Standardize model folders and checkpoint filenames
Browse files- README.md +8 -8
- {mask2former-cityscapes-olac β mask2former_cityscapes_olac}/LICENSE +0 -0
- {mask2former-cityscapes-olac β mask2former_cityscapes_olac}/README.md +5 -5
- {mask2former-cityscapes-olac β mask2former_cityscapes_olac}/config.yaml +1 -1
- mask2former-cityscapes-olac/model_final.pth β mask2former_cityscapes_olac/mask2former_cityscapes_olac.pth +0 -0
- {mask2former-coco-olac β mask2former_coco_olac}/LICENSE +0 -0
- {mask2former-coco-olac β mask2former_coco_olac}/README.md +5 -5
- {mask2former-coco-olac β mask2former_coco_olac}/config.yaml +1 -1
- mask2former-coco-olac/model_final.pth β mask2former_coco_olac/mask2former_coco_olac.pth +0 -0
- {pemola-cityscapes-olac β mask2former_pemola_cityscapes_olac}/LICENSE +0 -0
- {pemola-cityscapes-olac β mask2former_pemola_cityscapes_olac}/README.md +5 -5
- {pemola-cityscapes-olac β mask2former_pemola_cityscapes_olac}/config.yaml +1 -1
- pemola-cityscapes-olac/model_final.pth β mask2former_pemola_cityscapes_olac/mask2former_pemola_cityscapes_olac.pth +0 -0
- {pemola-cityscapes-olac β mask2former_pemola_cityscapes_olac}/run_metrics.json +0 -0
- {pemola-coco-olac β mask2former_pemola_coco_olac}/LICENSE +0 -0
- {pemola-coco-olac β mask2former_pemola_coco_olac}/README.md +5 -5
- {pemola-coco-olac β mask2former_pemola_coco_olac}/config.yaml +1 -1
- pemola-coco-olac/model_final.pth β mask2former_pemola_coco_olac/mask2former_pemola_coco_olac.pth +0 -0
- {pemola-coco-olac β mask2former_pemola_coco_olac}/run_metrics.json +0 -0
- {maskdino-coco-olac β maskdino_coco_olac}/LICENSE +0 -0
- {maskdino-coco-olac β maskdino_coco_olac}/README.md +4 -4
- {maskdino-coco-olac β maskdino_coco_olac}/config.yaml +1 -1
- maskdino-coco-olac/model_final.pth β maskdino_coco_olac/maskdino_coco_olac.pth +0 -0
- {pemola-maskdino-coco-olac β maskdino_pemola_coco_olac}/LICENSE +0 -0
- {pemola-maskdino-coco-olac β maskdino_pemola_coco_olac}/README.md +4 -4
- {pemola-maskdino-coco-olac β maskdino_pemola_coco_olac}/config.yaml +1 -1
- pemola-maskdino-coco-olac/model_final.pth β maskdino_pemola_coco_olac/maskdino_pemola_coco_olac.pth +0 -0
- {pemola-occlusion-swin-l β swin_l_384_occlusion_coco_olac}/LICENSE +0 -0
- {pemola-occlusion-swin-l β swin_l_384_occlusion_coco_olac}/README.md +6 -6
- {pemola-occlusion-swin-l β swin_l_384_occlusion_coco_olac}/config.yaml +0 -0
- pemola-occlusion-swin-l/ep29.pth β swin_l_384_occlusion_coco_olac/swin_l_384_occlusion_coco_olac.pth +0 -0
README.md
CHANGED
|
@@ -12,13 +12,13 @@ All seven model checkpoints, matching configurations, usage notes, and licenses
|
|
| 12 |
|
| 13 |
| Model | Dataset | Result | Config / Weights |
|
| 14 |
| :--- | :--- | :---: | :---: |
|
| 15 |
-
| [Mask2Former R50](https://huggingface.co/weiwb/PEMOLA/blob/main/
|
| 16 |
-
| [PEMOLA + Mask2Former R50](https://huggingface.co/weiwb/PEMOLA/blob/main/
|
| 17 |
-
| [Mask2Former R50](https://huggingface.co/weiwb/PEMOLA/blob/main/
|
| 18 |
-
| [PEMOLA + Mask2Former R50](https://huggingface.co/weiwb/PEMOLA/blob/main/
|
| 19 |
-
| [Mask DINO R50](https://huggingface.co/weiwb/PEMOLA/blob/main/
|
| 20 |
-
| [PEMOLA + Mask DINO R50](https://huggingface.co/weiwb/PEMOLA/blob/main/
|
| 21 |
-
| [Occlusion classifier: Swin-L 384](https://huggingface.co/weiwb/PEMOLA/blob/main/
|
| 22 |
|
| 23 |
## Download
|
| 24 |
|
|
@@ -32,7 +32,7 @@ hf download weiwb/PEMOLA --local-dir checkpoints
|
|
| 32 |
To download one model, select its folder:
|
| 33 |
|
| 34 |
```bash
|
| 35 |
-
hf download weiwb/PEMOLA --include "
|
| 36 |
```
|
| 37 |
|
| 38 |
For source code, [installation](https://github.com/wenbo-wei/PEMOLA#installation), and [inference](https://github.com/wenbo-wei/PEMOLA#inference--visualization), see the [PEMOLA GitHub repository](https://github.com/wenbo-wei/PEMOLA). Mask DINO models use the dedicated [Mask DINO implementation](https://github.com/wenbo-wei/MaskDINO).
