from src.training import SGD, SPDG from src.statistics import get_statistics import matplotlib.pyplot as plt torch.manual_seed(671470554) np.random.seed(70914308) # %% GENERATING DATASET ngram = Ngram(3) ngram[(0, 1, 2)] = 6. ngram[(1, 2, 3)] = 4. ngram.norm() data_loader = train_loader_MNIST() test_loader = test_loader_MNIST() sequence_loader = sequence_loader_MNIST(ngram, num_samples=40000) # %% REGULAR TRAINING (SGD) # model = Model(ngram) # model.to(DEVICE) # model.init_weights() # optimizer = torch.optim.Adam(model.primal.parameters()) # history = SGD(model, optimizer, data_loader, test_loader, num_epochs=1, log_every=50, test_every=1) # %% DUAL TRAINING model = Model(ngram, output_size=4) model.to(DEVICE) model.init_weights() primal_lr = 1e-6
test_every = 5
primal_lr = 1e-6
dual_lr = 1e-4
# %% GENERATING DATASET
# ngram = randomized_ngram(3, 2, out_dim=4, min_var=5e-2)
ngram = Ngram(3)
ngram[(0, 1, 2)] = 9.
ngram[(1, 2, 3)] = 1.
ngram.norm()
ngram.show()
# %% CREATING MODEL
data_loader = train_loader_MNIST()
test_loader = test_loader_MNIST()
sequence_loader = sequence_loader_MNIST(ngram, num_samples=50000)
sequence_test_loader = sequence_loader_MNIST(ngram, num_samples=10000)
# %% REGULAR TRAINING (SGD)
# model = Model(ngram)
# model.to(DEVICE)
# model.init_weights()
# optimizer = torch.optim.Adam(model.primal.parameters())
# history = SGD(model, optimizer, data_loader, test_loader, num_epochs=1, log_every=50, test_every=1)
# %% DUAL TRAINING
if continuation:
history, model, ngram, optimizer_primal, optimizer_dual = load()
print(model.ngram.n)
else:
# %% CREATING NGRAM
# ngram = randomized_ngram(3, 20, out_dim=4, min_var=-1e-2)
# ngram = Ngram(3)
# ngram[(0, 1, 2)] = 9.
# ngram[(1, 2, 3)] = 1.
# ngram.norm()
ngram_gen = get_brown_ngram(dim=3)
# ngram_gen = ngram
# ngram_gen.show()
# %% GENERATING DATASET
data_loader = train_loader_MNIST()
test_loader = test_loader_MNIST()
sequence_loader = sequence_loader_MNIST(ngram_gen,
num_samples=2000,
sequence_length=30)
sequence_test_loader = sequence_loader_MNIST(ngram_gen,
num_samples=10000,
train=False)
t = time.time()
stats = get_sequences_distribution(sequence_loader)
print(time.time() - t)
print(stats)
# %%
ngram = retrieve_ngram(sequence_loader, 3)
ngram.show()
# %% REGULAR TRAINING (SGD)
# %% CREATING NGRAM # ngram = randomized_ngram(3, 20, out_dim=4, min_var=-1e-2) ngram = Ngram(3) ngram[(0, 1, 2)] = 6. ngram[(1, 2, 3)] = 4. # ngram.norm() # ngram_gen = get_brown_ngram(dim=3) ngram_gen = ngram # ngram_gen.show() # %% GENERATING DATASET data_loader = train_loader_MNIST() test_loader = test_loader_MNIST() sequence_loader = sequence_loader_MNIST(ngram_gen, num_samples=40000) sequence_test_loader = sequence_loader_MNIST(ngram_gen, num_samples=10000, train=False) t = time.time() stats = get_sequences_distribution(sequence_loader) print(time.time() - t) print(stats) # %% # ngram = retrieve_ngram(sequence_loader, 3) # ngram.show() # %% REGULAR TRAINING (SGD) # model = Model(ngram) # model.to(DEVICE)
loss_on_test = False
# %% CREATING NGRAM
# ngram = randomized_ngram(3, 27, out_dim=3, min_var=-1e-2)
# ngram = Ngram(3)
# ngram[(0, 1, 2)] = 9.
# ngram[(1, 2, 3)] = 1.
# ngram.norm()
ngram = get_brown_ngram()
ngram.show()
# %% GENERATING DATASET
data_loader = train_loader_MNIST()
test_loader = test_loader_MNIST()
sequence_loader = sequence_loader_MNIST(ngram,
num_samples=2000,
sequence_length=30)
sequence_test_loader = sequence_loader_MNIST(ngram, num_samples=10000)
# %% REGULAR TRAINING (SGD)
# model = Model(ngram)
# model.to(DEVICE)
# model.init_weights()
# optimizer = torch.optim.Adam(model.primal.parameters())
# history = SGD(model, optimizer, data_loader, test_loader, num_epochs=1, log_every=50, test_every=1)
# %% DUAL TRAINING
if continuation:
history, model, ngram, optimizer_primal, optimizer_dual = load()
print(model.ngram.n)