Qian Wang
Qian Wang
把config.py中的load_model_path='checkpoints/model.pth' 改成load_model_path=None > user config: > lr_decay 0.95 > max_epoch 10 > model ResNet34 > use_gpu True > print_freq 20 > train_data_root ./data/train > lr 0.1 > num_workers 4 >...
+1
The same problem.
The input prompt and image is: prompt = "The white dog is singing" prev_p = ["The white dog"] ref_image = ["./data/image/00001.png"]
I see. So, how do you make a coherent story composed of several images and texts, just like what you did in the paper?
sh 改成 bash 试试