model.load_state_dict(torch.load(model_state_dict), strict=True)
model.train(False)
for params in model.parameters():
params.requires_grad = False
model = model.to(DEVICE)
normalize = transforms.Normalize(
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]
)
preprocess = transforms.Compose([
transforms.Scale(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
normalize])
in_path = "/content/drive/My Drive/Lorenzo/ego-rnn-two-in-one/get_modulation/frames"
out_path = "/content/drive/My Drive/Lorenzo/ego-rnn-two-in-one/get_modulation/out2"
inputFlow = []
inputFrame = []
frames = []
for i in range(1, len(os.listdir(in_path+"/rgb"))+1):
print(i)
# FLOW X
fl_name = in_path + '/X/flow_x_' + str(int(round(i))).zfill(5) + '.png' # zfill used to add leading zeros
if args.view == 'front_depth' or args.view == 'front_IR':
spatial_transform = spatial_transforms.Compose([
crop_method,
spatial_transforms.RandomRotate(),
spatial_transforms.SaltImage(),
spatial_transforms.Dropout(),
spatial_transforms.ToTensor(args.norm_value),
spatial_transforms.Normalize([0], [1])
])
elif args.view == 'top_depth' or args.view == 'top_IR':
spatial_transform = spatial_transforms.Compose([
spatial_transforms.RandomHorizontalFlip(),
spatial_transforms.Scale(args.sample_size),
spatial_transforms.CenterCrop(args.sample_size),
spatial_transforms.RandomRotate(),
spatial_transforms.SaltImage(),
spatial_transforms.Dropout(),
spatial_transforms.ToTensor(args.norm_value),
spatial_transforms.Normalize([0], [1])
])
print(
"=================================Loading Anormal-Driving Training Data!================================="
)
training_anormal_data = DAD(root_path=args.root_path,
subset='train',
view=args.view,
sample_duration=before_crop_duration,
type='anormal',
std=get_std())
train_transform = spatial_transforms.Compose([
spatial_transforms.RandomResizedCrop(size=(WIDTH, WIDTH),
scale=(0.5, 1.0),
ratio=(1. - 0.1, 1. + 0.1)),
# spatial_transforms.RandomHorizontalFlip(),
spatial_transforms.ColorJitter(brightness=0.25,
contrast=0.25,
saturation=0.25,
hue=0.1),
normalize
])
# validation transform
val_transform = spatial_transforms.Compose([
# spatial_transforms.Resize(256),
spatial_transforms.CenterCrop(WIDTH),
normalize
])
target_transform = target_transforms.ClassLabel()
train_loader, val_loader = dataloader.get_loader(
root=DATA,
train_transform=train_transform,
val_transform=val_transform,
target_transform=target_transform,
batch_size=BATCH_SIZE,
num_frames=NUM_FRAMES,
step_size=FRAME_STEP,
val_samples=1,
n_threads=NUM_THREADS)
DECAY_STEP = EPOCH_DECAY_STEP * len(train_loader)
os.system('cp %s %s' % (MODEL_FILE, DUMP_DIR)) # bkp of model def
os.system('cp utils/net_utils.py %s ' % (DUMP_DIR)) # bkp of net_utils file
LOG_FOUT = open(os.path.join(DUMP_DIR, 'log_evaluate.txt'), 'w')
LOG_FOUT.write(str(FLAGS) + '\n')
NUM_CLASSES = FLAGS.num_classes
HOSTNAME = socket.gethostname()
# validation transform
normalize = spatial_transforms.ToNormalizedTensor(mean=get_mean(),
std=get_std())
if FCN == 0:
val_transform = spatial_transforms.Compose([
spatial_transforms.Resize(FULL_SIZE),
spatial_transforms.CenterCrop(WIDTH), normalize
])
elif FCN == 1:
val_transform = spatial_transforms.Compose([
spatial_transforms.Resize(FULL_SIZE),
spatial_transforms.CenterCrop(WIDTH), normalize
])
elif FCN == 3:
val_transform = spatial_transforms.Compose(
[spatial_transforms.Resize(FULL_SIZE), normalize])
elif FCN == 5:
val_transform = spatial_transforms.Compose(
[spatial_transforms.Resize(FULL_SIZE), normalize])
elif FCN == 6:
val_transform = spatial_transforms.Compose(
[spatial_transforms.Resize(FULL_SIZE), normalize])
normal_vec_top_ir = np.load('./normvec/normal_vec_top_ir.npy')
normal_vec_front_d = torch.from_numpy(normal_vec_front_d)
normal_vec_front_ir = torch.from_numpy(normal_vec_front_ir)
normal_vec_top_d = torch.from_numpy(normal_vec_top_d)
normal_vec_top_ir = torch.from_numpy(normal_vec_top_ir)
if use_cuda:
normal_vec_front_d = normal_vec_front_d.cuda()
normal_vec_front_ir = normal_vec_front_ir.cuda()
normal_vec_top_d = normal_vec_top_d.cuda()
normal_vec_top_ir = normal_vec_top_ir.cuda()
val_spatial_transform = spatial_transforms.Compose([
spatial_transforms.Scale(sample_size),
spatial_transforms.CenterCrop(sample_size),
spatial_transforms.ToTensor(255),
spatial_transforms.Normalize([0], [1]),
])
print(
"===========================================Loading Test Data=========================================="
)
test_data_front_d = DAD_Test(
root_path=root_path,
subset='validation',
view='front_depth',
sample_duration=sample_duration,
type=None,
spatial_transform=val_spatial_transform,