fast-reid/MODEL_ZOO.md

# FastReID Model Zoo and Baselines

## Introduction

This file documents collection of baselines trained with fastreid. All numbers were obtained with 1 NVIDIA P40 GPU.
The software in use were PyTorch 1.4, CUDA 10.1.

In addition to these official baseline models, you can find more models in [projects/](https://github.com/JDAI-CV/fast-reid/tree/master/projects).

### How to Read the Tables

- The "Name" column contains a link to the config file.
Running `tools/train_net.py` with this config file and 1 GPU will reproduce the model.
- The *model id* column is provided for ease of reference. To check downloaded file integrity, any model on this page contains tis md5 prefix in its file name.
- Training curves and other statistics can be found in `metrics` for each model.

### Common Settings for all Person reid models

**BoT**:

[Bag of Tricks and A Strong Baseline for Deep Person Re-identification](http://openaccess.thecvf.com/content_CVPRW_2019/papers/TRMTMCT/Luo_Bag_of_Tricks_and_a_Strong_Baseline_for_Deep_Person_CVPRW_2019_paper.pdf). CVPRW2019, Oral.

**AGW**:

[ReID-Survey with a Powerful AGW Baseline](https://github.com/mangye16/ReID-Survey).

**MGN**:

[Learning Discriminative Features with Multiple Granularities for Person Re-Identification](https://arxiv.org/abs/1804.01438v1)

**SBS**:

stronger baseline on top of BoT:

Bag of Freebies(BoF):

1. Circle loss
2. Freeze backbone training
3. Cutout data augmentation & Auto Augmentation
4. Cosine annealing learning rate decay
5. Soft margin triplet loss

Bag of Specials(BoS):

1. Non-local block
2. GeM pooling

### Market1501 Baselines

**BoT**:

| Method | Pretrained | Rank@1 | mAP | mINP | download |
| :---: | :---: | :---: |:---: | :---: | :---: |
| [BoT(R50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/bagtricks_R50.yml) | ImageNet | 94.4% | 86.1% | 59.4% | - |
| [BoT(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/bagtricks_R50-ibn.yml) | ImageNet | 94.9% | 87.6% | 64.1% | - |
| [BoT(S50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/bagtricks_S50.yml) | ImageNet | 95.1% | 88.5% | 66.0% | - |
| [BoT(R101-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/bagtricks_R101-ibn.yml) | ImageNet| 95.4% | 88.9% | 67.4% | - |

**AGW**:

| Method | Pretrained | Rank@1 | mAP | mINP | download |
| :---: | :---: | :---: |:---: | :---: |:---: |
| [AGW(R50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/AGW_R50.yml) | ImageNet | 95.3% | 88.2% | 66.3% | - |
| [AGW(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/AGW_R50-ibn.yml) | ImageNet | 95.1% | 88.7% | 67.1% | -|
| [AGW(S50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/AGW_S50.yml) | ImageNet | 94.7% | 87.1% | 62.2% | -|
| [AGW(R101-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/AGW_R101-ibn.yml) | ImageNet | 95.5% | 89.5% | 69.5% | - |

**SBS**:

| Method | Pretrained | Rank@1 | mAP | mINP | download |
| :---: | :---: | :---: |:---: | :---: |:---:|
| [SBS(R50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/sbs_R50.yml) | ImageNet | 95.4% | 88.2% | 64.8% | - |
| [SBS(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/sbs_R50-ibn.yml) | ImageNet | 95.7% | 89.3% | 67.5% | -|
| [SBS(S50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/sbs_S50.yml) | ImageNet | 95.0% | 87.0% | 60.6% | -|
| [SBS(R101-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/sbs_R101-ibn.yml) | ImageNet | 96.3% | 90.3% | 70.0% | -|

**MGN**:

| Method | Pretrained | Rank@1 | mAP | mINP | download |
| :---: | :---: | :---: |:---: | :---: | :---:|
| [SBS(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/mgn_R50-ibn.yml) | ImageNet | 95.8% | 89.7% | 67.0% | -|

