luo3300612 / image-captioning-DLCT

Official pytorch implementation of paper "Dual-Level Collaborative Transformer for Image Captioning" (AAAI 2021).
BSD 3-Clause "New" or "Revised" License
193 stars 31 forks source link

TypeError: __init__() got an unexpected keyword argument 'train_on_pred_boxes' #30

Closed hwbhwbgao closed 2 years ago

hwbhwbgao commented 2 years ago

/usr/local/lib/python3.7/dist-packages/detectron2/config/config.py in wrapped(self, *args, kwargs) 188 if _called_with_cfg(*args, *kwargs): 189 explicit_args = _get_args_from_config(from_config_func, args, kwargs) --> 190 init_func(self, *explicit_args) 191 else: 192 init_func(self, args, **kwargs)

TypeError: init() got an unexpected keyword argument 'train_on_pred_boxes' 作者您好,我在复现您论文时,在实现提取特征的代码时出现该问题,我查询了相关的,但是没有解决?

competent-s commented 2 years ago

我也遇到了同样的问题,请问您解决了吗?

hwbhwbgao commented 2 years ago

我是在colab上运行该代码的,具体特征提取已经完成。但是对于该问题解决方案: !pip install -U git+https://github.com/facebookresearch/fvcore !python -m pip install 'git+https://github.com/facebookresearch/detectron2.git@ffff8ac' 希望对您有帮助!

competent-s commented 2 years ago

我是在colab上运行该代码的,具体特征提取已经完成。但是对于该问题解决方案: !pip install -U git+https://github.com/facebookresearch/fvcore !python -m pip install 'git+https://github.com/facebookresearch/detectron2.git@ffff8ac' 希望对您有帮助!

你好,我想问一下,grid特征提取的代码?因为使用grid-feats-vqa这个里面的extract_grid_feature.py提取grid特征的维度会有问题,和作者百度云提供的特征不一样

hwbhwbgao commented 2 years ago

我没有去专门提取grid特征,不好意思。