Cheng Yu
Cheng Yu
Thank you for sharing the code! I noticed that there seems to be no proper masking of the pad in the sequence in your code. In the item embedding, pad_idx...
Thank you for your great contributions! I noticed in your paper that the model is trained with a dataset from publicly available sources. Could you possibly provide further details about...
Thanks for your great work, however, I encountered one issue when running the pretraining code on my data, hope to get your assistant! **Issue Description:** When running pre-trained code, the...
感谢你的工作!当我使用时,我遇到了这样的报错: AttributeError: 'tuple' object has no attribute '__name__'. Did you mean: '__ne__'? 它在flops_engine.py, line 420触发: node_module_name = next(reversed(node.meta[_var_name].values())).__name__ 我还没有明白错误发生的原因,您对这个问题了解吗?如果需要进一步信息请告知,非常感谢!
Thank you for the excellent work! I have a question regarding the "Understanding Hyperparameters" function. This part is unable to handle the case where the input size is 4 (or...
您好!请教一下关于读取image格式的问题: 您使用了img = mmcv.imread(load_filename_with_extensions(data_path, filename)) 读取image, 默认读入的是bgr格式的。 但是我查看了使用的预训练模型sam, oneformer等等,注意到它们提供的demo中image输入都是rgb格式的,这种差异会对inference造成影响吗?_