,0],
# y=x[:,2],
# z=x[:,1],
# # i, j and k give the vertices of triangles
# i = F[:,0],
# j = F[:,1],
# k = F[:,2],
# vertexcolor=body_color
# ))
fig = go.Figure(data=meshes)
fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=2, z=1))
# fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=nr_of_samples-1, z=1))
fig.update_layout(
scene = dict(
xaxis = dict(nticks=4, range=[-1,1],),
# yaxis = dict(nticks=4, range=[-1,nr_of_samples+1],),
yaxis = dict(nticks=4, range=[-1,3],),
zaxis = dict(nticks=4, range=[-1,1],),)
)
# wandb.log({'plot_' + str(count): fig})
fig.show()
pred = pred.numpy()
frames = [Image.fromarray(((pred[i] + 1) * 128).astype(np.int8), mode='RGB') for i in range(pred.shape[0])]
frames[0].save("temp/garment_1.gif", format="GIF", append_images=frames[1:],
save_all=True, duration=500, loop=0)
if count > 10:
break
print(count)
count += 1
print()
def test():
garment_type_table = np.load('custom_data/garment_type_table_test.npy', allow_pickle=True).item()
str_split = config['name'].split('_')
test_idx = str_split.index('test')
checkpoint_name = '_'.join(str_split[:test_idx])
load_model(model, 'checkpoints/' + checkpoint_name)
dataset_test = factory.get_dataset(folder=config['test_dir'], batch_size=config['batch_size'], signature=config['signature_dynamic'], use_filled=config['use_filled'], resolutions=dataset_resolutions, in_memory=False, do_repeat=False)
static_dataset_test = StaticDataset(folder=config['test_dir'], signature=config['signature_static'], use_filled=config['use_filled'], resolutions=dataset_resolutions, in_memory=False)
step = 0
losses = []
if config['is_skirt']:
per_garment_errors = { 'Tshirt': [], 'Dress': [], 'Skirt': [], 'Top': [] }
else:
per_garment_errors = { 'Tshirt': [], 'Jumpsuit': [], 'Trousers': [], 'Top': [] }
for batch in tqdm.tqdm(dataset_test):
batch = static_dataset_test.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
test_loss, euclid_error_per_garment = test_step(batch)
losses.append(test_loss)
for i, id in enumerate(batch['id']):
id_str = id.numpy().decode("utf-8")
per_garment_errors[garment_type_table[id_str]].append(euclid_error_per_garment[i].numpy())
to_log = { **{ 'current_step': step }, **test_loss }
if step % 1000 == 0:
figs = plot_everything(batch, 'test')
to_log = { **to_log, **figs }
wandb.log(to_log, step = step)
# print(step)
step += 1
# averages = dict()
path_to_plotly_html = "temp/plotly_figure.html"
histograms = dict()
for key in test_loss.keys():
accumulated = [losses[i][key].numpy() for i in range(len(losses))]
fig = ex.histogram(accumulated, title='Average: ' + str(np.asarray(accumulated).mean()))
fig.write_html(path_to_plotly_html, auto_play = False)
histograms['all/' + key.split('/')[-1] + '_hist'] = wandb.Html(path_to_plotly_html)
# averages['all/' + key.split('/')[-1] + '_avg'] = np.asarray(accumulated).mean()
for key in per_garment_errors.keys():
fig = ex.histogram(per_garment_errors[key], title='Average: ' + str(np.asarray(per_garment_errors[key]).mean()))
fig.write_html(path_to_plotly_html, auto_play = False)
histograms['all/' + key + 'euclid_error_hist'] = wandb.Html(path_to_plotly_html)
wandb.log({ **histograms }, step = step)
wandb.finish()
pass
def generate_results():
load_model(model, 'checkpoints/' + config['name'])
dataset_test = factory.get_dataset(folder=config['test_dir'],
batch_size=config['batch_size'],
# batch_size=1,
signature=config['signature_dynamic'],
resolutions=dataset_resolutions,
in_memory=config['dataset_in_memory'],
is_cape=config['is_cape'],
frames_file=config['frames_file'] if 'frames_file' in config.keys() else None,
do_repeat=False,
shuffle=False)
static_dataset_test = StaticDataset(folder=config['test_dir'],
signature=config['signature_static'],
resolutions=dataset_resolutions,
in_memory=True,
is_cape=config['is_cape'])
folder = os.path.join('/home/workspace/data/results/cape', config['name'])
os.makedirs(folder, exist_ok=True)
for batch in tqdm.tqdm(dataset_test):
batch = static_dataset_test.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
levels_input, conds = group_inputs_for_levels(batch, config)
out_levels = model([levels_input, conds], training=False)
shape = batch['pose_shape'][:, 72:]
gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])])
i = -1
pred = out_levels[i][0]
mesh_pred = uv2mesh(pred)
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None]
mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
for i in range(batch['id'].shape[0]):
mask = batch['mesh_mask'][i].numpy().astype(bool)
id, frame_nr = batch['id'][i].numpy().decode("utf-8"), batch['frame_nr'][i].numpy().decode("utf-8")
unposed = mesh_pred[i].numpy()[mask, :]
posed = mesh_pred_posed[i].numpy()[mask, :]
np.save(os.path.join(folder, id + '_' + frame_nr + '_posed.npy'), posed)
np.save(os.path.join(folder, id + '_' + frame_nr + '_unposed.npy'), unposed)
pass
def speed_step(levels_input, conds):
return model.sample([levels_input, conds], training=False)
@@ -840,7 +553,7 @@ if __name__ == '__main__':
optimizer = optim.Adam(model.parameters(), lr=config['lr'])
_MSSSIM = MS_SSIM(data_range=2, size_average=True, channel=3)
ckpt_saver = CheckpointSaver('checkpoints/iccvw/' + config['name'], top_n=5)
ckpt_saver = CheckpointSaver('checkpoints/iccvw/' + config['name'], top_n=20)
scaler = torch.cuda.amp.GradScaler(enabled=use_amp)
g_balancing_coeff = config['starting_balancing_coeff']