|
|
|
|
| 12 |
|
| 13 |
| Model | Dataset | Result | Config / Weights |
|
| 14 |
| :--- | :--- | :---: | :---: |
|
| 15 |
+
| [Mask2Former R50](https://huggingface.co/weiwb/PEMOLA/blob/main/mask2former_coco_olac/README.md) | COCO-OLAC | PQ 40.7 | [config](https://huggingface.co/weiwb/PEMOLA/resolve/main/mask2former_coco_olac/config.yaml) / [weights](https://huggingface.co/weiwb/PEMOLA/resolve/main/mask2former_coco_olac/mask2former_coco_olac.pth) |
|
| 16 |
+
| [PEMOLA + Mask2Former R50](https://huggingface.co/weiwb/PEMOLA/blob/main/mask2former_pemola_coco_olac/README.md) | COCO-OLAC | PQ 41.5 | [config](https://huggingface.co/weiwb/PEMOLA/resolve/main/mask2former_pemola_coco_olac/config.yaml) / [weights](https://huggingface.co/weiwb/PEMOLA/resolve/main/mask2former_pemola_coco_olac/mask2former_pemola_coco_olac.pth) |
|
| 17 |
+
| [Mask2Former R50](https://huggingface.co/weiwb/PEMOLA/blob/main/mask2former_cityscapes_olac/README.md) | Cityscapes-OLAC | PQ 61.5 | [config](https://huggingface.co/weiwb/PEMOLA/resolve/main/mask2former_cityscapes_olac/config.yaml) / [weights](https://huggingface.co/weiwb/PEMOLA/resolve/main/mask2former_cityscapes_olac/mask2former_cityscapes_olac.pth) |
|
| 18 |
+
| [PEMOLA + Mask2Former R50](https://huggingface.co/weiwb/PEMOLA/blob/main/mask2former_pemola_cityscapes_olac/README.md) | Cityscapes-OLAC | PQ 62.3 | [config](https://huggingface.co/weiwb/PEMOLA/resolve/main/mask2former_pemola_cityscapes_olac/config.yaml) / [weights](https://huggingface.co/weiwb/PEMOLA/resolve/main/mask2former_pemola_cityscapes_olac/mask2former_pemola_cityscapes_olac.pth) |
|
| 19 |
+
| [Mask DINO R50](https://huggingface.co/weiwb/PEMOLA/blob/main/maskdino_coco_olac/README.md) | COCO-OLAC | PQ 44.0 | [config](https://huggingface.co/weiwb/PEMOLA/resolve/main/maskdino_coco_olac/config.yaml) / [weights](https://huggingface.co/weiwb/PEMOLA/resolve/main/maskdino_coco_olac/maskdino_coco_olac.pth) |
|
| 20 |
+
| [PEMOLA + Mask DINO R50](https://huggingface.co/weiwb/PEMOLA/blob/main/maskdino_pemola_coco_olac/README.md) | COCO-OLAC | PQ 44.8 | [config](https://huggingface.co/weiwb/PEMOLA/resolve/main/maskdino_pemola_coco_olac/config.yaml) / [weights](https://huggingface.co/weiwb/PEMOLA/resolve/main/maskdino_pemola_coco_olac/maskdino_pemola_coco_olac.pth) |
|
| 21 |
+
| [Occlusion classifier: Swin-L 384](https://huggingface.co/weiwb/PEMOLA/blob/main/swin_l_384_occlusion_coco_olac/README.md) | COCO-OLAC test, black background | Top-1 75.3% | [config](https://huggingface.co/weiwb/PEMOLA/resolve/main/swin_l_384_occlusion_coco_olac/config.yaml) / [weights](https://huggingface.co/weiwb/PEMOLA/resolve/main/swin_l_384_occlusion_coco_olac/swin_l_384_occlusion_coco_olac.pth) |
|
| 22 |
|
| 23 |
## Download
|
| 24 |
|
|
|
|
| 32 |
To download one model, select its folder:
|
| 33 |
|
| 34 |
```bash
|
| 35 |
+
hf download weiwb/PEMOLA --include "mask2former_pemola_coco_olac/*" --local-dir checkpoints
|
| 36 |
```
|
| 37 |
|
| 38 |
For source code, [installation](https://github.com/wenbo-wei/PEMOLA#installation), and [inference](https://github.com/wenbo-wei/PEMOLA#inference--visualization), see the [PEMOLA GitHub repository](https://github.com/wenbo-wei/PEMOLA). Mask DINO models use the dedicated [Mask DINO implementation](https://github.com/wenbo-wei/MaskDINO).
