def main(args):
"""Main train and evaluation function.
Parameters
----------
args: argparse.Namespace
Arguments
"""
formatter = logging.Formatter('%(asctime)s %(levelname)s - %(funcName)s: %(message)s',
"%H:%M:%S")
logger = logging.getLogger(__name__)
logger.setLevel(args.log_level.upper())
stream = logging.StreamHandler()
stream.setLevel(args.log_level.upper())
stream.setFormatter(formatter)
logger.addHandler(stream)
set_seed(args.seed)
device = get_device(is_gpu=not args.no_cuda)
exp_dir = os.path.join(RES_DIR, args.name)
feature_dir = os.path.join(exp_dir, 'training_features')
logger.info("Root directory for saving and loading experiments: {}".format(exp_dir))
if not args.is_eval_only:
create_safe_directory(feature_dir, logger=logger)
# Setting number of epochs to 1, as we need to extract features
args.epochs = 1
args.batch_size = 1
# PREPARES DATA
data_loader = get_dataloaders(args.dataset,
batch_size=args.batch_size,
logger=logger, test=False)
logger.info("Train {} with {} samples".format(args.dataset, len(data_loader.dataset)))
# PREPARES MODEL
args.img_size = get_img_size(args.dataset) # stores for metadata
model = load_model(exp_dir, filename='model.pt')
logger.info('Num parameters in model: {}'.format(get_n_param(model)))
# Extract Features
model = model.to(device) # make sure trainer and viz on same device
fe = FeatureExtractor(model,
save_dir=exp_dir,
is_progress_bar=not args.no_progress_bar)
fe(data_loader,
epochs=args.epochs,
checkpoint_every=args.checkpoint_every, feature_dir=feature_dir)
# SAVE MODEL AND EXPERIMENT INFORMATION
# save_model(trainer.model, exp_dir, metadata=vars(args))
print('Done.')
def main(args):
"""Main train and evaluation function.
Parameters
----------
args: argparse.Namespace
Arguments
"""
formatter = logging.Formatter(
'%(asctime)s %(levelname)s - %(funcName)s: %(message)s', "%H:%M:%S")
logger = logging.getLogger(__name__)
logger.setLevel(args.log_level.upper())
stream = logging.StreamHandler()
stream.setLevel(args.log_level.upper())
stream.setFormatter(formatter)
logger.addHandler(stream)
set_seed(args.seed)
device = get_device(is_gpu=not args.no_cuda)
exp_dir = os.path.join(RES_DIR, args.name)
logger.info("Root directory for saving and loading experiments: {}".format(
exp_dir))
if not args.is_eval_only:
create_safe_directory(exp_dir, logger=logger)
if args.loss == "factor":
logger.info(
"FactorVae needs 2 batches per iteration. To replicate this behavior while being consistent, we double the batch size and the the number of epochs."
)
args.batch_size *= 2
args.epochs *= 2
# PREPARES DATA
train_loader = get_dataloaders(args.dataset,
batch_size=args.batch_size,
logger=logger)
logger.info("Train {} with {} samples".format(
args.dataset, len(train_loader.dataset)))
# PREPARES MODEL
args.img_size = get_img_size(args.dataset) # stores for metadata
model = init_specific_model(args.model_type, args.img_size,
args.latent_dim)
logger.info('Num parameters in model: {}'.format(get_n_param(model)))
# TRAINS
optimizer = optim.Adam(model.parameters(), lr=args.lr)
model = model.to(device) # make sure trainer and viz on same device
gif_visualizer = GifTraversalsTraining(model, args.dataset, exp_dir)
loss_f = get_loss_f(args.loss,
n_data=len(train_loader.dataset),
device=device,
**vars(args))
trainer = Trainer(model,
optimizer,
loss_f,
device=device,
logger=logger,
save_dir=exp_dir,
is_progress_bar=not args.no_progress_bar,
gif_visualizer=gif_visualizer)
trainer(
train_loader,
epochs=args.epochs,
checkpoint_every=args.checkpoint_every,
)
