Training method of target model for predicting anemia evaluation index and related device

The embodiment of the invention provides a training method of a target model for predicting an anemia evaluation index and a related device, and the method comprises the steps: obtaining a training data set which comprises a first training data set and a second training data set; pre-training a coding module in a preset initial model by using the first training data set until a preset first convergence condition is met, and determining that the pre-training of the coding module is completed; training a decoding module in the initial model by taking a second eye image in a second training data set as a sample and an anemia detection index correspondingly matched with the second eye image as an expected true value of an anemia evaluation index under the condition of ensuring that network parameters in the pre-trained coding module are unchanged; and when the training of the decoding module in the initial model is completed, determining that the initial model is a target model for predicting the anemia evaluatio