Skip to content

GitLab

"launch/dynamo-run/src/lib.rs" did not exist on "6e0cfbd967147e4d48ab0542127760939c0a2b68"
Commit 0f982e7a authored by Zhe Chen's avatar Zhe Chen Committed by zhe chen
Browse files

[log] Release logs of detection models (#30) 

* [feature] Add image_demo.py & get_flops.py (#22)

* [fix] PyTorch>=1.10.0 in README.md (#25)

* [log] Release logs of detection models (#29)
parent f05db000
Show whitespace changes
Inline Side-by-side
Showing with 32 additions and 21 deletions
README.md
View file @ 0f982e7a
......@@ -53,7 +53,7 @@ to reduces the strict inductive bias. Our model makes it possible to learn more
**ImageNet-1K and ImageNet-22K Pretrained InternImage Models**
| name | pretrain | resolution | acc@1 | #params | FLOPs | 22K model | 1K model |
| name | pretrain | resolution | acc@1 | #param | FLOPs | 22K model | 1K model |
| :------------: | :----------: | :--------: | :---: | :-----: | :---: | :-----------------: | :-----------------: |
| InternImage-T | ImageNet-1K | 224x224 | 83.5 | 30M | 5G | - | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/cls_model/internimage_t_1k_224.pth) \| [cfg](classification/configs/internimage_t_1k_224.yaml) |
| InternImage-S | ImageNet-1K | 224x224 | 84.2 | 50M | 8G | - | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/cls_model/internimage_s_1k_224.pth) \| [cfg](classification/configs/internimage_s_1k_224.yaml) |
......@@ -65,7 +65,7 @@ to reduces the strict inductive bias. Our model makes it possible to learn more
**COCO Object Detection**
| backbone | method | schd | box mAP | mask mAP | #params | FLOPs | Download |
| backbone | method | schd | box mAP | mask mAP | #param | FLOPs | Download |
| :------------: | :----------------: | :---------: | :-----: | :------: | :-----: | :---: | :---: |
| InternImage-T | Mask R-CNN | 1x | 47.2 | 42.5 | 49M | 270G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/det_model/mask_rcnn_internimage_t_fpn_1x_coco.pth) \| [cfg](detection/configs/mask_rcnn/mask_rcnn_internimage_t_fpn_1x_coco.py) |
| InternImage-T | Mask R-CNN | 3x | 49.1 | 43.7 | 49M | 270G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/det_model/mask_rcnn_internimage_t_fpn_3x_coco.pth) \| [cfg](detection/configs/mask_rcnn/mask_rcnn_internimage_t_fpn_3x_coco.py) |
......@@ -80,7 +80,7 @@ to reduces the strict inductive bias. Our model makes it possible to learn more
**ADE20K Semantic Segmentation**
| backbone | resolution | single scale | multi scale | #params | FLOPs | Download |
| backbone | resolution | single scale | multi scale | #param | FLOPs | Download |
| :------------: | :--------: | :----------: | :---------: | :-----: | :---: | :---: |
| InternImage-T | 512x512 | 47.9 | 48.1 | 59M | 944G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/seg_models/upernet_internimage_t_512_160k_ade20k.pth) \| [cfg](segmentation/configs/upernet/upernet_internimage_t_512_160k_ade20k.py) |
| InternImage-S | 512x512 | 50.1 | 50.9 | 80M | 1017G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/seg_models/upernet_internimage_s_512_160k_ade20k.pth) \| [cfg](segmentation/configs/upernet/upernet_internimage_s_512_160k_ade20k.py) |
......
detection/configs/cascade_mask_rcnn/README.md
View file @ 0f982e7a
......@@ -12,11 +12,16 @@ In object detection, the intersection over union (IoU) threshold is frequently u
<img src="https://user-images.githubusercontent.com/40661020/143872197-d99b90e4-4f05-4329-80a4-327ac862a051.png"/>
</div>
## Results and Models
| backbone | method | schd | box mAP | mask mAP | #params | FLOPs | Download |
| :------------: | :----------------: | :---------: | :-----: | :------: | :-----: | :---: | :---: |
