-
请问这个https://huggingface.co/ConvLLaVA/ConvLLaVA-ConvNeXt-1536链接里面的ConvNeXt模型权重是在文章中第二个stage训练得到的模型吗
-
Hi, thanks for open sourcing this brilliant work!
I read your paper in detail. You use ConvNeXt as the pretrained model of PointPillars. This is very pioneering.
I want to know:
Does the pretra…
-
**Short Description**
Just released - ConvNeXt with a new internal layer.
**Papers**
https://arxiv.org/abs/2301.00808
**Existing Implementations**
https://github.com/facebookresearch/ConvNeXt…
-
Hello and nice work! My question is how to finetune the model on KITTI?
I tried with the script ./finetune/train_ft_SQLdepth.py but cannot get good enough results. Only abs_rel 0.0494 and rmse 2.182.
-
thank you very much the implementation of your paper. I was wondering if there is going to be any implementation for connvnext or can I use timm models instead of your version of swin transformer?
-
### 🐛 Describe the bug
Model list:
- [ ] `convnext_base`
E0804 00:49:00.458000 519441 torch/_dynamo/utils.py:1558] RMSE (res-fp64): nan, (ref-fp64): 0.00512 and shape=torch.Size([128]). res.dtype…
-
I benchmarked my model with fp16 + int8 engine and fp16 engine and it seems fp16 is faster somehow even though its a timm convnext model with a lot of convolution layers.
Here is a quantized model :…
-
Can we convert ConvNeXt model to hef format?
-
首先感谢作者的工作,有个问题需要请教一下,在AsymFormer中,默认的是:model1 = convnext_tiny(pretrained=True, drop_path_rate=0.3),我想训练convnext_small模型,只把这里更换了后会报尺寸错误,请问一下还有哪里需要更改吗
-
It seems there is a error when I try to start the first docker build.
![image](https://github.com/user-attachments/assets/7f2566fa-c2c9-4442-8599-ca89521d09d0)