# value_range=[32],
# log=False)
#Init autonet
# autoPyTorch = AutoNetClassification(hyperparameter_search_space_updates=search_space_updates, # config
autoPyTorch = AutoNetClassification(
# "full_cs", # config
networks=["resnet"],
# torch_num_threads=2,
log_level='info',
budget_type='epochs',
min_budget=5,
max_budget=20,
num_iterations=100,
cuda=True,
use_pynisher=False)
#fit
autoPyTorch.fit(X_train=X_train,
Y_train=y_train,
X_valid=X_test,
Y_valid=y_test,
optimize_metric="auc_metric",
loss_modules=["cross_entropy", "cross_entropy_weighted"])
#predict
y_pred = autoPyTorch.predict(X_test)
#check
print("Accuracy score", sklearn.metrics.accuracy_score(y_test, y_pred))
print("Confusion matrix",
sklearn.metrics.confusion_matrix(y_test, y_pred, labels=le.classes_))
print(autoPyTorch)
pytorch_model = autoPyTorch.get_pytorch_model()
print(pytorch_model)
results_fit = autonet.fit(X_train=X_train,
Y_train=Y_train,
validation_split=0.3,
max_runtime=300,
min_budget=60,
max_budget=100,
refit=True)
# Save fit results as json
with open("logs/results_fit.json", "w") as file:
json.dump(results_fit, file)
# See how the random configuration performs (often it just predicts 0)
score = autonet.score(X_test=X_test, Y_test=Y_test)
pred = autonet.predict(X=X_test)
print("Model prediction:", pred[0:10])
print("Accuracy score", score)
pytorch_model = autonet.get_pytorch_model()
print(pytorch_model)
# Load fit results as json
with open("logs/results_fit.json") as file:
results_fit = json.load(file)
# Create an autonet
autonet_config = {
"result_logger_dir": "logs/",
"budget_type": "epochs",
"log_level": "info",
"use_tensorboard_logger": True,
"validation_split": 0.0
}
autonet = AutoNetClassification(**autonet_config)
# Sample a random hyperparameter configuration as an example
hyperparameter_config = autonet.get_hyperparameter_search_space(