def predict_mnist():
dls = read_data_loaders()
lr = 1.
learn = Learner(dls=dls,
model=torch.nn.Linear(28 * 28, 1),
opt_func=SGD,
loss_func=mnist_loss,
metrics=batch_accuracy)
learn.fit(10, lr=lr)
def objective(trial: optuna.trial.Trial) -> float:
model = nn.Sequential(nn.Linear(20, 1), nn.Sigmoid())
learn = Learner(
data,
model,
loss_func=F.nll_loss,
metrics=[accuracy],
)
learn.fit(1, cbs=FastAIV2PruningCallback(trial))
return 1.0
# %%
learner = Learner(
mnist_dls,
ConvNet(),
loss_func=F.nll_loss,
metrics=[accuracy, Precision(average="macro"), Recall(average="macro")],
)
# %%[markdown]
#
# These are too many epochs, but we want to see the behavior of the net when it
# is trained for some time.
# %%
learner.fit(n_epoch=20)
# %%
pprint(list(learner.metrics))
# %%
model = learner.model
x, y = mnist_dls.valid.one_batch()
model, type(x), x.shape, type(y), y.shape
# %%
with torch.no_grad():
pred_proba = model(x)
# %%
pred_proba.shape
print(summary(mlp_model, torch.zeros((1, 1, 28, 28)).to(device), show_input=True))
print(summary(mlp_model, torch.zeros((1, 1, 28, 28)).to(device), show_input=False))
# %%
mlp_learner = Learner(
mnist_dls,
mlp_model,
metrics=[accuracy, Precision(average="macro"), Recall(average="macro")],
)
# %%
mlp_learner.lr_find()
# %%
with mlp_learner.no_bar():
mlp_learner.fit(n_epoch=4)
# %%
conv_model = nn.Sequential(
nn.Conv2d(1, 10, kernel_size=5, stride=(2, 2)),
nn.ReLU(),
nn.Conv2d(10, 20, kernel_size=5, stride=(2, 2)),
nn.ReLU(),
nn.Flatten(),
nn.Linear(320, 60),
nn.ReLU(),
nn.Linear(60, 10),
nn.LogSoftmax(dim=1),
).to(device)
# %%
