某二次元的高坂桐乃

thanks！

Thank you so much！！

I edit gradcam_utils.py file (Line119) by this way to support the transformer-based models. gradients = self.target_gradients activations = self.target_activations if self.is_recognizer2d: # [B*Tg, C', H', W'] b_tg, c, _, _...

> @ZechengLi19 @ZechengLi19 Thank you very much! I have tried your modification but something went wrong. First, I suppose that feature_h = img_size/patch_size. Second, the param, target-layer-name, is set to...

> > [Ze ChengLi19](/ZechengLi19) > > 我按照您的建议编辑了 gradcam_utils.py 文件（第 119 行）。唯一的区别在于第 138 行和第 140 行，我在梯度和激活中省略了第一个元素（我猜这可能是 cls_token）以确保重塑过程。 > > 以下是修改内容： > > ``` > gradients = self.target_gradients > activations = self.target_activations...

> I tried using ImageNet pretrained ResNet18 on the TCGA dataset without normalizing the input image patches, it worked decently well. Make sure the model uses BatchNorm (not InstanceNorm which...

> > 该损失按预期正常减少。请注意，记录的损失是在一个短窗口内平均的，因此一些波动是正常的。 > > 感谢您的回复。我想在中文数据集上预训练 Blip2。所以我应该用中文版本的语言模型替换英文版本的语言模型。你能建议我应该使用哪种中文语言模型吗？ > > 该损失按预期正常减少。请注意，记录的损失是在一个短窗口内平均的，因此一些波动是正常的。 > > 感谢您的回复。我想在中文数据集上预训练 Blip2。所以我应该用中文版本的语言模型替换英文版本的语言模型。你能建议我应该使用哪种中文语言模型吗？ Same question!

> problem actually exists. Later we will relase a stronger DWPose model. The accuracy will gets higher. When will it be released? Will you continue to build on this repository?...

> Now the ms-celeb weight pre-training model cannot be downloaded, can you share it? Same question！

> > > > 请问你有了么，链接还是失效 you can check this link https://github.com/zyh-uaiaaaa/relative-uncertainty-learning