np.random.seed(1)
if __name__ == "__main__":
# Load data
x_test, y_test, names = read_names_test()
classes = read_names_countries()
print(x_test.shape)
# Load model model
model = Sequential(loss=CrossEntropy())
model.load("models/names_test")
# model.load("models/names_no_compensation")
y_pred_prob_test = model.predict(x_test)
y_pred_test = model.predict_classes(x_test)
print(y_pred_prob_test)
print(y_test)
plot_confusion_matrix(y_pred_test, y_test, classes, "figures/conf_test")
import matplotlib.pyplot as plt
plt.title("Prediction Vectors")
pos = plt.imshow(y_pred_prob_test.T)
plt.xticks(range(len(classes)), classes, rotation=45, ha='right')
plt.yticks(range(len(names)), names)
# plt.xticks(rotation=45, ha='right')
plt.colorbar(pos)
plt.savefig("figures/prob_vector_test")
plt.show()
model.add(Softmax())
# for filt in model.layers[0].filters:
# print(filt)
# y_pred_prob = model.predict(x_train)
# print(y_pred_prob)
# Fit model
model.fit(X=x_train,
Y=y_train,
X_val=x_val,
Y_val=y_val,
batch_size=100,
epochs=200,
lr=1e-2,
momentum=0.5,
callbacks=callbacks)
model.save("models/mnist_test_conv_2")
# model.layers[0].show_filters()
# for filt in model.layers[0].filters:
# print(filt)
# print(model.layers[0].biases)
mt.plot_training_progress()
y_pred_prob = model.predict(x_train)
# # # model.pred
# print(y_train)
# print(np.round(y_pred_prob, decimals=2))
