Hugging Face's logo

mit-han-lab
/
efficientvit-sam

Mask Generation
ONNX
Model card Files Community
6
zhuoyang20 commited on
Commit
a4a9bc0
•
1 Parent(s): 219cd34

Fix the download links in the table.

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -15,11 +15,11 @@ Latency/Throughput is measured on NVIDIA Jetson AGX Orin, and NVIDIA A100 GPU wi
15
 
16
  | Model | Resolution | COCO mAP | LVIS mAP | Params | MACs | Jetson Orin Latency (bs1) | A100 Throughput (bs16) | Checkpoint |
17
  |----------------------|:----------:|:----------:|:---------:|:------------:|:---------:|:---------:|:------------:|:------------:|
18
- | EfficientViT-SAM-L0 | 512x512 | 45.7 | 41.8 | 34.8M | 35G | 8.2ms | 762 images/s | [link](https://huggingface.co/han-cai/efficientvit-sam/resolve/main/l0.pt) |
19
- | EfficientViT-SAM-L1 | 512x512 | 46.2 | 42.1 | 47.7M | 49G | 10.2ms | 638 images/s | [link](https://huggingface.co/han-cai/efficientvit-sam/resolve/main/l1.pt) |
20
- | EfficientViT-SAM-L2 | 512x512 | 46.6 | 42.7 | 61.3M | 69G | 12.9ms | 538 images/s | [link](https://huggingface.co/han-cai/efficientvit-sam/resolve/main/l2.pt) |
21
- | EfficientViT-SAM-XL0 | 1024x1024 | 47.5 | 43.9 | 117.0M | 185G | 22.5ms | 278 images/s | [link](https://huggingface.co/han-cai/efficientvit-sam/resolve/main/xl0.pt) |
22
- | EfficientViT-SAM-XL1 | 1024x1024 | 47.8 | 44.4 | 203.3M | 322G | 37.2ms | 182 images/s | [link](https://huggingface.co/han-cai/efficientvit-sam/resolve/main/xl1.pt) |
23
  <p align="center">
24
  <b> Table1: Summary of All EfficientViT-SAM Variants.</b> COCO mAP and LVIS mAP are measured using ViTDet's predicted bounding boxes as the prompt. End-to-end Jetson Orin latency and A100 throughput are measured with TensorRT and fp16.
25
  </p>
 
15
 
16
  | Model | Resolution | COCO mAP | LVIS mAP | Params | MACs | Jetson Orin Latency (bs1) | A100 Throughput (bs16) | Checkpoint |
17
  |----------------------|:----------:|:----------:|:---------:|:------------:|:---------:|:---------:|:------------:|:------------:|
18
+ | EfficientViT-SAM-L0 | 512x512 | 45.7 | 41.8 | 34.8M | 35G | 8.2ms | 762 images/s | [link](https://huggingface.co/mit-han-lab/efficientvit-sam/resolve/main/efficientvit_sam_l0.pt?download=true) |
19
+ | EfficientViT-SAM-L1 | 512x512 | 46.2 | 42.1 | 47.7M | 49G | 10.2ms | 638 images/s | [link](https://huggingface.co/mit-han-lab/efficientvit-sam/resolve/main/efficientvit_sam_l1.pt?download=true) |
20
+ | EfficientViT-SAM-L2 | 512x512 | 46.6 | 42.7 | 61.3M | 69G | 12.9ms | 538 images/s | [link](https://huggingface.co/mit-han-lab/efficientvit-sam/resolve/main/efficientvit_sam_l2.pt?download=true) |
21
+ | EfficientViT-SAM-XL0 | 1024x1024 | 47.5 | 43.9 | 117.0M | 185G | 22.5ms | 278 images/s | [link](https://huggingface.co/mit-han-lab/efficientvit-sam/resolve/main/efficientvit_sam_xl0.pt?download=true) |
22
+ | EfficientViT-SAM-XL1 | 1024x1024 | 47.8 | 44.4 | 203.3M | 322G | 37.2ms | 182 images/s | [link](https://huggingface.co/mit-han-lab/efficientvit-sam/resolve/main/efficientvit_sam_xl1.pt?download=true) |
23
  <p align="center">
24
  <b> Table1: Summary of All EfficientViT-SAM Variants.</b> COCO mAP and LVIS mAP are measured using ViTDet's predicted bounding boxes as the prompt. End-to-end Jetson Orin latency and A100 throughput are measured with TensorRT and fp16.
25
  </p>