OpenGVLab / InternImage

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

https://arxiv.org/abs/2211.05778

OpenGVLab/InternImage Issues

How to install InternImage/detection with A100
Updated 7 days ago1
Typo in classification/meta_data/map22kto1k.txt?
Closed 3 months ago
使用DCNv3_pytorch 训练的分割模型，导出onnx后，还是存在不支持的onnx node
Updated 21 days ago2
InternImage is not in the models registry
Updated 21 days ago
conda env specs for CVPR23 Occupancy Prediction Challenge
Updated 24 days ago
Great work! Can you share the training details of RGB-D semantic segmentation on the nyu dataset?
Updated 25 days ago
ImportError: DLL load failed while importing DCNv3
Updated a month ago
The outdoor window is missing?
Updated a month ago
如何才能使分割建筑的结果区分外墙和窗户，或者有更多精细的标签体现出来呢？我想对一个建筑进行详细分割。How can the results of dividing buildings distinguish between exterior walls and windows, or have more detailed labels reflected? I want to perform a detailed segmentation of a building.
Updated a month ago1
ImportError: /root/miniconda3/lib/python3.8/site-packages/DCNv3.cpython-38-x86_64-linux-gnu.so: undefined symbol: _ZN3c1015SmallVectorBaseIjE8grow_podEPvmm
Updated a month ago2
DCNv3 编译问题
Updated 2 months ago
cmake error
Closed 2 months ago
About the stride in detection/ops_dcnv3
Closed 6 months ago1
[DCNv4 ERROR] cuda op error when use internimage-L and internimage-LX with DCNv4, however internimage-B works well with DCNv4
Updated 2 months ago2
Unsupported gpu architecture 'compute_86'
Updated 3 months ago
Cannot export classification model to ONNX
Updated 3 months ago3
Fine Tune only using detection grand truth
Closed 3 months ago1
detection 我是用自己数据训练就是那个官方balloon数据，典型小样本，效果太差
Updated 4 months ago2
[DCNv4 error] RuntimeError: falseINTERNAL ASSERT FAILED at src/cuda/dcnv4_col2im_cuda.cuh:470
Updated 4 months ago1
Tensorrt engine inference of C++ API
Updated 4 months ago
build torchscript extension
Closed 4 months ago
Weights for CrowdHuman dataset
Updated 4 months ago
RuntimeError: Not implemented on the CPU
Updated 5 months ago2
Unable to train the algorithms with 2 GPU instances (multi-node), each with 4 A100s
Updated 5 months ago
预训练模型无法下载
Updated 5 months ago
Is there a way to extract the heatmap based on the feature map from image_demo.py?
Updated 5 months ago
python-pytorch版本DCNv3
Updated 6 months ago
What are the differences between DCNv3 and DCNv3 pytorch?
Updated 6 months ago
sampling_locations = (ref + grid * offset_scale).repeat(N_, 1, 1, 1, 1).flatten(3, 4) + \ RuntimeError: The size of tensor a (16) must match the size of tensor b (32) at non-singleton dimension 2
Updated 6 months ago3
a bug when converting the dino detector to tensorrt
Updated 6 months ago1
DCNv3_pytorch代码中可变形卷积的卷积过程
Updated 6 months ago
Release date for InternImage-H pretrained weights
Updated 6 months ago
Inference GPU memory is more than training
Updated 6 months ago
Latency too high with DCNv3_pytorch op on cpu
Updated 6 months ago
GPU memory requirements increases when using DCNv3_pytorch rather than DCNv3
Updated 6 months ago
Why whl_files can not download?
Updated 6 months ago
error in dcnv3_im2col_cuda: no kernel image is available for execution on the device
Closed 6 months ago2
ONNXRuntimeError: Failed to Load Model due to Unregistered Function/Op
Updated 6 months ago
请问你们打榜的模型是backbone一起做fine-tune的吗？
Updated 7 months ago
error in detection for image_demo.py
Updated 7 months ago
Cityscapes extra data
Updated 7 months ago
Binary Mask Semantic Segmentation Issue
Updated 7 months ago
could you please provide me with your trained model
Updated 7 months ago
RuntimeError: expected scalar type Half but found Float: issues when I tried to run DCN on pytorch without C++
Updated 7 months ago2
InternImage not loading custom classes
Updated 7 months ago
ModuleNotFoundError: No module named 'DCNv3' in YOLOv8
Updated 7 months ago2
AttributeError: type object 'DCNv3' has no attribute 'dcnv3_forward'
Updated 7 months ago1
Are you planning to release the models with AP higher than 65.0?
Updated 8 months ago
TypeError: forward_train() missing 2 required positional arguments: 'gt_labels' and 'gt_masks'
Updated 8 months ago
Pre-train and fine tuning with lot of instances
Updated 8 months ago