Skip to content

Commit

Permalink
first inference version
Browse files Browse the repository at this point in the history
  • Loading branch information
@LPXTT
LPXTT committed Jul 16, 2022
1 parent 1b77922 commit a238932
Show file tree
Hide file tree
Showing 385 changed files with 100,775 additions and 0 deletions.
123 changes: 123 additions & 0 deletions MODEL_ZOO.md
View file
@@ -0,0 +1,123 @@
# STARK Model Zoo

Here we provide the performance of the STARK trackers on multiple tracking benchmarks and the corresponding raw results.
The model weights and the corresponding training logs are also given by the links.

## Tracking
### Models & Logs

<table>
<tr>
<th>Model</th>
<th>LaSOT<br>AUC (%)</th>
<th>GOT-10k<br>AO (%)</th>
<th>TrackingNet<br>AUC (%)</th>
<th>VOT2020<br>EAO</th>
<th>VOT2020-LT<br>F-score (%)</th>
<th>Models</th>
<th>Logs</th>
<th>Logs(GOT10K)</th>
</tr>
<tr>
<td>STARK-S50</td>
<td>65.8</td>
<td>67.2</td>
<td>80.3</td>
<td>0.462</td>
<td>-</td>
<td><a href="https://drive.google.com/drive/folders/1144cEuF_yn9UwTfrSVl5wmaMK3F92q42?usp=sharing">model</a></td>
<td><a href="https://drive.google.com/file/d/1_YI0CX52vg8zN6hWsYK22_78FXPiukdv/view?usp=sharing">log</a></td>
<td><a href="https://drive.google.com/file/d/1xLUeV9I9tejT4eYd1mYpeB_AsndiaJNI/view?usp=sharing">log</a></td>
</tr>
<tr>
<td>STARK-ST50</td>
<td>66.4</td>
<td>68.0</td>
<td>81.3</td>
<td>0.505</td>
<td>70.2</td>
<td><a href="https://drive.google.com/drive/folders/1fSgll53ZnVKeUn22W37Nijk-b9LGhMdN?usp=sharing">model</a></td>
<td><a href="https://drive.google.com/drive/folders/1RcPoBxI1_E6U9s5Y6BEhQH_ov-sT7SJM?usp=sharing">log</a></td>
<td><a href="https://drive.google.com/drive/folders/13guPF1MUOaRa09_4y_K9do9yhQsC_y_y?usp=sharing">log</a></td>
</tr>
<tr>
<td>STARK-ST101</td>
<td>67.1</td>
<td>68.8</td>
<td>82.0</td>
<td>0.497</td>
<td>70.1</td>
<td><a href="https://drive.google.com/drive/folders/1fSgll53ZnVKeUn22W37Nijk-b9LGhMdN?usp=sharing">model</a></td>
<td><a href="https://drive.google.com/drive/folders/1nTDRfG0K0w2XiP5RDrYJXhotUYQJBNoY?usp=sharing">log</a></td>
<td><a href="https://drive.google.com/drive/folders/1PR6PRdARHFKBDSjoqeO7qxx9y87AZWSD?usp=sharing">log</a></td>
</tr>


