oftenliu

1. 代码段augmentations.py：412～416行 centers = (boxes[:, :2] + boxes[:, 2:]) / 2.0 m1 = (choice_box[0] < centers[:, 0]) * (choice_box[1] < centers[:, 1]) m2 = (choice_box[2] > centers[:, 0]) * (choice_box[3]...

想请问下你这边训练时正负样本比例，以及产生正样本的阈值及loss的权重

你好，请问下sdm训练loss最终会收敛到一个什么范围的值？

when i load the pb model,i meet a problem as: tensorflow.python.framework.errors_impl.NotFoundError: Op type not registered 'ImageProjectiveTransformV2' in binary running on liuqiucheng. Make sure the Op and Kernel are registered in...

数据处理

1

utils.py中一条数据在处理完后为什么不在句子的末尾添加[SEP]

ValueError: With local_files_only set to None, you must first locally save the tokenizer in the following path: 'openai/clip-vit-large-patch14'.

9

error happens,like this: ValueError: With local_files_only set to None, you must first locally save the tokenizer in the following path: 'openai/clip-vit-large-patch14'. i try to run the demo in localhost @Paper99...

ValueError: With local_files_only set to None, you must first locally save the tokenizer in the following path: 'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k' with `pad_token` set to '!'.

3

error happen,like this: ValueError: With local_files_only set to None, you must first locally save the tokenizer in the following path: 'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k' with `pad_token` set to '!'.