|
{mask2former-cityscapes-olac β mask2former_cityscapes_olac}/LICENSE
RENAMED
|
File without changes
|
{mask2former-cityscapes-olac β mask2former_cityscapes_olac}/README.md
RENAMED
|
@@ -29,14 +29,14 @@ Run from the PEMOLA repository root after installing its dependencies:
|
|
| 29 |
```bash
|
| 30 |
python -m pip install huggingface_hub
|
| 31 |
hf download weiwb/PEMOLA \
|
| 32 |
-
--include "
|
| 33 |
--local-dir checkpoints
|
| 34 |
|
| 35 |
python predict.py \
|
| 36 |
-
--config checkpoints/
|
| 37 |
-
--weights checkpoints/
|
| 38 |
--input /path/to/image.jpg \
|
| 39 |
-
--output-dir output/
|
| 40 |
--no-pemola \
|
| 41 |
--format png
|
| 42 |
```
|
|
@@ -45,7 +45,7 @@ The baseline requires only an input image; CAM tensors and occlusion labels are
|
|
| 45 |
|
| 46 |
## Files
|
| 47 |
|
| 48 |
-
- `
|
| 49 |
- `config.yaml`: matching configuration for the PEMOLA implementation.
|
| 50 |
- `LICENSE`: MIT license.
|
| 51 |
|
|
|
|
| 29 |
```bash
|
| 30 |
python -m pip install huggingface_hub
|
| 31 |
hf download weiwb/PEMOLA \
|
| 32 |
+
--include "mask2former_cityscapes_olac/*" \
|
| 33 |
--local-dir checkpoints
|
| 34 |
|
| 35 |
python predict.py \
|
| 36 |
+
--config checkpoints/mask2former_cityscapes_olac/config.yaml \
|
| 37 |
+
--weights checkpoints/mask2former_cityscapes_olac/mask2former_cityscapes_olac.pth \
|
| 38 |
--input /path/to/image.jpg \
|
| 39 |
+
--output-dir output/mask2former_cityscapes_olac-predictions \
|
| 40 |
--no-pemola \
|
| 41 |
--format png
|
| 42 |
```
|
|
|
|
| 45 |
|
| 46 |
## Files
|
| 47 |
|
| 48 |
+
- `mask2former_cityscapes_olac.pth`: model weights.
|
| 49 |
- `config.yaml`: matching configuration for the PEMOLA implementation.
|
| 50 |
- `LICENSE`: MIT license.
|
| 51 |
|
{mask2former-cityscapes-olac β mask2former_cityscapes_olac}/config.yaml
RENAMED
|
@@ -383,7 +383,7 @@ MODEL:
|
|
| 383 |
QK_SCALE: null
|
| 384 |
USE_CHECKPOINT: false
|
| 385 |
WINDOW_SIZE: 7
|
| 386 |
-
WEIGHTS:
|
| 387 |
OUTPUT_DIR: output/mask2former-r50-cityscapes-olac
|
| 388 |
SEED: 618
|
| 389 |
SOLVER:
|
|
|
|
| 383 |
QK_SCALE: null
|
| 384 |
USE_CHECKPOINT: false
|
| 385 |
WINDOW_SIZE: 7
|
| 386 |
+
WEIGHTS: mask2former_cityscapes_olac.pth
|
| 387 |
OUTPUT_DIR: output/mask2former-r50-cityscapes-olac
|
| 388 |
SEED: 618
|
| 389 |
SOLVER:
|
mask2former-cityscapes-olac/model_final.pth β mask2former_cityscapes_olac/mask2former_cityscapes_olac.pth
RENAMED
|
File without changes
|
{mask2former-coco-olac β mask2former_coco_olac}/LICENSE
RENAMED
|
File without changes
|
{mask2former-coco-olac β mask2former_coco_olac}/README.md
RENAMED
|
@@ -29,14 +29,14 @@ Run from the PEMOLA repository root after installing its dependencies:
|
|
| 29 |
```bash
|
| 30 |
python -m pip install huggingface_hub
|
| 31 |
hf download weiwb/PEMOLA \
|
| 32 |
-
--include "
|
| 33 |
--local-dir checkpoints
|
| 34 |
|
| 35 |
python predict.py \
|
| 36 |
-
--config checkpoints/
|
| 37 |
-
--weights checkpoints/
|
| 38 |
--input /path/to/image.jpg \
|
| 39 |
-
--output-dir output/
|
| 40 |
--no-pemola \
|
| 41 |
--format png
|
| 42 |
```
|
|
@@ -45,7 +45,7 @@ The baseline requires only an input image; CAM tensors and occlusion labels are
|
|
| 45 |
|
| 46 |
## Files
|
| 47 |
|
| 48 |
-
- `
|
| 49 |
- `config.yaml`: matching configuration for the PEMOLA implementation.