### DukeMTMC Baseline

**BoT**:

| Method | Pretrained | Rank@1 | mAP | mINP | download |
| :---: | :---: | :---: |:---: | :---: | :---: |
| [BoT(R50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/bagtricks_R50.yml) | ImageNet | 87.1% | 76.9% | 41.6% | - |
| [BoT(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/bagtricks_R50-ibn.yml) | ImageNet | 89.6% | 79.1% | 44.4% | - |
| [BoT(S50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/bagtricks_S50.yml) | ImageNet | 87.8% | 77.7% | 39.6% | - |
| [BoT(R101-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/bagtricks_R101-ibn.yml) | ImageNet| 91.1% | 81.3% | 47.7% | -|

**AGW**:

| Method | Pretrained | Rank@1 | mAP | mINP | download |
| :---: | :---: | :---: |:---: | :---: | :---:|
| [AGW(R50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/AGW_R50.yml) | ImageNet | 89.0% | 79.9% | 46.3% | - |
| [AGW(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/AGW_R50-ibn.yml) | ImageNet | 89.8% | 80.7% | 47.7% | - |
| [AGW(S50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/AGW_S50.yml) | ImageNet | 89.9% | 79.7% | 44.2% | -| 
| [AGW(R101-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/AGW_R101-ibn.yml) | ImageNet | 91.4% | 82.1% | 50.2% | -|

**SBS**:

| Method | Pretrained | Rank@1 | mAP | mINP | download |
| :---: | :---: | :---: |:---: | :---: | :---:|
| [SBS(R50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/sbs_R50.yml) | ImageNet | 89.6% | 79.8% | 44.6% | -|
| [SBS(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/sbs_R50-ibn.yml) | ImageNet | 91.3% | 81.6% | 47.6% | -|
| [SBS(S50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/sbs_S50.yml) | ImageNet | 90.5% | 79.1% | 42.7% | -|
| [SBS(R101-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/sbs_R101-ibn.yml) | ImageNet | 92.4% | 83.2% | 49.7% | -|

**MGN**:

| Method | Pretrained | Rank@1 | mAP | mINP | download |
| :---: | :---: | :---: |:---: | :---: | :---:|
| [SBS(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/mgn_R50-ibn.yml) | ImageNet | 91.6% | 82.1% | 46.7% | - |

### MSMT17 Baseline

**BoT**:

| Method | Pretrained | Rank@1 | mAP | mINP | download |
| :---: | :---: | :---: |:---: | :---: | :---:|
| [BoT(R50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/bagtricks_R50.yml) | ImageNet | 72.3%  | 48.3% | 9.7% | -|
| [BoT(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/bagtricks_R50-ibn.yml) | ImageNet | 77.0% | 54.4% | 12.5% | -|
| [BoT(S50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/bagtricks_S50.yml) | ImageNet | 80.4% | 59.2% | 15.9% | -|
| [BoT(R101-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/bagtricks_R101-ibn.yml) | ImageNet| 79.0% | 57.5% | 14.6% | -|

**AGW**:

| Method | Pretrained | Rank@1 | mAP | mINP | download |
| :---: | :---: | :---: |:---: | :---: | :---:|
| [AGW(R50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/AGW_R50.yml) | ImageNet | 76.7% | 53.6% | 12.2% | -|
| [AGW(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/AGW_R50-ibn.yml) | ImageNet | 79.3% | 57.5% | 14.3% | -|
| [AGW(S50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/AGW_S50.yml) | ImageNet | 77.3% | 54.7% | 12.6% | -|
| [AGW(R101-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/AGW_R101-ibn.yml) | ImageNet | 80.8% | 60.2% | 16.5% | -|