| InternImage-L | Cascade | 1x | 54.9 | 47.7 | 277M | 1399G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/det_model/cascade_internimage_l_fpn_1x_coco.pth) \| [cfg](./cascade_internimage_l_fpn_1x_coco.py) |
| InternImage-L | Cascade | 3x | 56.1 | 48.5 | 277M | 1399G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/det_model/cascade_internimage_l_fpn_3x_coco.pth) \| [cfg](./cascade_internimage_l_fpn_3x_coco.py) |
| InternImage-XL | Cascade | 1x | 55.3 | 48.1 | 387M | 1782G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/det_model/cascade_internimage_xl_fpn_1x_coco.pth) \| [cfg](./cascade_internimage_xl_fpn_1x_coco.py) |
| InternImage-XL | Cascade | 3x | 56.2 | 48.8 | 387M | 1782G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/det_model/cascade_internimage_xl_fpn_1x_coco.pth) \| [cfg](./cascade_internimage_xl_fpn_3x_coco.py) |
## Model Zoo
| backbone | schd | box mAP | mask mAP | train speed | train time | #param | FLOPs | Config | Download |
| :------------: | :---------: | :-----: | :------: | :-----: | :---: | :-----: | :---: | :---: | :---: |
| InternImage-L | 1x | 54.9 | 47.7 | 0.73s / iter | 18h | 277M | 1399G | [config](./cascade_internimage_l_fpn_1x_coco.py) | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/det_model/cascade_internimage_l_fpn_1x_coco.pth) |
| InternImage-L | 3x | 56.1 | 48.5 | 0.79s / iter | 15h (n4) | 277M | 1399G | [config](./cascade_internimage_l_fpn_3x_coco.py) | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/det_model/cascade_internimage_l_fpn_3x_coco.pth) \| [log](https://github.com/OpenGVLab/InternImage/releases/download/det_model/cascade_internimage_l_fpn_3x_coco.log.json) |
| InternImage-XL | 1x | 55.3 | 48.1 | 0.82s / iter | 21h | 387M | 1782G | [config](./cascade_internimage_xl_fpn_1x_coco.py) | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/det_model/cascade_internimage_xl_fpn_1x_coco.pth) \| [log](https://github.com/OpenGVLab/InternImage/releases/download/det_model/cascade_internimage_xl_fpn_1x_coco.log.json) |
| InternImage-XL | 3x | 56.2 | 48.8 | 0.91s / iter | 17h (n4) | 387M | 1782G | [config](./cascade_internimage_xl_fpn_3x_coco.py) | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/det_model/cascade_internimage_xl_fpn_1x_coco.pth) \| [log](https://github.com/OpenGVLab/InternImage/releases/download/det_model/cascade_internimage_xl_fpn_3x_coco.log.json) |
- Training speed is measured with A100 GPUs using current code and may be faster than the speed in logs.
- Some logs are our recent newly trained ones. There might be slight differences between the results in logs and our paper.
- Please set `with_cp=True` to save memory if you meet `out-of-memory` issues.
detection/configs/mask_rcnn/README.md
View file @ 0f982e7a
......@@ -12,13 +12,19 @@ Mask R-CNN is a conceptually simple, flexible, and general framework for object
<img src="https://user-images.githubusercontent.com/40661020/143967081-c2552bed-9af2-46c4-ae44-5b3b74e5679f.png"/>
</div>
## Results and Models
| backbone | method | schd | box mAP | mask mAP | #params | FLOPs | Download |
| :------------: | :----------------: | :---------: | :-----: | :------: | :-----: | :---: | :---: |
| InternImage-T | Mask R-CNN | 1x | 47.2 | 42.5 | 49M | 270G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/det_model/mask_rcnn_internimage_t_fpn_1x_coco.pth) \| [cfg](./mask_rcnn_internimage_t_fpn_1x_coco.py) |
| InternImage-T | Mask R-CNN | 3x | 49.1 | 43.7 | 49M | 270G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/det_model/mask_rcnn_internimage_t_fpn_3x_coco.pth) \| [cfg](./mask_rcnn_internimage_t_fpn_3x_coco.py) |
