ybgdgh / L3MVN

Leveraging Large Language Models for Visual Target Navigation
https://sites.google.com/view/l3mvn
62 stars 13 forks source link

Where is legend.png? #3

Closed YESAndy closed 8 months ago

YESAndy commented 1 year ago

Hi

Thank you for sharing your work here! When i am running the evaluation command " python main_llm_vis.py --split val_mini --eval 1 --auto_gpu_config 0 -n 1 --num_eval_episodes 2000 --load pretrained_models/llm_model.pt --use_gtsem 0 --num_local_steps 10 It said: line 62, in init_vis_image lx, ly, _ = legend.shape AttributeError: 'NoneType' object has no attribute 'shape'

So I found out it is because there is no "legend.png" in your repo, see "self.legend = cv2.imread('docs/legend.png')" in line 72 in sem_exp.py.

Could you help? Thank you!

YESAndy commented 1 year ago

NVM, I found it in the Object Goal Navigation repo