**SBS**:

| Method | Pretrained | Rank@1 | mAP | mINP | download |
| :---: | :---: | :---: |:---: | :---: | :---:|
| [SBS(R50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/sbs_R50.yml) | ImageNet | 83.3% | 59.9% | 14.6% | -|
| [SBS(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/sbs_R50-ibn.yml) | ImageNet | 84.0% | 61.2% | 15.5% | -|
| [SBS(S50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/sbs_S50.yml) | ImageNet | 82.6% | 58.2% | 13.2% | -|
| [SBS(R101-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/sbs_R101-ibn.yml) | ImageNet | 85.1% | 63.3% | 16.6% | -|

**MGN**:

| Method | Pretrained | Rank@1 | mAP | mINP | download |
| :---: | :---: | :---: |:---: | :---: | :---:|
| [SBS(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/mgn_R50-ibn.yml) | ImageNet | 85.1% | 65.4% | 18.4% | -|

### VeRi Baseline

**SBS**:

| Method | Pretrained | Rank@1 | mAP | mINP | download |
| :---: | :---: | :---: |:---: | :---: | :---:| 
| BoT(R50-ibn) | ImageNet | 97.0%  | 81.9% | 46.3% | -|

### VehicleID Baseline

**BoT**:
Method: BoT(R50-ibn+gem pooling+weighted triplet+soft margin)  
Test protocol: 10-fold cross-validation

| Testset size | Pretrained | Rank@1 | Rank@5 | download |
| :---: | :---: | :---: |:---: | :---:|
| Small(800) | ImageNet | 86.6%  | 97.9% | -|
| Medium(1600) | ImageNet | 82.9%  | 96.0% | -|
| Large(2400) | ImageNet | 80.6%  | 93.9% | -|

### VERI-Wild Baseline

**BoT**:  
Method: BoT(R50-ibn+gem pooling+weighted triplet+soft margin)

| Testset size | Pretrained | Rank@1 | mAP | mINP | download |
| :---: | :---: | :---: |:---: | :---: | :---:|
| Small(3000) | ImageNet | 96.4%  | 87.7% | 69.2% | -|
| Medium(5000) | ImageNet | 95.1%  | 83.5% | 61.2% | -|
| Large(10000) | ImageNet | 92.5%  | 77.3% | 49.8% | -|
style(configs): put all config files together put all config files into one place for easily control, and add tools for put train_net.py which almost the same in different projects 2020-04-29 16:18:54 +08:00			`# FastReID Model Zoo and Baselines`

			`## Introduction`

update model config url 2020-05-29 10:10:43 +08:00			`This file documents collection of baselines trained with fastreid. All numbers were obtained with 1 NVIDIA P40 GPU.`
			`The software in use were PyTorch 1.4, CUDA 10.1.`

			`In addition to these official baseline models, you can find more models in [projects/](https://github.com/JDAI-CV/fast-reid/tree/master/projects).`

			`### How to Read the Tables`

			`- The "Name" column contains a link to the config file.`
			Running `tools/train_net.py` with this config file and 1 GPU will reproduce the model.
			`- The model id column is provided for ease of reference. To check downloaded file integrity, any model on this page contains tis md5 prefix in its file name.`
			- Training curves and other statistics can be found in `metrics` for each model.

			`### Common Settings for all Person reid models`

style(model_zoo): add bot, agw, sbs as built-in model 2020-05-01 09:56:33 +08:00			`BoT:`

update model config url 2020-05-29 10:10:43 +08:00			`[Bag of Tricks and A Strong Baseline for Deep Person Re-identification](http://openaccess.thecvf.com/content_CVPRW_2019/papers/TRMTMCT/Luo_Bag_of_Tricks_and_a_Strong_Baseline_for_Deep_Person_CVPRW_2019_paper.pdf). CVPRW2019, Oral.`
style(model_zoo): add bot, agw, sbs as built-in model 2020-05-01 09:56:33 +08:00
			`AGW:`

