def main():
X_train, y_train, inpz_train = load('data/train/merged.npz')
X_test, y_test, inpz_test = load('data/test/merged.npz')
# One-hot encoded
Y_train = to_categorical(y_train, 2)
Y_test = to_categorical(y_test, 2)
Phi_sizes, F_sizes = (100, 100, 128), (100, 100, 100)
efn = EFN(input_dim=2, Phi_sizes=Phi_sizes, F_sizes=F_sizes)
efn.load_weights('ckpts_Apr06_134930/ckpt-40-val_acc-0.73.hdf5')
ckpt_dir = strftime('ckpts_%b%d_%H%M%S')
if not osp.isdir(ckpt_dir): os.makedirs(ckpt_dir)
checkpoint_callback = ModelCheckpoint(
ckpt_dir + '/ckpt-{epoch:02d}-val_acc-{val_acc:.3f}.hdf5',
monitor='val_acc',
verbose=1,
save_best_only=False,
mode='max')
best_checkpoint_callback = ModelCheckpoint(ckpt_dir + '/ckpt-best.hdf5',
monitor='val_acc',
verbose=1,
save_best_only=True,
mode='max')
efn.fit([X_train[:, :, 0], X_train[:, :, 1:]],
Y_train,
epochs=40,
batch_size=64,
validation_data=([X_test[:, :, 0], X_test[:, :, 1:]], Y_test),
verbose=1,
callbacks=[checkpoint_callback, best_checkpoint_callback])
print('Finished preprocessing')
# do train/val/test split
(z_train, z_val, z_test, p_train, p_val, p_test, Y_train, Y_val,
Y_test) = data_split(X[:, :, 0], X[:, :, 1:], Y, val=val, test=test)
print('Done train/val/test split')
print('Model summary:')
# build architecture
efn = EFN(input_dim=2, Phi_sizes=Phi_sizes, F_sizes=F_sizes)
# train model
efn.fit([z_train, p_train],
Y_train,
epochs=num_epoch,
batch_size=batch_size,
validation_data=([z_val, p_val], Y_val),
verbose=1)
# get predictions on test data
preds = efn.predict([z_test, p_test], batch_size=1000)
# get ROC curve
efn_fp, efn_tp, threshs = roc_curve(Y_test[:, 1], preds[:, 1])
# get area under the ROC curve
auc = roc_auc_score(Y_test[:, 1], preds[:, 1])
print()
print('EFN AUC:', auc)
print()
f_sizes = (100, 100, 100)
X, Y = load_data(2000000, 'final_efn_train')
X = preprocess(X)
Y = ef.utils.to_categorical(Y)
(Z_train, Z_val, Z_test, P_train, P_val, P_test, Y_train, Y_val,
Y_test) = split_data(X[:, :, 0],
X[:, :, [1, 2]],
Y,
test_prop=1.0 / 5,
val_prop=1.0 / 5)
#adam = optimizers.Adam(lr=.005)
efn = EFN(input_dim=P_train.shape[-1],
Phi_sizes=phi_sizes,
F_sizes=f_sizes)
efn.fit([Z_train, P_train],
Y_train,
epochs=NUM_EPOCHS,
batch_size=500,
validation_data=([Z_val, P_val], Y_val),
verbose=1)
preds = efn.predict([Z_test, P_test], batch_size=1000)
fpr, tpr, thresholds = roc_curve(Y_test[:, 1], preds[:, 1])
print('AUC: ' + str(auc(fpr, tpr)))
plt.plot(tpr, 1 - fpr, '-', color='black', label='EFN')
plt.show()
es = EarlyStopping(monitor='val_auc',
mode='max',
verbose=1,
patience=20,
restore_best_weights=True)
#mc = ModelCheckpoint('best_model.h5', monitor='val_auc', mode='max', verbose=1, save_best_only=True)
efn = EFN(input_dim=2,
Phi_sizes=Phi_sizes,
F_sizes=F_sizes,
metrics=['acc', auc],
Phi_l2_regs=5e-05,
F_l2_regs=5e-05)
history = efn.fit([z_train, p_train],
Y_train,
epochs=num_epoch,
batch_size=batch_size,
validation_data=([z_val, p_val], Y_val),
verbose=1,
callbacks=[es])
#dependencies = {
# 'auc': tf.keras.metrics.AUC(name="auc")
#}
#saved_model = load_model('best_model.h5', custom_objects=dependencies)
#preds = saved_model.predict([z_test, p_test], batch_size=1000)
preds = efn.predict([z_test, p_test], batch_size=1000)
auc = roc_auc_score(Y_test[:, 1], preds[:, 1])
print('EFN AUC:', auc)
#save plots
name = "{0}Jet_{1}Tag".format(args.nJets, args.nTags)