A practical neural network model was designed to realize the color space conversion of digitalphotof inishing. The sampling, network structure and training process were introduced respectively. But inactual training, the networks fall into local minimum in all probability. To solve this problem, evolutionaryprogramming (EP) algorithm was applied and the learning rate was adaptively adjusted. In the exper-iment, the performance of network was compared with pre-optimizing. Then the color space conversionwas evaluated by the simulation error of samples from the point of color difference. A practical neural network model was designed to realize the color space conversion of digitalphotof inishing. The sampling, network structure and training process were introduced respectively respectively. But inactual training, the networks fall into local minimum in all probability. To solve this problem, evolutionary programming ( EP) algorithm was applied and the learning rate was adaptively adjusted. In the exper-iment, the performance of network was compared with pre-optimizing. Then the color space conversionwas evaluated by the simulation error of samples from the point of color difference.