Prepare COCO according to the guidelines in [MMDetection v2.28.1](https://github.com/open-mmlab/mmdetection/blob/master/docs/en/1_exist_data_model.md).
### Evaluation
To evaluate our `InternImage` on COCO val, run:
...
...
@@ -107,6 +108,7 @@ GPUS=32 sh slurm_train.sh <partition> <job-name> configs/coco/cascade_internimag
### Export
To export a detection model from PyTorch to TensorRT, run:
```shell
MODEL="model_name"
CKPT_PATH="/path/to/model/ckpt.pth"
...
...
@@ -122,6 +124,7 @@ python deploy.py \
```
For example, to export `mask_rcnn_internimage_t_fpn_1x_coco` from PyTorch to TensorRT, run:
Introduced by Lin et al. in [Microsoft COCO: Common Objects in Context](https://arxiv.org/pdf/1405.0312v3.pdf)
...
...
@@ -11,19 +10,18 @@ Splits: The first version of MS COCO dataset was released in 2014. It contains 1
Based on community feedback, in 2017 the training/validation split was changed from 83K/41K to 118K/5K. The new split uses the same images and annotations. The 2017 test set is a subset of 41K images of the 2015 test set. Additionally, the 2017 release contains a new unannotated dataset of 123K images.
Introduced by Shao et al. in [CrowdHuman: A Benchmark for Detecting Human in a Crowd](https://arxiv.org/pdf/1805.00123.pdf)
...
...
@@ -8,6 +7,7 @@ Introduced by Shao et al. in [CrowdHuman: A Benchmark for Detecting Human in a C
CrowdHuman is a benchmark dataset to better evaluate detectors in crowd scenarios. The CrowdHuman dataset is large, rich-annotated and contains high diversity. CrowdHuman contains 15000, 4370 and 5000 images for training, validation, and testing, respectively. There are a total of 470K human instances from train and validation subsets and 23 persons per image, with various kinds of occlusions in the dataset. Each human instance is annotated with a head bounding-box, human visible-region bounding-box and human full-body bounding-box. We hope our dataset will serve as a solid baseline and help promote future research in human detection tasks.
## Prepare the data
Download the original dataset from [CrowdHuman](https://www.crowdhuman.org/download.html). Then convert annotations by detection/tools/create_crowd_anno.py
- Data Tree of CrowdHuman should look like:
...
...
@@ -25,16 +25,15 @@ Download the original dataset from [CrowdHuman](https://www.crowdhuman.org/downl