</table>

The downloaded checkpoints should be organized in the following structure
```
${STARK_ROOT}
-- checkpoints
-- train
-- stark_s
-- baseline
STARKS_ep0500.pth.tar
-- baseline_got10k_only
STARKS_ep0500.pth.tar
-- stark_st2
-- baseline
STARKST_ep0050.pth.tar
-- baseline_got10k_only
STARKST_ep0050.pth.tar
-- baseline_R101
STARKST_ep0050.pth.tar
-- baseline_R101_got10k_only
STARKST_ep0050.pth.tar
```
### Raw Results
The [raw results](https://drive.google.com/drive/folders/16rWehrDmJVmvMsadffOPaCczz7pst4PH?usp=sharing) are in the format [top_left_x, top_left_y, width, height]. Raw results of GOT-10K and TrackingNet can be
directly submitted to the corresponding evaluation servers. The folder ```test/tracking_results/``` contains raw results
for the LaSOT dataset and results should be organized in the following structure
```
${STARK_ROOT}
-- test
-- tracking_results
-- stark_s
-- baseline
airplane-1.txt
airplane-13.txt
...
-- stark_st2
-- baseline
airplane-1.txt
airplane-13.txt
...
-- baseline_R101
airplane-1.txt
airplane-13.txt
...
```
The raw results of VOT2020 and VOT2020-LT should be organized in the following structure
```
${STARK_ROOT}
-- external
-- vot20
-- stark_s50
-- results
-- stark_s50_ar
-- results
-- stark_st50
-- results
-- stark_st50_ar
-- results
-- stark_st101
-- results
-- stark_st101_ar
-- results
-- vot20_lt
-- stark_st50
-- results
-- stark_st101
-- results
```
78 changes: 78 additions & 0 deletions experiments/simtrack/baseline.yaml
View file
@@ -0,0 +1,78 @@
DATA:
MAX_SAMPLE_INTERVAL: 200
MEAN:
- 0.485
- 0.456
- 0.406
SEARCH:
CENTER_JITTER: 3.5
FACTOR: 4.0
SCALE_JITTER: 0.5
SIZE: 224
STD:
- 0.229
- 0.224
- 0.225
TEMPLATE:
CENTER_JITTER: 0
FACTOR: 2.0
SCALE_JITTER: 0
SIZE: 112
TRAIN:
DATASETS_NAME:
- LASOT
- GOT10K_vottrain
- COCO17
- TRACKINGNET
DATASETS_RATIO:
- 1
- 1
- 1
- 1
SAMPLE_PER_EPOCH: 60000
VAL:
DATASETS_NAME:
- GOT10K_votval
DATASETS_RATIO:
- 1
SAMPLE_PER_EPOCH: 10000
MODEL:
BACKBONE:
NUM_FEA: 768
TEMPLATE_SZ: 112
SEARCH_SZ: 224
WINDOW_SZ: 16
FOVEAL_SZ: 64
TYPE: 'ViT-B/16'
HEAD_TYPE: CORNER
HIDDEN_DIM: 256


TRAIN:
BACKBONE_MULTIPLIER: 0.1
BATCH_SIZE: 64
DEEP_SUPERVISION: false
EPOCH: 50
FREEZE_BACKBONE_BN: false
# FREEZE_LAYERS:
# - conv1
# - layer1
GIOU_WEIGHT: 2.0
GRAD_CLIP_NORM: 0.1
L1_WEIGHT: 5.0
LR: 0.0001
LR_DROP_EPOCH: 40
NUM_WORKER: 8
OPTIMIZER: ADAMW
PRINT_INTERVAL: 40
SCHEDULER:
TYPE: step
DECAY_RATE: 0.1
VAL_EPOCH_INTERVAL: 20
WEIGHT_DECAY: 0.0001
TEST:
EPOCH: 50
SEARCH_FACTOR: 4.0
SEARCH_SIZE: 224
TEMPLATE_FACTOR: 2.0
TEMPLATE_SIZE: 112
72 changes: 72 additions & 0 deletions experiments/simtrack/baseline_got10k_only.yaml
View file
@@ -0,0 +1,72 @@
DATA:
MAX_SAMPLE_INTERVAL: 200
MEAN:
- 0.485
- 0.456
- 0.406
SEARCH:
CENTER_JITTER: 3.5
FACTOR: 4.0
SCALE_JITTER: 0.5
SIZE: 224
STD:
- 0.229
- 0.224
- 0.225
TEMPLATE:
CENTER_JITTER: 0
FACTOR: 2.0
SCALE_JITTER: 0
SIZE: 112
TRAIN:
DATASETS_NAME:
- GOT10K_train_full
DATASETS_RATIO:
- 1
SAMPLE_PER_EPOCH: 60000
VAL:
DATASETS_NAME:
- GOT10K_votval
DATASETS_RATIO:
- 1
SAMPLE_PER_EPOCH: 10000
MODEL:
BACKBONE:
NUM_FEA: 768
TEMPLATE_SZ: 112
SEARCH_SZ: 224
WINDOW_SZ: 16
FOVEAL_SZ: 64
TYPE: 'ViT-B/16'
HEAD_TYPE: CORNER
HIDDEN_DIM: 256


