args.weights)
best_model.compile(optimizer=Adam(lr=best_lr), loss="binary_crossentropy")
print("Model built")
final_pred = best_model.predict_classes(X=Xs["test"],
batch_size=best_batch_size,
verbose=0)
test_perf = eval_pred(ys["test"], final_pred)
print("Test labels:")
print(list(ys["test"]))
print("Predictions")
print([x[0] for x in final_pred])
print("Test perf: {}".format(test_perf))
if args.mode == "aggregate":
best_model.save_weights(os.path.join(save_path, "best_weights.h5"),
overwrite=True)
summary = {
"best_lr": best_lr,
"best_epochs": best_epochs,
"best_dropout": best_dropout,
"best_dense_layers": best_dense_layers,
"best_dense_layer_units": best_dense_layer_units,
"best_batch_size": best_batch_size,
"ensemble_size": args.ensemble_size,
"test_ensemble_size": args.test_ensemble_size,
"test_perf": test_perf
}
print("\n".join(map(lambda x: "{}: {}".format(x[0], x[1]),
summary.items())),
file=open(os.path.join(save_path, "summary.txt"), "w"))
print("Building model")
model = ShallowNet(Xs["train"].shape[1], best_dropout, best_dense_layers, best_dense_layer_units, args.weights)
model.compile(optimizer=Adam(lr=best_lr), loss="binary_crossentropy")
print("Model built")
history = model.fit(
X=np.concatenate((Xs["train"], Xs["val"])),
y=np.concatenate((ys["train"], ys["val"])),
batch_size=best_batch_size,
nb_epoch=best_epochs,
verbose=1,
shuffle=True,
show_accuracy=True,
)
model.save_weights(os.path.join(save_path, "weights{}.h5".format(i)), overwrite=True)
print("\n".join(map(str, history.history["acc"])), file=open(os.path.join(save_path, "train_accs{}.txt".format(i)), "w"))
print("\n".join(map(str, history.history["loss"])), file=open(os.path.join(save_path, "train_losses{}.txt".format(i)), "w"))
pred = model.predict_classes(X=Xs["test"], batch_size=batch_size, verbose=0)
preds[:, i] = pred[:, 0]
final_pred = mode(preds, axis=1).mode
test_perf = eval_pred(ys["test"], final_pred)
else:
print("Building model")
model = ShallowNet(Xs["train"].shape[1], best_dropout, best_dense_layers, best_dense_layer_units, args.weights)
model.compile(optimizer=Adam(lr=best_lr), loss="binary_crossentropy")
print("Model built")
test_perf = eval_model(model, best_batch_size, Xs["test"], ys["test"])
best_dense_layers, best_dense_layer_units,
args.weights)
model.compile(optimizer=Adam(lr=best_lr), loss="binary_crossentropy")
print("Model built")
history = model.fit(
X=np.concatenate((Xs["train"], Xs["val"])),
y=np.concatenate((ys["train"], ys["val"])),
batch_size=best_batch_size,
nb_epoch=best_epochs,
verbose=1,
shuffle=True,
show_accuracy=True,
)
model.save_weights(os.path.join(save_path, "weights{}.h5".format(i)),
overwrite=True)
print("\n".join(map(str, history.history["acc"])),
file=open(os.path.join(save_path, "train_accs{}.txt".format(i)),
"w"))
print("\n".join(map(str, history.history["loss"])),
file=open(
os.path.join(save_path, "train_losses{}.txt".format(i)),
"w"))
pred = model.predict_classes(X=Xs["test"],
batch_size=batch_size,
verbose=0)
preds[:, i] = pred[:, 0]
final_pred = mode(preds, axis=1).mode
test_perf = eval_pred(ys["test"], final_pred)
best_val_perf = val_perf
best_model = model
else:
print("Building model")
best_model = ShallowNet(Xs["train"].shape[1], best_dropout, best_dense_layers, best_dense_layer_units, args.weights)
best_model.compile(optimizer=Adam(lr=best_lr), loss="binary_crossentropy")
print("Model built")
final_pred = best_model.predict_classes(X=Xs["test"], batch_size=best_batch_size, verbose=0)
test_perf = eval_pred(ys["test"], final_pred)
print("Test labels:")
print(list(ys["test"]))
print("Predictions")
print([x[0] for x in final_pred])
print("Test perf: {}".format(test_perf))
if args.mode == "aggregate":
best_model.save_weights(os.path.join(save_path, "best_weights.h5"), overwrite=True)
summary = {
"best_lr": best_lr,
"best_epochs": best_epochs,
"best_dropout": best_dropout,
"best_dense_layers": best_dense_layers,
"best_dense_layer_units": best_dense_layer_units,
"best_batch_size": best_batch_size,
"ensemble_size": args.ensemble_size,
"test_ensemble_size": args.test_ensemble_size,
"test_perf": test_perf
}
print("\n".join(map(lambda x: "{}: {}".format(x[0], x[1]), summary.items())), file=open(os.path.join(save_path, "summary.txt"), "w"))
