Closed xiaoxia0722 closed 7 months ago
A1: You can generate dinov2_converted.pth
by running the command: python tools/convert_models/convert_dinov2_large_512x512.py checkpoints/dinov2_vitl14_pretrain.pth
.
A2: This does not work.
A3: You can obtain the checkpoint for DINOv2-large from https://dl.fbaipublicfiles.com/dinov2/dinov2_vitl14/dinov2_vitl14_pretrain.pth. More backbones can be found according to the model from https://github.com/facebookresearch/dinov2/tree/main.
A4: Yes, we use the segmentation data from the 10K part of BDD100K. The official website of BDD100K seems to be down. You might be able to obtain these data from https://opendatalab.com/OpenDataLab/BDD100K, but I'm not certain.
Do other backbone networks also use command python tools/convert_models/convert_dinov2_large_512x512.py checkpoint/backbone
for conversion? I get error RuntimeError: shape '[1, 37, 37, 1024]' is invalid for input of size 525696
when I run the dinov2_vits14_pretrain.pth
model transformation using command python tools/convert_models/convert_dinov2_large_512x512.py checkpoint/dinov2_vits14_pretrain.pth
. And the same problem is encountered when transforming other pretain models. The download address is https://dl.fbaipublicfiles.com/dinov2/dinov2_vits14/dinov2_vits14_pretrain.pth
When I used config file GTAV+ConvNeXt-L
, GTAV+ResNet101
and GTAV+ResNet50
from tags, running it showed that model ReinsConvNeXt
and ReinsResNetV1c
didn't exist, and I couldn't find them in the code.
Do other backbone networks also use command
python tools/convert_models/convert_dinov2_large_512x512.py checkpoint/backbone
for conversion? I get errorRuntimeError: shape '[1, 37, 37, 1024]' is invalid for input of size 525696
when I run thedinov2_vits14_pretrain.pth
model transformation using commandpython tools/convert_models/convert_dinov2_large_512x512.py checkpoint/dinov2_vits14_pretrain.pth
. And the same problem is encountered when transforming other pretain models. The download address is https://dl.fbaipublicfiles.com/dinov2/dinov2_vits14/dinov2_vits14_pretrain.pth
As the name suggests, convert_dinov2_large_512x512.py
is developed for dinov2_large. You can easily adapt it for different backbones by copying and making simple edits, mainly by changing the number of channels from 1024 to the corresponding number of channels in lines 15 to 29.
When I used config file
GTAV+ConvNeXt-L
,GTAV+ResNet101
andGTAV+ResNet50
from tags, running it showed that modelReinsConvNeXt
andReinsResNetV1c
didn't exist, and I couldn't find them in the code.
It has been updated! Thank you for point out!
Thank you for your answer. The code has run successfully
good lock to you
Hello, I'm having some problems running Rein's code. Because this is my first time coming into contact with this direction, there may be errors in my operation. Please try to solve the following problems:
readme.md
, the error shows thatcheckpoints/dinov2_converted.pth
does not exist after running the training commandpython tools/train.py configs/dinov2/rein_dinov2_mask2former_512x512_bs1x4.py
. There are onlydinov2_rein_and_head.pth
anddinov2_vitl14_pretrain.pth
in the checkpoint file. How to downloaddinov2_converted.pth
?dinov2_rein_and_head.pth
todinov2_converted.pth
worked, but the results were not ideal.bdd100k_seg.zip
? The download from the official website is not available. If not, can you provide a download link to the dataset?