| InternImage-S | Mask R-CNN | 1x | 47.8 | 43.3 | 69M | 340G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/det_model/mask_rcnn_internimage_s_fpn_1x_coco.pth) \| [cfg](./mask_rcnn_internimage_s_fpn_1x_coco.py) |
| InternImage-S | Mask R-CNN | 3x | 49.7 | 44.5 | 69M | 340G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/det_model/mask_rcnn_internimage_s_fpn_3x_coco.pth) \| [cfg](./mask_rcnn_internimage_s_fpn_3x_coco.py) |
| InternImage-B | Mask R-CNN | 1x | 48.8 | 44.0 | 115M | 501G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/det_model/mask_rcnn_internimage_b_fpn_1x_coco.pth) \| [cfg](./mask_rcnn_internimage_b_fpn_1x_coco.py) |
| InternImage-B | Mask R-CNN | 3x | 50.3 | 44.8 | 115M | 501G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/det_model/mask_rcnn_internimage_b_fpn_3x_coco.pth) \| [cfg](./mask_rcnn_internimage_b_fpn_3x_coco.py) |
## Model Zoo
| backbone | schd | box mAP | mask mAP | train speed | train time |#param | FLOPs | Config | Download |
| :------------: | :---------: | :-----: | :------: | :-----: |:------: | :-----: |:------: | :-----: | :---: |
| InternImage-T | 1x | 47.2 | 42.5 | 0.36s / iter | 9h | 49M | 270G | [config](./mask_rcnn_internimage_t_fpn_1x_coco.py) | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/det_model/mask_rcnn_internimage_t_fpn_1x_coco.pth) \| [log](https://github.com/OpenGVLab/InternImage/releases/download/det_model/mask_rcnn_internimage_t_fpn_1x_coco.log.json) |
| InternImage-T | 3x | 49.1 | 43.7 | 0.34s / iter | 26h | 49M | 270G | [config](./mask_rcnn_internimage_t_fpn_3x_coco.py) | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/det_model/mask_rcnn_internimage_t_fpn_3x_coco.pth) \| [log](https://github.com/OpenGVLab/InternImage/releases/download/det_model/mask_rcnn_internimage_t_fpn_3x_coco.log.json) |
| InternImage-S | 1x | 47.8 | 43.3 | 0.40s / iter | 10h | 69M | 340G | [config](./mask_rcnn_internimage_s_fpn_1x_coco.py) | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/det_model/mask_rcnn_internimage_s_fpn_1x_coco.pth) \| [log](https://github.com/OpenGVLab/InternImage/releases/download/det_model/mask_rcnn_internimage_s_fpn_1x_coco.log.json) |
| InternImage-S | 3x | 49.7 | 44.5 | 0.40s / iter | 30h | 69M | 340G | [config](./mask_rcnn_internimage_s_fpn_3x_coco.py) | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/det_model/mask_rcnn_internimage_s_fpn_3x_coco.pth) \| [log](https://github.com/OpenGVLab/InternImage/releases/download/det_model/mask_rcnn_internimage_s_fpn_3x_coco.log.json) |
| InternImage-B | 1x | 48.8 | 44.0 | 0.45s / iter | 11.5h | 115M | 501G | [config](./mask_rcnn_internimage_b_fpn_1x_coco.py) | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/det_model/mask_rcnn_internimage_b_fpn_1x_coco.pth) \| [log](https://github.com/OpenGVLab/InternImage/releases/download/det_model/mask_rcnn_internimage_b_fpn_1x_coco.log.json) |
| InternImage-B | 3x | 50.3 | 44.8 | 0.45s / iter | 34h | 115M | 501G | [config](./mask_rcnn_internimage_b_fpn_3x_coco.py)| [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/det_model/mask_rcnn_internimage_b_fpn_3x_coco.pth) \| [log](https://github.com/OpenGVLab/InternImage/releases/download/det_model/mask_rcnn_internimage_b_fpn_3x_coco.log.json) |
- Training speed is measured with A100 GPUs using current code and may be faster than the speed in logs.
- Some logs are our recent newly trained ones. There might be slight differences between the results in logs and our paper.
- Please set `with_cp=True` to save memory if you meet `out-of-memory` issues.
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment