mod = RegionEncoder(n_nodes=n_nodes,
n_nodal_features=n_nodal_features,
h_dim_graph=h_dim_graph,
h_dim_img=h_dim_img,
lambda_ae=lambda_ae,
lambda_edge=lambda_edge,
lambda_g=lambda_g,
neg_samples_gcn=neg_samples_gcn,
h_dim_size=h_dim_size,
img_dims=img_dims,
lambda_weight_decay=lambda_weight_decay)
mod.run_train_job(region_grid, epochs=epochs, lr=learning_rate, tol_order=3)
if torch.cuda.is_available():
embedding = mod.embedding.data.cpu().numpy()
else:
embedding = mod.embedding.data.numpy()
fname = "{}embedding-iter-{}.txt".format(OUT_DIR, i)
write_embeddings(arr=embedding, n_nodes=n_nodes, fname=fname)
with open(OUT_DIR + "params-{}.txt".format(i), 'w') as f:
param = params[i]
f.write("{}: ".format(i))
for p in param:
f.write("{:.4f}, ".format(p))
f.write("\n")
epochs = int(sys.argv[1])
learning_rate = float(sys.argv[2])
else:
epochs = 25
learning_rate = .1
context_gcn = 4
neg_samples_gcn = 10
c = get_config()
region_grid = RegionGrid(config=c)
region_grid.load_weighted_mtx()
n_nodes = len(region_grid.regions)
h_dim_size = int(c['hidden_dim_size'])
n_nodal_features = region_grid.feature_matrix.shape[1]
gcn = GCN(n_features=n_nodal_features, h_dim_size=h_dim_size)
embedding = gcn.run_train_job(region_grid, n_epoch=epochs, learning_rate=learning_rate, penalty=(1, 1),
n_neg_samples=context_gcn, n_pos_samples=neg_samples_gcn)
if torch.cuda.is_available():
embedding = embedding.data.cpu().numpy()
else:
embedding = embedding.data.numpy()
embed_fname = '{}gcn_all_embedding.txt'.format(c['data_dir_main'])
write_embeddings(arr=embedding, n_nodes=region_grid.n_regions, fname=embed_fname)
if __name__ == "__main__":
import numpy as np
from grid.create_grid import RegionGrid
if len(sys.argv) > 1:
epochs = int(sys.argv[1])
learning_rate = float(sys.argv[2])
batch_size = int(sys.argv[3])
else:
epochs = 25
learning_rate = .05
batch_size = 25
c = get_config()
region_grid = RegionGrid(config=c)
region_grid.load_img_data(std_img=True)
img_tensor = torch.Tensor(region_grid.img_tensor)
h_dim_size = int(c['hidden_dim_size'])
auto_encoder = AutoEncoder(img_dims=(50, 50), h_dim_size=h_dim_size)
embedding = auto_encoder.run_train_job(n_epoch=epochs, img_tensor=img_tensor, lr=learning_rate)
if torch.cuda.is_available():
embedding = embedding.data.cpu().numpy()
else:
embedding = embedding.data.numpy()
write_embeddings(arr=embedding, n_nodes=region_grid.n_regions, fname=c['tile2vec_file'])
h_dim_graph = 64
h_dim_img = 64
h_dim_size = int(c['hidden_dim_size'])
lambda_ae = .5
lambda_edge = .1
lambda_g = .1
neg_samples_gcn = 10
epochs = 15
learning_rate = .1
if len(sys.argv) > 1:
epochs = int(sys.argv[1])
learning_rate = float(sys.argv[2])
mod = RegionEncoder(n_nodes=n_nodes,
n_nodal_features=n_nodal_features,
h_dim_graph=h_dim_graph,
h_dim_img=h_dim_img,
lambda_ae=lambda_ae,
lambda_edge=lambda_edge,
lambda_g=lambda_g,
neg_samples_gcn=neg_samples_gcn,
h_dim_size=h_dim_size)
mod.run_train_job(region_grid, epochs=epochs, lr=learning_rate, tol_order=3)
if torch.cuda.is_available():
embedding = mod.embedding.data.cpu().numpy()
else:
embedding = mod.embedding.data.numpy()
write_embeddings(arr=embedding, n_nodes=n_nodes, fname=c['embedding_file'])
mod.plt_learning_curve("plots/region-learning-curve.pdf", plt_all=False, log_scale=True)
if len(sys.argv) > 1:
epochs = int(sys.argv[1])
learning_rate = float(sys.argv[2])
batch_size = int(sys.argv[3])
else:
epochs = 25
learning_rate = .1
batch_size = 20
c = get_config()
region_grid = RegionGrid(config=c)
region_grid.load_img_data(std_img=True)
img_tensor = torch.Tensor(region_grid.img_tensor)
h_dim_size = int(c['hidden_dim_size'])
auto_encoder = AutoEncoder(img_dims=(50, 50), h_dim_size=h_dim_size)
embedding = auto_encoder.run_train_job(n_epoch=epochs,
batch_size=batch_size,
img_tensor=img_tensor,
lr=learning_rate)
if torch.cuda.is_available():
embedding = embedding.data.cpu().numpy()
else:
embedding = embedding.data.numpy()
write_embeddings(arr=embedding,
n_nodes=region_grid.n_regions,
fname=c['autoencoder_embedding_file'])
import sys sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))) from config import get_config from grid.create_grid import RegionGrid from model.utils import write_embeddings c = get_config() region_grid = RegionGrid(config=c) region_grid.load_img_data(std_img=True) region_grid.load_img_data() h_dim_size = int(c['hidden_dim_size']) img_dims = region_grid.img_tensor.shape n_samples = img_dims[0] n_channel = img_dims[1] n_rows = img_dims[2] n_cols = img_dims[3] flat_shape = n_channel*n_rows*n_cols X = region_grid.img_tensor.reshape((n_samples, flat_shape)) pca_model = PCA(n_components=h_dim_size) embedding = pca_model.fit_transform(X) write_embeddings(embedding, n_nodes=n_samples, fname=c['pca_file'])