search

batra-mlp-lab / visdial-rl

PyTorch code for Learning Cooperative Visual Dialog Agents using Deep Reinforcement Learning
170 stars 39 forks source link

KeyError: 'test_ans_ind' #8

Closed badripatro closed 6 years ago

badripatro commented 6 years ago

Hi When I run this command

CUDA_VISIBLE_DEVICES=4 python train.py -useGPU -trainMode sl-qbot -enableVisdom 1 \ -visdomServer http://127.0.0.1 -visdomServerPort 8098 -visdomEnv my-qbot-job

I got this error

File "train.py", line 39, in dataset = VisDialDataset(params, splits) File "/home/badri/badripatro/workspace_project/visual_dialog/visdial-rl-master_v10/dataloader.py", line 149, in init self.prepareDataset(dtype) File "/visdial-rl-master_v10/dataloader.py", line 185, in prepareDataset self.data[dtype + '_ans_ind'] -= 1 KeyError: 'test_ans_ind'

Should I change in the "propro.py" file?

These are the keys present in "chat_processed_data.h5" file

f = h5py.File("chat_processed_data.h5") list(f) ['ans_index_train', 'ans_index_val', 'ans_length_test', 'ans_length_train', 'ans_length_val', 'ans_test', 'ans_train', 'ans_val', 'cap_length_test', 'cap_length_train', 'cap_length_val', 'cap_test', 'cap_train', 'cap_val', 'img_pos_test', 'img_pos_train', 'img_pos_val', 'num_rounds_test', 'opt_length_test', 'opt_length_train', 'opt_length_val', 'opt_list_test', 'opt_list_train', 'opt_list_val', 'opt_test', 'opt_train', 'opt_val', 'ques_length_test', 'ques_length_train', 'ques_length_val', 'ques_test', 'ques_train', 'ques_val']

kdexd commented 6 years ago

Hi @badripatro - it is a recently introduced bug in #8 mainly caused by a difference in schema between VisDial v0.5 and v1.0. We continue to offer out of the box support for v0.5 with this codebase. I have opened #9, once it gets merged, you may pull from master and this issue will be resolved. :slightly_smiling_face:

kdexd commented 6 years ago

Hi @badripatro: #9 is merged, please pull from master.

badripatro commented 6 years ago

Thanks a lot.