Closed SShah30-hue closed 1 year ago
It is because you failed to load the bert model. You should place the bert model in the correct path as in the open intent detection module :)
Hi Hanlei, thanks for your reply. I understand but it is already using the same path as open intent detection module which is /home/sharing/disk1/pretrained_embedding/bert/uncased_L-12_H-768_A-12/
and it works ok with open intent detection
.
I just git cloned the model from https://huggingface.co/google/bert_uncased_L-12_H-768_A-12/tree/main
and inserted it's dir path in the config file. It seems to have worked. Do you think it's the right approach?
I see. We have updated the open intent detection module so it can automatically download the needed pre-trained bert model. You can download the pre-trained bert model prepared in ADB repository and put it in the correct path. (Baidu Cloud Drive with code: v8tk). We will also update the open intent discovery module for more convenience within the next two months.
Thanks so much!
I have a different issue now - I am getting an error when setting the cluster_num_factor > 1 for intent discovery module. Below is the error:
Can you please explain why this is happening?
Hello, we have updated the codes and fixed the bugs. Please notify us if there are any other problems.
I have a different issue now - I am getting an error when setting the cluster_num_factor > 1 for intent discovery module. Below is the error:
Can you please explain why this is happening?
Hi,
Many thanks for this repo. I ran intent detection and it runs smoothly. However, I am facing issues with intent discovery. The requirements were the first issue I encountered as some of the libraries were not getting installed. I then used python 3.7 and all installations were completed except deepspeed and triton. I manually installed deepspeed==0.3.16 but could'nt get triton installed. Regardless, I continued along the tutorial and ran run.py file but got below error. Please can you offer any advice? Thanks
Below is the syntax I used:
python run.py --setting semi_supervised --dataset banking --known_cls_ratio 0.75 --train --save_results --results_file_name results_DeepAligned.csv --save_model --labeled_ratio 0.2