update model config url 2020-05-29 10:10:43 +08:00			`[ReID-Survey with a Powerful AGW Baseline](https://github.com/mangye16/ReID-Survey).`
style(model_zoo): add bot, agw, sbs as built-in model 2020-05-01 09:56:33 +08:00
chore(model_zoo): update mgn metrics 2020-05-23 10:42:24 +08:00			`MGN:`

update model config url 2020-05-29 10:10:43 +08:00			`[Learning Discriminative Features with Multiple Granularities for Person Re-Identification](https://arxiv.org/abs/1804.01438v1)`

style(model_zoo): add bot, agw, sbs as built-in model 2020-05-01 09:56:33 +08:00			`SBS:`

chore(model_zoo): update mgn metrics 2020-05-23 10:42:24 +08:00			`stronger baseline on top of BoT:`

			`Bag of Freebies(BoF):`

			`1. Circle loss`
			`2. Freeze backbone training`
			`3. Cutout data augmentation & Auto Augmentation`
			`4. Cosine annealing learning rate decay`
			`5. Soft margin triplet loss`

			`Bag of Specials(BoS):`
update model zoo results 2020-05-06 09:58:49 +08:00
style(model_zoo): add bot, agw, sbs as built-in model 2020-05-01 09:56:33 +08:00			`1. Non-local block`
			`2. GeM pooling`

chore(model_zoo): fix typo 2020-04-29 16:22:02 +08:00			`### Market1501 Baselines`
style(configs): put all config files together put all config files into one place for easily control, and add tools for put train_net.py which almost the same in different projects 2020-04-29 16:18:54 +08:00
chore: update model zoo 2020-04-29 18:15:27 +08:00			`BoT:`

update model config url 2020-05-29 10:10:43 +08:00			`\| Method \| Pretrained \| Rank@1 \| mAP \| mINP \| download \|`
			`\| :---: \| :---: \| :---: \|:---: \| :---: \| :---: \|`
			`\| [BoT(R50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/bagtricks_R50.yml) \| ImageNet \| 94.4% \| 86.1% \| 59.4% \| - \|`
			`\| [BoT(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/bagtricks_R50-ibn.yml) \| ImageNet \| 94.9% \| 87.6% \| 64.1% \| - \|`
			`\| [BoT(S50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/bagtricks_S50.yml) \| ImageNet \| 95.1% \| 88.5% \| 66.0% \| - \|`
			`\| [BoT(R101-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/bagtricks_R101-ibn.yml) \| ImageNet\| 95.4% \| 88.9% \| 67.4% \| - \|`
chore: update model zoo 2020-04-29 18:15:27 +08:00
			`AGW:`

update model config url 2020-05-29 10:10:43 +08:00			`\| Method \| Pretrained \| Rank@1 \| mAP \| mINP \| download \|`
			`\| :---: \| :---: \| :---: \|:---: \| :---: \|:---: \|`
			`\| [AGW(R50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/AGW_R50.yml) \| ImageNet \| 95.3% \| 88.2% \| 66.3% \| - \|`
			`\| [AGW(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/AGW_R50-ibn.yml) \| ImageNet \| 95.1% \| 88.7% \| 67.1% \| -\|`
			`\| [AGW(S50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/AGW_S50.yml) \| ImageNet \| 94.7% \| 87.1% \| 62.2% \| -\|`
			`\| [AGW(R101-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/AGW_R101-ibn.yml) \| ImageNet \| 95.5% \| 89.5% \| 69.5% \| - \|`
chore: update model zoo 2020-04-29 18:15:27 +08:00
			`SBS:`

