523997931

about pretrained mode to finetune

1

Hello, I try to use the pretrained model that you provided to finetune, but when I use train script to set the ckpt, it tell me like this: 2021/07/08 20:26:17...

训练animegan 无法复现出原有效果

2

尝试使用原本的配置，对animegan进行训练，按照文档指引，一步一步做的，但是，无法复现出原本的效果

向量支持的数据类型

5

想问一下，vearch是否支持量化后的向量相似度检索，比如，我们想使用16位的float组成的向量来进行检索，而不是32位，甚至可能使用8位的情况，来减少计算量提升效率

How can I did better in car model.

2

Hello, this days I try to use multiview pictures to build the car model, I use the example data, and I also search some picture from websites, same as the...

第四章经典网络 resnet

1

resnet部分发现完全是空的，和目录对不上，是什么原因呢

about load pruned model

1

when I try to load the pruned model, it report error RuntimeError: Error(s) in loading state_dict for MobileNetV3: Missing key(s) in state_dict: "features.1.conv.4.bias", "features.2.conv.0.bias", "features.2.conv.7.bias", "features.3.conv.0.bias", "features.3.conv.7.bias", "features.4.conv.0.bias", "features.4.conv.7.bias", "features.5.conv.0.bias",...

生成的结果如何贴回原视频

1

训练完head和torso的模型之后，将结果贴回原视频中，发现有些帧肩膀和原视频间会出现位移错位的误差，这种应该怎么解决呢？