InternImage icon indicating copy to clipboard operation
InternImage copied to clipboard

[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions

Results 132 InternImage issues
Sort by recently updated
recently updated
newest added

Could you let me know why the pad_h, and pad_w here are not used in the following function? ``` def _get_reference_points(spatial_shapes, device, kernel_h, kernel_w, dilation_h, dilation_w, pad_h=0, pad_w=0, stride_h=1, stride_w=1):...

Hi, I am trying to reproduce the reported results on OpenLanev2. I didn't change anything. I downloaded the checkpoint and run the test script with this cmd: ./tools/test.sh plugin/mmdet3d/configs/internimage-s.py internimage-s-openlane.pth...

Hi, what is the “config-file ”in the detect task,?"sh dist_train.sh "? In what format should it be written and what should it say? Can you give me an example file...

Hello everyone, and thank you for your work. I have just cloned the complete repository and installed all the necessary dependencies. I have tested DCNV3 : ![image](https://github.com/OpenGVLab/InternImage/assets/43862103/dfbb2dd6-fbcf-4416-acbf-6ea8443e6602) and tried to...

I've installed the DCNv3 via the whl file, but I don't know how to use it , where can I see instructions for that? "from DCNv3 import DCNv3 DCNv3(*args)" is...

(internimage) xxh@hua-GPU-CloudKirin:/6_data/xxh/Project2023/InternImage/segmentation/ops_dcnv3$ sh ./make.sh True running build running build_py running build_ext /home/xxh/.virtualenvs/internimage/lib/python3.8/site-packages/torch/utils/cpp_extension.py:381: UserWarning: Attempted to use ninja as the BuildExtension backend but we could not find ninja.. Falling back to...

install DCNv3 with DCNv3-1.0+cu113torch1.12.1-cp38-cp38-linux_x86_64.whl my torch version: '1.12.1+cu113' import DCNv3 meets the following errors: ImportError: libc10.so: cannot open shared object file: No such file or directory ![image](https://github.com/OpenGVLab/InternImage/assets/16524582/0628f563-7a70-4e74-a64f-830479ac015e) Looking for help!...

Hello and thank you for sharing your work, i was wondering if you woul dprovide some information about training on custom dataset ? Thank you !

作者您好 首先感谢您的开源代码,我在训练目标检测模型的时候出现了问题,使用internimage_t_1k_224.pth作为预训练模型去训练coco数据集时报了如下错误: ![image](https://github.com/OpenGVLab/InternImage/assets/71921740/0988ed9c-c55c-4bbf-b5d5-263a544d92ed) 而后我将mask_rcnn_internimage_t_fpn_1x_coco.py的coco_instance.py替换为coco_detection.py,又替换了几个检测模型时如:mask_rcnn_r50_fpn.py,fast_rcnn_r50_fpn.py均会报以上错误。 期待您的解答,感谢!

Hi, congrats for the great work! Could you provide the code to train on iNaturalist 2018 dataset? Or describe how to train/fine-tune the model? Thanks