-
:
```
th slow_neural_style.lua -gpu 0…
-
I keep getting errors when trying to merge either two LORAs or a checkpoint with at least one LORA.
Here's an example of the log I get from one of my attempts :
```
07:26:36-762384 INFO Mer…
-
As #197 and #206 have pointed out, there are some inconsistencies with the implementation of Inception-ResNet-v2 and [the paper](https://arxiv.org/pdf/1602.07261). @agsourav highlights that the stem s…
-
Hi,
I am using your pytorch implementation to train a Rational [ResNet 164](https://github.com/bearpaw/pytorch-classification) on CIFAR 10 and while I can get the model to behave well for a ResNet wi…
-
Changing either or both of the parameters: nconcepts, concept_dim leads to a dimensionality error. I have tried a bunch of different values for these parameters, and all of them fail to run the code. …
-
### 描述该功能
1.希望可以整理如何对这些模型进行微调的文档
### 是否希望自己实现该功能？
- [ ] 我希望自己来实现这一功能，并向 MMPreTrain 贡献代码！
-
hi @hunto
I have been following your work for a long time and I am very excited that the code has been made public in the target classification task.
but I found a problem: when I use resnet-34(tea…
-
### Describe the feature
This is the configuration I modified, mainly to change it to 640. Is this modification correct?
train_pipeline = [
dict(type='LoadImageFromFile'),
# dict(type=…
-
I trained a model of ResNet on ImageNet and get a model file. I use the model file to finetune ResNet for Oxford102, but the network doesn't converge. The loss is between [4.63,4.65]. Here is my code:…