reg_model = create_model() save_graph_plot(reg_model, project_paths["plots"] + "/reg_model.ps") save_graph_json(reg_model, project_paths["plots"] + "/reg_model.json") reg_model_hist = reg_model.fit( train_images, train_labels, epochs=epochs, validation_data=(test_images, test_labels), callbacks=[csv_logger, callback_save_model_reg, callback_weights_reg]) model_list.append(reg_model_hist) model_name_list.append("Regular model ") # Pred Model # pred_model = create_model() pred_model = tf.keras.models.load_model(restore_path) pred_model_hist = pred_model.fit(train_images, train_labels, epochs=epochs - TotalSkips - 1, initial_epoch=FirstSkip, validation_data=(test_images, test_labels), callbacks=[csv_logger, callback_weights_pred]) model_list.append(pred_model_hist) model_name_list.append("Pred Model ") drawPlot_acc_loss(model_list, model_name_list, project_paths["plots"])
optimizer='adam', loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True), metrics=['accuracy']) reg_model_hist = reg_model.fit(train_images, train_labels, epochs=10, validation_data=(test_images, test_labels)) model_list.append(reg_model_hist) model_name_list.append("reg_model") norm_model = tf.keras.Sequential([ tf.keras.layers.Flatten(input_shape=(10, 10)), tf.keras.layers.Dense(15, activation='relu'), tf.keras.layers.Dense(10) ]) norm_model.compile( optimizer='adam', loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True), metrics=['accuracy']) norm_model_hist = norm_model.fit(train_images, train_labels, epochs=10, validation_data=(test_images, test_labels)) model_list.append(norm_model_hist) model_name_list.append("norm_model") #drawPlot_acc_loss(model_list, model_name_list,project_paths["plots"]) drawPlot_acc_loss(model_list, model_name_list, '/home/sap/IdeaProjects/XAI/April/plots')