OOM when allocating tensor with shape[300,14,14,256] and type float on /job:localhost/replica:0/tas
训练mask-R-cnn模型,训练时将model.train(dataset_train, dataset_val,learning_rate=config.LEARNING_RATE,epochs=40,layers='heads')中的layers=‘heads’修改成layers='4+',结果报错OOM when allocating tensor with shape[300,25...