TRAIN:
BACKBONE_MULTIPLIER: 0.1
BATCH_SIZE: 64
DEEP_SUPERVISION: false
EPOCH: 50
FREEZE_BACKBONE_BN: false
# FREEZE_LAYERS:
# - conv1
# - layer1
GIOU_WEIGHT: 2.0
GRAD_CLIP_NORM: 0.1
L1_WEIGHT: 5.0
LR: 0.0001
LR_DROP_EPOCH: 40
NUM_WORKER: 8
OPTIMIZER: ADAMW
PRINT_INTERVAL: 40
SCHEDULER:
TYPE: step
DECAY_RATE: 0.1
VAL_EPOCH_INTERVAL: 20
WEIGHT_DECAY: 0.0001
TEST:
EPOCH: 50
SEARCH_FACTOR: 4.0
SEARCH_SIZE: 224
TEMPLATE_FACTOR: 2.0
TEMPLATE_SIZE: 112
84 changes: 84 additions & 0 deletions experiments/stark_lightning_X_trt/baseline_rephead_4_lite_search5.yaml
View file
@@ -0,0 +1,84 @@
DATA:
MAX_SAMPLE_INTERVAL: 200
MEAN:
- 0.485
- 0.456
- 0.406
SEARCH:
CENTER_JITTER: 4.5 # ori 4.5
FACTOR: 5.0 # ori 5.0
SCALE_JITTER: 0.5 # ori 0.5
SIZE: 320 # ori 320
FEAT_SIZE: 20
STD:
- 0.229
- 0.224
- 0.225
TEMPLATE:
CENTER_JITTER: 0
FACTOR: 2.0
SCALE_JITTER: 0
SIZE: 128
FEAT_SIZE: 8
TRAIN:
DATASETS_NAME:
- LASOT
- GOT10K_vottrain
- COCO17
- TRACKINGNET
DATASETS_RATIO:
- 1
- 1
- 1
- 1
SAMPLE_PER_EPOCH: 60000
VAL:
DATASETS_NAME:
- GOT10K_votval
DATASETS_RATIO:
- 1
SAMPLE_PER_EPOCH: 10000
MODEL:
BACKBONE:
LAST_STAGE_BLOCK: 4
DILATION: false
OUTPUT_LAYERS:
- stage3 # ori layer3
TYPE: RepVGG-A0 # ori resnet50
HEAD_TYPE: CORNER_LITE_REP_v2 # ori CORNER
HIDDEN_DIM: 128
HEAD_DIM: 128 # ori 256
TRANSFORMER:
DIM_FEEDFORWARD: 1024
DROPOUT: 0.1
NHEADS: 8
TRAIN:
AMP: False
BACKBONE_MULTIPLIER: 0.1
BATCH_SIZE: 16
DEEP_SUPERVISION: false
EPOCH: 500
FREEZE_BACKBONE_BN: true
BACKBONE_TRAINED_LAYERS:
- stage1
- stage2
- stage3
GIOU_WEIGHT: 2.0
GRAD_CLIP_NORM: 0.1
L1_WEIGHT: 5.0
LR: 0.0001
LR_DROP_EPOCH: 400
NUM_WORKER: 8
OPTIMIZER: ADAMW
PRINT_INTERVAL: 50
SCHEDULER:
TYPE: step
DECAY_RATE: 0.1
VAL_EPOCH_INTERVAL: 20
WEIGHT_DECAY: 0.0001
TEST:
EPOCH: 500
SEARCH_FACTOR: 5.0 # ori 5.0
SEARCH_SIZE: 320 # ori 320
TEMPLATE_FACTOR: 2.0
TEMPLATE_SIZE: 128

0 comments on commit a238932

Please sign in to comment.