update model config url 2020-05-29 10:10:43 +08:00			`\| Method \| Pretrained \| Rank@1 \| mAP \| mINP \| download \|`
			`\| :---: \| :---: \| :---: \|:---: \| :---: \|:---:\|`
			`\| [SBS(R50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/sbs_R50.yml) \| ImageNet \| 95.4% \| 88.2% \| 64.8% \| - \|`
			`\| [SBS(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/sbs_R50-ibn.yml) \| ImageNet \| 95.7% \| 89.3% \| 67.5% \| -\|`
			`\| [SBS(S50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/sbs_S50.yml) \| ImageNet \| 95.0% \| 87.0% \| 60.6% \| -\|`
			`\| [SBS(R101-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/sbs_R101-ibn.yml) \| ImageNet \| 96.3% \| 90.3% \| 70.0% \| -\|`
style(configs): put all config files together put all config files into one place for easily control, and add tools for put train_net.py which almost the same in different projects 2020-04-29 16:18:54 +08:00
chore(model_zoo): update mgn metrics 2020-05-23 10:42:24 +08:00			`MGN:`

update model config url 2020-05-29 10:10:43 +08:00			`\| Method \| Pretrained \| Rank@1 \| mAP \| mINP \| download \|`
			`\| :---: \| :---: \| :---: \|:---: \| :---: \| :---:\|`
			`\| [SBS(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/Market1501/mgn_R50-ibn.yml) \| ImageNet \| 95.8% \| 89.7% \| 67.0% \| -\|`
chore(model_zoo): update mgn metrics 2020-05-23 10:42:24 +08:00
chore(model_zoo): fix typo 2020-04-29 16:22:02 +08:00			`### DukeMTMC Baseline`
style(configs): put all config files together put all config files into one place for easily control, and add tools for put train_net.py which almost the same in different projects 2020-04-29 16:18:54 +08:00
chore: update model zoo 2020-04-29 18:15:27 +08:00			`BoT:`

update model config url 2020-05-29 10:10:43 +08:00			`\| Method \| Pretrained \| Rank@1 \| mAP \| mINP \| download \|`
			`\| :---: \| :---: \| :---: \|:---: \| :---: \| :---: \|`
			`\| [BoT(R50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/bagtricks_R50.yml) \| ImageNet \| 87.1% \| 76.9% \| 41.6% \| - \|`
			`\| [BoT(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/bagtricks_R50-ibn.yml) \| ImageNet \| 89.6% \| 79.1% \| 44.4% \| - \|`
			`\| [BoT(S50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/bagtricks_S50.yml) \| ImageNet \| 87.8% \| 77.7% \| 39.6% \| - \|`
			`\| [BoT(R101-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/bagtricks_R101-ibn.yml) \| ImageNet\| 91.1% \| 81.3% \| 47.7% \| -\|`
chore: update model zoo 2020-04-29 18:15:27 +08:00
			`AGW:`

update model config url 2020-05-29 10:10:43 +08:00			`\| Method \| Pretrained \| Rank@1 \| mAP \| mINP \| download \|`
			`\| :---: \| :---: \| :---: \|:---: \| :---: \| :---:\|`
			`\| [AGW(R50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/AGW_R50.yml) \| ImageNet \| 89.0% \| 79.9% \| 46.3% \| - \|`
			`\| [AGW(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/AGW_R50-ibn.yml) \| ImageNet \| 89.8% \| 80.7% \| 47.7% \| - \|`
			`\| [AGW(S50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/AGW_S50.yml) \| ImageNet \| 89.9% \| 79.7% \| 44.2% \| -\|`
			`\| [AGW(R101-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/AGW_R101-ibn.yml) \| ImageNet \| 91.4% \| 82.1% \| 50.2% \| -\|`
chore: update model zoo 2020-04-29 18:15:27 +08:00
			`SBS:`

