MIMDet
MIMDet copied to clipboard
hustvl
[ICCV 2023] You Only Look at One Partial Sequence
Is it possible to remove the Detectron2 dependency and use MIMDet more like YOLOS / DETR?
I want to use the video stream as input and get the visualization results, I don't know if this model can modify the input interface to achieve the effect like...
Hi, I'm trying to train a detection model with the plain ViT backbone on 8 GPUs (by scaling down batch size + lr 4x) using the 100 epoch config. Training...
Thanks for your excellent work! I want to use your MAE detector as an ROI feature extractor to extract object embedding for downstream tasks. Could you provide the corresponding code...
Hi, would you be interested in adding MIMDet to Hugging Face? The Hub offers free hosting, and it would make your work more accessible and visible to the rest of...
Hello, the visualizations in the paper are beautiful, can you share the code? Thanks a million!
Hello, did you solve this problem? @junchen14 ，I'm having the same problem． When my default configuration: "python lazyconfig_train_net.py --num-gpus 1 --config-file configs/mimdet/mimdet_vit_base_mask_rcnn_fpn_sr_0p5_800_ 1333_4xdec_coco_3x.py --num-machines 1". Training has diverged.", "FloatingPointError: Predicted...
Thanks for your great work. It seems that the shallow layers of the pre-trained backbone are more important because they can be frozen or given a smaller learning rate. I...
Thanks for your great work！ I have used the source code to reproduce the performance of mask_rcnn_vitbase，I used the original "mimdet_vit_base_mask_rcnn_fpn_sr_0p5_800_1333_4xdec_coco_3x.py" config with 64 4090D GPU, But I have just...
Hi, I'm following the official guide from the repository and using the recommended Conda environment on Windows 11. I've installed all dependencies correctly and am trying to run inference with...
