var.to_csv(path+'/test_rmse.csv',index = False,header = False)
#var = pd.DataFrame(alpha1)
#var.to_csv(path+'/alpha.csv',index = False, header = False)
#print('min_rmse:%r'%(np.min(test_rmse)),
# 'min_mae:%r'%(np.min(test_mae)),
# 'max_acc:%r'%(np.max(test_acc)))
index = test_rmse.index(np.min(test_rmse))
#test_mae.index(np.min(test_mae))
#test_acc.index(np.max(test_acc))
test_result = test_pred[index]
var = pd.DataFrame(test_result)
var.to_csv(path+'/test_result.csv',index = False,header = False)
plot_result(test_result,test_label1,path)
plot_error(train_rmse,train_loss,test_rmse,test_acc,test_mae,path)
fig1 = plt.figure(figsize=(7,3))
ax1 = fig1.add_subplot(1,1,1)
plt.plot(np.sum(alpha1,0))
plt.savefig(path+'/alpha.jpg',dpi=500)
plt.show()
plt.imshow(np.mat(np.sum(alpha1,0)))
plt.savefig(path+'/alpha11.jpg',dpi=500)
plt.show()
print('min_rmse:%r'%(np.min(test_rmse)),
'min_mae:%r'%(test_mae[index]),
'max_acc:%r'%(test_acc[index]),
validation_label = target_cpu * max_value
validation_pred.append(pred_cpu * max_value)
# mae = np.mean(np.absolute(pred_unnormalized - target_unnormalized))
# validation_maes.append(mae)
out = None
val_input = val_input.to(device="cpu")
val_target = val_target.to(device="cpu")
print('epoch' + str(epoch))
print("Training loss: {}".format(training_losses[-1]))
print("Training rmse: {}".format(training_rmses[-1]))
print("Validation loss: {}".format(validation_losses[-1]))
print("Validation rmse: {}".format(validation_rmse[-1]))
print("Validation acc: {}".format(validation_acc[-1]))
if (epoch % 1000 == 0):
torch.save(net, './torchimage/model_epoch' + str(epoch) + '.pkl')
index = validation_rmse.index(
np.min(validation_rmse)) # 找出testrmse中最小的那个epoch
test_result = validation_pred[index]
var = pd.DataFrame(test_result)
var.to_csv('./torchimage' + '/test_result_epoch' + str(index) + '.csv',
index=False,
header=False)
print(validation_label.shape)
print(test_result.shape)
plot_result_3ave(test_result, validation_label,
'./torchimage/') # shape为[testbatch*prelen, num_nodes]
plot_error(training_rmses, training_losses, validation_rmse,
validation_acc, validation_maes, './torchimage/')