update model config url 2020-05-29 10:10:43 +08:00			`\| Method \| Pretrained \| Rank@1 \| mAP \| mINP \| download \|`
			`\| :---: \| :---: \| :---: \|:---: \| :---: \| :---:\|`
			`\| [SBS(R50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/sbs_R50.yml) \| ImageNet \| 89.6% \| 79.8% \| 44.6% \| -\|`
			`\| [SBS(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/sbs_R50-ibn.yml) \| ImageNet \| 91.3% \| 81.6% \| 47.6% \| -\|`
			`\| [SBS(S50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/sbs_S50.yml) \| ImageNet \| 90.5% \| 79.1% \| 42.7% \| -\|`
			`\| [SBS(R101-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/sbs_R101-ibn.yml) \| ImageNet \| 92.4% \| 83.2% \| 49.7% \| -\|`
style(configs): put all config files together put all config files into one place for easily control, and add tools for put train_net.py which almost the same in different projects 2020-04-29 16:18:54 +08:00
chore(model_zoo): update mgn metrics 2020-05-23 10:42:24 +08:00			`MGN:`

update model config url 2020-05-29 10:10:43 +08:00			`\| Method \| Pretrained \| Rank@1 \| mAP \| mINP \| download \|`
			`\| :---: \| :---: \| :---: \|:---: \| :---: \| :---:\|`
			`\| [SBS(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/DukeMTMC/mgn_R50-ibn.yml) \| ImageNet \| 91.6% \| 82.1% \| 46.7% \| - \|`
chore(model_zoo): update mgn metrics 2020-05-23 10:42:24 +08:00
style(configs): put all config files together put all config files into one place for easily control, and add tools for put train_net.py which almost the same in different projects 2020-04-29 16:18:54 +08:00			`### MSMT17 Baseline`

chore: update model zoo 2020-04-29 18:15:27 +08:00			`BoT:`

update model config url 2020-05-29 10:10:43 +08:00			`\| Method \| Pretrained \| Rank@1 \| mAP \| mINP \| download \|`
			`\| :---: \| :---: \| :---: \|:---: \| :---: \| :---:\|`
			`\| [BoT(R50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/bagtricks_R50.yml) \| ImageNet \| 72.3% \| 48.3% \| 9.7% \| -\|`
			`\| [BoT(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/bagtricks_R50-ibn.yml) \| ImageNet \| 77.0% \| 54.4% \| 12.5% \| -\|`
			`\| [BoT(S50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/bagtricks_S50.yml) \| ImageNet \| 80.4% \| 59.2% \| 15.9% \| -\|`
			`\| [BoT(R101-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/bagtricks_R101-ibn.yml) \| ImageNet\| 79.0% \| 57.5% \| 14.6% \| -\|`
chore: update model zoo 2020-04-29 18:15:27 +08:00
			`AGW:`

update model config url 2020-05-29 10:10:43 +08:00			`\| Method \| Pretrained \| Rank@1 \| mAP \| mINP \| download \|`
			`\| :---: \| :---: \| :---: \|:---: \| :---: \| :---:\|`
			`\| [AGW(R50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/AGW_R50.yml) \| ImageNet \| 76.7% \| 53.6% \| 12.2% \| -\|`
			`\| [AGW(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/AGW_R50-ibn.yml) \| ImageNet \| 79.3% \| 57.5% \| 14.3% \| -\|`
			`\| [AGW(S50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/AGW_S50.yml) \| ImageNet \| 77.3% \| 54.7% \| 12.6% \| -\|`
			`\| [AGW(R101-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/AGW_R101-ibn.yml) \| ImageNet \| 80.8% \| 60.2% \| 16.5% \| -\|`
chore: update model zoo 2020-04-29 18:15:27 +08:00
			`SBS:`

update model config url 2020-05-29 10:10:43 +08:00			`\| Method \| Pretrained \| Rank@1 \| mAP \| mINP \| download \|`
			`\| :---: \| :---: \| :---: \|:---: \| :---: \| :---:\|`
			`\| [SBS(R50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/sbs_R50.yml) \| ImageNet \| 83.3% \| 59.9% \| 14.6% \| -\|`
			`\| [SBS(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/sbs_R50-ibn.yml) \| ImageNet \| 84.0% \| 61.2% \| 15.5% \| -\|`
			`\| [SBS(S50)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/sbs_S50.yml) \| ImageNet \| 82.6% \| 58.2% \| 13.2% \| -\|`
			`\| [SBS(R101-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/sbs_R101-ibn.yml) \| ImageNet \| 85.1% \| 63.3% \| 16.6% \| -\|`
Update MODEL_ZOO.md 2020-04-29 18:33:11 +08:00
chore(model_zoo): update mgn metrics 2020-05-23 10:42:24 +08:00			`MGN:`

