InternImage
InternImage copied to clipboard
OpenGVLab
[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
Will you guys release the Objects365 pretraining models for InternImage-XL/H DINO in the Table 4?
When are you guys planning to release Internimage-G or H version. Atleast for Object detection? SOTA model is yet to be released and on hiatus from long time. @ottolu @shepnerd...
I have my own way to call the dataloader and sampler, loss, etc. is there a way to extract the segmentation model only, so that I could plug it into...
In segmentation/configs/_base_/models/mask2former_beit.py ```python decode_head=dict( type='Mask2FormerHead', in_channels=[256, 512, 1024, 2048], # pass to pixel_decoder inside # strides=[4, 8, 16, 32], feat_channels=256, out_channels=256, in_index=[0, 1, 2, 3], num_things_classes=num_things_classes, num_stuff_classes=num_stuff_classes, num_queries=100, num_transformer_feat_level=3, ```...
Finished processing dependencies for DCNv3==1.0 (yolo8_cyy) nd@aiso-PR4904P:~/yt_data/cyy/yolov8/yolov8/ultralytics/nn/modules/ops_dcnv3$ python test.py /home/nd/anaconda3/envs/yolo8_cyy/lib/python3.8/site-packages/torch/functional.py:478: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2894.) return...
When will the large model be released? For example, InternImage-G of DINO for detection，or InternImage-H of Mask2Former for segmentation.
The links on the official website are deprecated. I want them to evaluate the models for research only. Could you please send a copy of the dataset? Many thanks.
The forward/backward error comparison between the master branch and this PR branch: 
