Update README.md
Browse files
README.md
CHANGED
|
@@ -4,10 +4,10 @@ license: mit
|
|
| 4 |
|
| 5 |
# InternImage Model Card
|
| 6 |
|
| 7 |
-
## Introduction
|
| 8 |
-
|
| 9 |
This repository provides PyTorch-format pretrained weights for different variants of the InternImage model. The weights are intended for use in downstream tasks and fine-tuning on specific datasets.
|
| 10 |
|
|
|
|
|
|
|
| 11 |
InternImage is an advanced vision foundation model developed by researchers from Shanghai AI Laboratory, Tsinghua University, and other institutions. Unlike models based on Transformers, InternImage employs DCNv3 as its core operator. This approach equips the model with dynamic and effective receptive fields required for downstream tasks like object detection and segmentation, while enabling adaptive spatial aggregation.
|
| 12 |
|
| 13 |
<div style="text-align: center;"> <img src="https://github.com/OpenGVLab/InternImage/raw/master/docs/figs/arch.png" style="width:60%;" /> </div>
|
|
|
|
| 4 |
|
| 5 |
# InternImage Model Card
|
| 6 |
|
|
|
|
|
|
|
| 7 |
This repository provides PyTorch-format pretrained weights for different variants of the InternImage model. The weights are intended for use in downstream tasks and fine-tuning on specific datasets.
|
| 8 |
|
| 9 |
+
## Introduction
|
| 10 |
+
|
| 11 |
InternImage is an advanced vision foundation model developed by researchers from Shanghai AI Laboratory, Tsinghua University, and other institutions. Unlike models based on Transformers, InternImage employs DCNv3 as its core operator. This approach equips the model with dynamic and effective receptive fields required for downstream tasks like object detection and segmentation, while enabling adaptive spatial aggregation.
|
| 12 |
|
| 13 |
<div style="text-align: center;"> <img src="https://github.com/OpenGVLab/InternImage/raw/master/docs/figs/arch.png" style="width:60%;" /> </div>
|