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

I am trying to run the scripts you provide in "Huggingface Accelerate Integration of Deepspeed" `accelerate launch --config_file configs/accelerate/dist_8gpus_zero3_offload.yaml main_accelerate.py --cfg configs/internimage_t_1k_224.yaml --data-path /mnt/lustre/share/images --batch-size 128 --accumulation-steps 4 --output output_zero3_offload...

I am trying to incorporate DCNv3 into YOLOv8, but it shows ModuleNotFoundError: No module named 'DCNv3', seems like the code has not been compliled yet. I then tried to install...

Hi , I was trying to create a separate object of DCNv3 ``` dcn = DCNv3( channels=3, kernel_size=3, stride=1, pad=1, dilation=1, group=1,) x = torch.randn(2, 64, 64, 3) ``` but...

# Objective If there is non image file exists, it fails. So to debug where the process died, I sorted images, and at the same time, check the input file...

Hi! First of all thank you for your work. The following error occurs when I compile the CUDA operator: ![2274c78279d0a58778c20ea032f2112](https://user-images.githubusercontent.com/76090133/226549980-d732ccf3-c14a-4f7c-bee2-79b7d5bb9b1e.png) ![1679386680987](https://user-images.githubusercontent.com/76090133/226550534-7b555661-5b8c-47a2-b70e-9261511f37a6.png) Looking forward to your reply!Thanks!

when train with mask2former > File "/root/InternImage/segmentation/mmseg_custom/models/segmentors/encoder_decoder_mask2former.py", line 88, in _decode_head_forward_train gt_semantic_seg, **kwargs) TypeError: forward_train() missing 2 required positional arguments: 'gt_labels' and 'gt_masks'

Why am I getting these errors? I installed DCNv3 in Docker via whl file. I want to avoid that error python test.py err

Dear authors, Great work. I have followiing doubts, 1. I have a large segmentation data, I would like to pre-train the back bone. How do i do that? 2. I...

Traceback (most recent call last): File "train.py", line 616, in train(hyp, opt, device, tb_writer) File "train.py", line 95, in train model = Model(opt.cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create File "/media/kb541/ruanpuchao/yolov7_train/models/yolo.py",...