Should structure data in a similar way, but simply use a different label type.
Training can be performed initially by-structure, just to get the code up and running.
'''
# --- Parameter setting -----
if p.suppress_warnings:
import warnings
warnings.filterwarnings("ignore")
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
cpu = torch.device('cpu')
# reproducibility
torch.manual_seed(p.random_seed)
np.random.seed(p.random_seed)
learn_rate = p.learn_rate
modelpath = make_model_directory('c_beta_models')
epochs = p.epochs
# ---- Importing and structuring Datasets and Model ----
# Remember!!! Shape Index can only be computed on local. Add other transforms after
# Pre_tranform step to not contaminate the data.
trainset = StructuresDataset(
root='/work/upcorreia/users/dcoukos/datasets/res_train/'
) #Pretranforms performed on local.
validset = trainset[:150]
trainset = trainset[150:]
model = p.model_type(3, heads=p.heads).to(cpu)
model.to(device)
optimizer = torch.optim.Adam(model.parameters(),
from statistics import mean
import torch.nn.functional as F
from tqdm import tqdm
# --- Parameter setting -----
if p.suppress_warnings:
import warnings
warnings.filterwarnings("ignore")
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
cpu = torch.device('cpu')
# reproducibility
torch.manual_seed(p.random_seed)
np.random.seed(p.random_seed)
learn_rate = p.learn_rate
modelpath = make_model_directory()
if str(device) == 'cuda:0':
epochs = p.epochs
else:
epochs = 20
# ---- Importing and structuring Datasets and Model ----
print('Importing structures.')
# Remember!!! Shape Index can only be computed on local. Add other transforms after
# Pre_tranform step to not contaminate the data.
trainset = Structures(root='./datasets/masif_site_train/',
pre_transform=Compose((FaceAttributes(), NodeCurvature(),
FaceToEdge(), TwoHop())))
# Define transform in epoch, so that rotation occurs around Δ axis every time.
validset = Structures(root='./datasets/masif_site_test/',