# SAVE MODEL AND EXPERIMENT INFORMATION
save_model(trainer.model, exp_dir, metadata=vars(args))
if args.is_metrics or not args.no_test:
model = load_model(exp_dir, is_gpu=not args.no_cuda)
metadata = load_metadata(exp_dir)
# TO-DO: currently uses train datatset
test_loader = get_dataloaders(metadata["dataset"],
batch_size=args.eval_batchsize,
shuffle=False,
logger=logger)
loss_f = get_loss_f(args.loss,
n_data=len(test_loader.dataset),
device=device,
**vars(args))
use_wandb = False
if use_wandb:
loss = args.loss
wandb.init(project="atmlbetavae", config={"VAE_loss": args.loss})
if loss == "betaH":
beta = loss_f.beta
wandb.config["Beta"] = beta
evaluator = Evaluator(model,
loss_f,
device=device,
logger=logger,
save_dir=exp_dir,
is_progress_bar=not args.no_progress_bar,
use_wandb=use_wandb)
evaluator(test_loader,
is_metrics=args.is_metrics,
is_losses=not args.no_test)
m1, s1 = _calculate_activation_statistics(dataloader_original, length, model, batch_size, dims)
print("Calculated m1 and s1")
m2, s2 = _calculate_activation_statistics(dataloader_reconstructed, length, model, batch_size, dims)
print("Calculated m2 and s2")
fid_value = _calculate_frechet_distance(m1, s1, m2, s2)
return fid_value
if __name__ == "__main__":
import torch
import random
from disvae.utils.modelIO import load_model
import argparse
import logging
import sys
MODEL_PATH = sys.argv[2] # get the model path (e.g. "results/betaH_mnist")
MODEL_NAME = "model.pt"
GPU_AVAILABLE = True
vae_model = load_model(directory=MODEL_PATH, is_gpu=GPU_AVAILABLE, filename=MODEL_NAME)
mode = sys.argv[1] # get the name of the dataset you want to measure FID for
dataloader1 = get_dataloaders(mode, batch_size=128)[0]
fid_value = get_fid_value(dataloader1, vae_model)
print("FID for ", mode, ": ", fid_value)
import ctypes
ctypes.cdll.LoadLibrary(
'caffe2_nvrtc.dll'
) # this was necessary on my machine, may not be on yours
img_index = 5000
model_paths = [
"marbles_b4_u0", "marbles_b4_u1e-2", "marbles_b4_u1e-1", "marbles_b40_u0",
"marbles_b40_u1e-2", "marbles_b40_u1e-1", "marbles_b100_u0",
"marbles_b100_u1e-2", "marbles_b100_u1e-1"
]
for model_path in model_paths:
bvae_model = load_model("./results/" + model_path + "/",
filename="model-480.pt")
imgs = np.load("./data/marbles/raw/10k_marbles.npy")
utils = np.load("./data/marbles/raw/10k_marbles_utilities.npy")
im = Image.fromarray(imgs[img_index])
im.save("./original.jpeg")
data = np.array([np.transpose(imgs[img_index])])
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
tensor = torch.from_numpy(data).float().to(device)
recon_batch, latent_dist, latent_sample = bvae_model(tensor)
recon = recon_batch.cpu().detach().numpy()
recon_img = np.transpose(recon[0]) * 255
recon_img = recon_img.astype('uint8')
trainer = Trainer(model, optimizer, loss_f=loss_f,
loss_name=args.loss,
device=device,
logger=logger,
save_dir=exp_dir,
is_progress_bar=not args.no_progress_bar,
gif_visualizer=gif_visualizer)
trainer(train_loader,
epochs=args.epochs,
checkpoint_every=args.checkpoint_every)
# SAVE MODEL AND EXPERIMENT INFORMATION
save_model(trainer.model, exp_dir, metadata=vars(args))
if args.is_metrics or not args.no_test:
model = load_model(exp_dir, is_gpu=not args.no_cuda)
metadata = load_metadata(exp_dir)
# TO-DO: currently uses train datatset
test_loader = get_dataloaders(metadata["dataset"],
batch_size=args.eval_batchsize,
shuffle=False,
logger=logger)
loss_f = get_loss_f(args.loss,
n_data=len(test_loader.dataset),
device=device,
**vars(args))
evaluator = Evaluator(model, loss_f,
device=device,
logger=logger,
save_dir=exp_dir,
is_progress_bar=not args.no_progress_bar)
