Huanyi Xie

multi_languages_ocr_db_crnn类型错误

1

我在ai studio上使用paddlehub的multi_languages_ocr_db_crnn，但是出现报错如下： ``` --------------------------------------------------------------------------- TypeError Traceback (most recent call last) /tmp/ipykernel_26157/1143782944.py in 3 4 ocr = hub.Module(name="multi_languages_ocr_db_crnn", lang='en') # mkldnn加速仅在CPU下有效 ----> 5 result = ocr.recognize_text(paths=['/home/aistudio/test/test4.jpg']) /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddlehub/compat/paddle_utils.py in runner(*args, **kwargs) 219...

cannot import name 'PPO' from 'parl.algorithms'

7

my code: ``` from parl.algorithms import PPO ``` my parl version: ``` grpcio-1.37.0 parl-2.2.1 pyzmq-18.1.1 tensorboardX-2.5 ``` what can I do to solve this problem?

Graph4KG的ComplEx跑验证集时Out of Memory

2

使用ai studio上的32g v100在OpenBG500数据集上跑RotatE模型，训练集正常，测试集无论bs调多少都会OOM。 我的代码: ``` !python -u train.py --model_name RotatE \ --data_name OpenBG500\ --data_path /home/aistudio/data/\ --save_path /home/aistudio/result/Rotate --max_steps 1\ --batch_size 1 --log_interval 1000 --eval_interval 20000 --reg_coef 1e-7 --reg_norm 3 \...

I am recently finetuning a gpt-like model on some toy-dataset with fake personal data. I am trying to test differential privacy on this LLMs. I wonder if pyvacy will work...

How to train on a customied dataset?

1

I have a dataset with molcules and their atoms, positions, energy, and forces information. I wonder how to train my dataset with equiformer_v2. Is it possible to support customied dataset...