update model config url 2020-05-29 10:10:43 +08:00			`\| Method \| Pretrained \| Rank@1 \| mAP \| mINP \| download \|`
			`\| :---: \| :---: \| :---: \|:---: \| :---: \| :---:\|`
			`\| [SBS(R50-ibn)](https://github.com/JDAI-CV/fast-reid/blob/master/configs/MSMT17/mgn_R50-ibn.yml) \| ImageNet \| 85.1% \| 65.4% \| 18.4% \| -\|`
chore(model_zoo): update mgn metrics 2020-05-23 10:42:24 +08:00
Update MODEL_ZOO.md 2020-04-29 18:33:11 +08:00			`### VeRi Baseline`

Fix VehicleID's results and update VeRi's results Fix VehicleID's results and update VeRi's results 2020-05-22 13:43:34 +08:00			`SBS:`
Update MODEL_ZOO.md 2020-04-29 18:33:11 +08:00
update model config url 2020-05-29 10:10:43 +08:00			`\| Method \| Pretrained \| Rank@1 \| mAP \| mINP \| download \|`
			`\| :---: \| :---: \| :---: \|:---: \| :---: \| :---:\|`
			`\| BoT(R50-ibn) \| ImageNet \| 97.0% \| 81.9% \| 46.3% \| -\|`
Update MODEL_ZOO.md 2020-04-29 18:33:11 +08:00
			`### VehicleID Baseline`

update model config url 2020-05-29 10:10:43 +08:00			`BoT:`
Update VeRi's results Update VeRi's results 2020-05-27 13:05:15 +08:00			`Method: BoT(R50-ibn+gem pooling+weighted triplet+soft margin)`
Change VehilcleID results Replace VehicleID results with those under 10-fold cross-validation. 2020-05-25 16:36:08 +08:00			`Test protocol: 10-fold cross-validation`
Update MODEL_ZOO.md 2020-04-29 18:33:11 +08:00
update model config url 2020-05-29 10:10:43 +08:00			`\| Testset size \| Pretrained \| Rank@1 \| Rank@5 \| download \|`
			`\| :---: \| :---: \| :---: \|:---: \| :---:\|`
			`\| Small(800) \| ImageNet \| 86.6% \| 97.9% \| -\|`
			`\| Medium(1600) \| ImageNet \| 82.9% \| 96.0% \| -\|`
			`\| Large(2400) \| ImageNet \| 80.6% \| 93.9% \| -\|`
Update MODEL_ZOO.md 2020-04-29 18:33:11 +08:00
			`### VERI-Wild Baseline`

Update VeRi's results Update VeRi's results 2020-05-27 13:05:15 +08:00			`BoT:`
Fix VehicleID's results and update VeRi's results Fix VehicleID's results and update VeRi's results 2020-05-22 13:43:34 +08:00			`Method: BoT(R50-ibn+gem pooling+weighted triplet+soft margin)`
Update MODEL_ZOO.md 2020-04-29 18:33:11 +08:00
update model config url 2020-05-29 10:10:43 +08:00			`\| Testset size \| Pretrained \| Rank@1 \| mAP \| mINP \| download \|`
			`\| :---: \| :---: \| :---: \|:---: \| :---: \| :---:\|`
			`\| Small(3000) \| ImageNet \| 96.4% \| 87.7% \| 69.2% \| -\|`
			`\| Medium(5000) \| ImageNet \| 95.1% \| 83.5% \| 61.2% \| -\|`
			`\| Large(10000) \| ImageNet \| 92.5% \| 77.3% \| 49.8% \| -\|`