FILM icon indicating copy to clipboard operation
FILM copied to clipboard

Official repository of ICLR 2022 paper FILM: Following Instructions in Language with Modular Methods

Results 24 FILM issues
Sort by recently updated
recently updated
newest added

Sorry to bother you. When I tried to execute the main.py on a headless machine, there came some errors about: ALSA lib confmisc.c:855:(parse_card) cannot find card '0' ALSA lib conf.c:5204:(_snd_config_evaluate)...

Sorry to bother you. When I tried to execute the main.py on a headless machine, there came some errors about: ALSA lib confmisc.c:855:(parse_card) cannot find card '0' ALSA lib conf.c:5204:(_snd_config_evaluate)...

Hello @soyeonm , I am running main.py commands given in the README.md , I am getting 'Insufficient GPU Memory'. I have a 4GB Nvidia 1650Ti. 1. I wanted to know...

Hey, for the pretrained **receptacle Mask RCNN**, where is the corresponding label set (classes) that contains the **32** categories? The `alfworld_receptacles` variable contains 38 classes, and upon visualizing the bboxes,...

Hi, thanks for sharing this amazing work! I've read your paper and in Table 3 (Section 5.2) you show the percentage of error mode of FILM. It would be great...

Could you please provide more details about how to implement the works mentioned in the paper : "Fine-tuning a pre-trained BART (Lewis et al., 2020) model, we directly learned a...

I ran the experiment just like the command on github, and I used trained model weight on Google drive. However, I could not reproduce the number shown in the paper....

Auto GPU config: Number of processes: 14 Number of processes on GPU 0: 14 Number of processes per GPU: 0 Found path: /home/user/.ai2thor/releases/thor-201909061227-Linux64/thor-201909061227-Linux64 Mono path[0] = '/home/user/.ai2thor/releases/thor-201909061227-Linux64/thor-201909061227-Linux64_Data/Managed' Mono config path...

Hello,Semantic search data set link failed.Is there any other link?https://github.com/soyeonm/FILM/blob/public

We were reviewing the `main.py` script that loads `traj_data` from `alfred_data_all`, a subset of the data, and generates evaluation results for multiple modules, excluding the `BERT` module. However, upon submitting...