def test_step_with_model(self, optim_class):
torch.manual_seed(1234)
inp, tar = torch.randn(10, 3), torch.randn(10, 1)
net = torch.nn.Linear(3, 1)
model = Model(net, torch.nn.MSELoss(), optim_class(lr=0.1))
params = get_params(net)
model.fit(inp, tar, verbose=False)
new_params = get_params(net)
with pytest.raises(AssertionError) as ex:
assert_tupletree_equal(params, new_params)
assert str(ex.value) == "Not equal values"
def test_readme_example():
import torch
from torch import nn
from torchtuples import Model, optim
torch.manual_seed(0)
n = 500
x0, x1, x2 = [torch.randn(n, 3) for _ in range(3)]
y = torch.randn(n, 1)
x = (x0, (x0, x1, x2))
class Net(nn.Module):
def __init__(self):
super().__init__()
self.lin_tuple = nn.Linear(3, 2)
self.lin_cat = nn.Linear(5, 1)
self.relu = nn.ReLU()
def forward(self, x_tensor, x_tuple):
x = [self.relu(self.lin_tuple(xi)) for xi in x_tuple]
x = torch.stack(x).mean(0)
x = torch.cat([x, x_tensor], dim=1)
return self.lin_cat(x)
model = Model(Net(), nn.MSELoss(), optim.SGD(0.01))
log = model.fit(x, y, batch_size=64, epochs=5, verbose=False)
preds = model.predict(x)
assert preds is not None
emb_model_filename = \
os.path.join(output_dir, 'models',
'rsf_full_train_neural_approx_'
+
'%s_exp%d_mf%d_msl%d_km%d_'
% (dataset, experiment_idx,
max_features, min_samples_leaf, use_km)
+
'bs%d_nep%d_nla%d_nno%d_'
% (batch_size, 100, n_layers, n_nodes)
+
'lr%f_test.pt' % lr)
if not os.path.isfile(emb_model_filename):
emb_model.fit(X_train_std, mds_embedding,
batch_size=batch_size, epochs=100,
verbose=False)
emb_model.save_net(emb_model_filename)
else:
emb_model.load_net(emb_model_filename)
emb_model.net.train()
print('*** Fine-tuning with DKSA...')
torch.manual_seed(fine_tune_random_seed + 1)
np.random.seed(fine_tune_random_seed + 1)
optimizer = tt.optim.Adam(lr=lr)
if num_durations > 0:
labtrans = NKSDiscrete.label_transform(num_durations)
y_train_discrete = labtrans.fit_transform(*y_train.T)
surv_model = NKSDiscrete(emb_model.net, optimizer,
duration_index=labtrans.cuts)