jutyer notebook中RVAEload_weightscheckpointscheckpoint train_mu = utilsviz_latent_spaceRVAEencoder npconcatenatex_train x_val npconcatenatey_train y_val test_mu = utilsviz_latent_spaceRVAEencoder
加载模型权重
RVAE.load_weights('./checkpoints/checkpoint')
可视化训练和验证集的潜在空间
train_mu = utils.viz_latent_space(RVAE.encoder, np.concatenate((x_train, x_val)), np.concatenate((y_train, y_val)))
可视化测试集的潜在空间
test_mu = utils.viz_latent_space(RVAE.encoder, x_test, y_test.clip(upper=threshold))
使用回归器预测训练集和测试集的目标变量
y_hat_train = RVAE.regressor.predict(train_mu) y_hat_test = RVAE.regressor.predict(test_mu)
评估训练集和测试集的预测结果
utils.evaluate(np.concatenate((y_train, y_val)), y_hat_train, 'train') utils.evaluate(y_test, y_hat_test, 'test'
原文地址: https://www.cveoy.top/t/topic/cimg 著作权归作者所有。请勿转载和采集!