dinov2

dinov2 copied to clipboard

Hello, It has come to my attention that in the train.py file, the function "dinov2 > data > collate > collate_data_and_cast" is passed to the dataloader to collate the samples...

jeromel05

New paper model release

2

Hi! I wonder if you have plan to share model weight of your new paper at huggingface?

rese1f

Poor Object Detection Performance with DINOv2 Backbone and Faster R-CNN Head on Cityscapes Dataset

10

I am working on an object detection task using the DINOv2 backbone with a Faster R-CNN head. While I have successfully implemented semantic segmentation with a linear head on the...

busenuraktilav

Convert model to TensorRT fails

1

I am trying to convert the model to a torch TensorRT pre-compiled model for inference on an embedded device. I am using this script: ``` import torch_tensorrt import torch model...

janblumenkamp

problem with installing mmcv

7

` conda env create -f conda-extras.yaml` fails with error message ``` Solving environment: done ==> WARNING: A newer version of conda exists. [16 lines of output] /tmp/pip-install-pa3tzeja/mmcv-full_26c44a3cfd544d1f80c1a675007fd507/setup.py:6: DeprecationWarning: pkg_resources is...

nagitam

mmcv installation issue

9

--------------------------------------------------------------------------- ModuleNotFoundError Traceback (most recent call last) Cell In[2], line 7 5 import torch 6 import torch.nn.functional as F ----> 7 from mmseg.apis import init_segmentor, inference_segmentor 9 import dinov2.eval.segmentation.models 12...

shravankumar-concat

Confused on how to use pretrained backbone where you need full details of the image

1

Hi, Thank you for the great work. I am conceptually confused on how to use this backbone. I read through your code on the depth estimation head but it is...

smandava98

Training pipeline of linear probing for semantic segmentation and depth estimation

1

Dear DINOv2 team, thank you for this amazing work! If I am correct, I only found the whole pipeline of linear probing for classification on ImageNet in [https://github.com/facebookresearch/dinov2/blob/main/dinov2/eval/linear.py](https://github.com/facebookresearch/dinov2/blob/main/dinov2/eval/linear.py). Is it...

ywyue

Sinkhorn Knopp NaN

1

I was running a debug job on 2 processes. I noticed that Sinkhorn Knopp produces NaN valeus for teacher randomly(the previous loss & data in current batch all look normal)....

JunzheJosephZhu

Is this the right way to fine-tune DINOv2?

16

I am trying to finetune dinov2 for image classification on a custom dataset (medical image dataset) with the objective of increasing accuracy. The problem is that when I use linear...

namrahrehman