|
| 50 |
- `LICENSE`: MIT license.
|
| 51 |
|
|
|
|
| 29 |
```bash
|
| 30 |
python -m pip install huggingface_hub
|
| 31 |
hf download weiwb/PEMOLA \
|
| 32 |
+
--include "mask2former_coco_olac/*" \
|
| 33 |
--local-dir checkpoints
|
| 34 |
|
| 35 |
python predict.py \
|
| 36 |
+
--config checkpoints/mask2former_coco_olac/config.yaml \
|
| 37 |
+
--weights checkpoints/mask2former_coco_olac/mask2former_coco_olac.pth \
|
| 38 |
--input /path/to/image.jpg \
|
| 39 |
+
--output-dir output/mask2former_coco_olac-predictions \
|
| 40 |
--no-pemola \
|
| 41 |
--format png
|
| 42 |
```
|
|
|
|
| 45 |
|
| 46 |
## Files
|
| 47 |
|
| 48 |
+
- `mask2former_coco_olac.pth`: model weights.
|
| 49 |
- `config.yaml`: matching configuration for the PEMOLA implementation.
|
| 50 |
- `LICENSE`: MIT license.
|
| 51 |
|
{mask2former-coco-olac β mask2former_coco_olac}/config.yaml
RENAMED
|
@@ -371,7 +371,7 @@ MODEL:
|
|
| 371 |
QK_SCALE: null
|
| 372 |
USE_CHECKPOINT: false
|
| 373 |
WINDOW_SIZE: 7
|
| 374 |
-
WEIGHTS:
|
| 375 |
OUTPUT_DIR: output/mask2former-r50-coco-olac
|
| 376 |
SEED: 618
|
| 377 |
SOLVER:
|
|
|
|
| 371 |
QK_SCALE: null
|
| 372 |
USE_CHECKPOINT: false
|
| 373 |
WINDOW_SIZE: 7
|
| 374 |
+
WEIGHTS: mask2former_coco_olac.pth
|
| 375 |
OUTPUT_DIR: output/mask2former-r50-coco-olac
|
| 376 |
SEED: 618
|
| 377 |
SOLVER:
|
mask2former-coco-olac/model_final.pth β mask2former_coco_olac/mask2former_coco_olac.pth
RENAMED
|
File without changes
|
{pemola-cityscapes-olac β mask2former_pemola_cityscapes_olac}/LICENSE
RENAMED
|
File without changes
|
{pemola-cityscapes-olac β mask2former_pemola_cityscapes_olac}/README.md
RENAMED
|
@@ -32,12 +32,12 @@ Install the [PEMOLA environment](https://github.com/wenbo-wei/PEMOLA#installatio
|
|
| 32 |
|
| 33 |
```bash
|
| 34 |
hf download weiwb/PEMOLA \
|
| 35 |
-
--include "
|
| 36 |
--local-dir checkpoints
|
| 37 |
|
| 38 |
python predict.py \
|
| 39 |
-
--config checkpoints/
|
| 40 |
-
--weights checkpoints/
|
| 41 |
--input /path/to/image.png \
|
| 42 |
--output-dir output/pemola-city-predictions \
|
| 43 |
--cam-dir /path/to/cam_pt \
|
|
@@ -49,11 +49,11 @@ For `image.jpg`, provide `cam_pt/image.pt` and a label JSON entry such as `{"ima
|
|
| 49 |
|
| 50 |
For Cityscapes, CAM filenames and label keys must include `_leftImg8bit` when the input filename does.
|
| 51 |
|
| 52 |
-
The [Swin-L classifier](https://huggingface.co/weiwb/PEMOLA/blob/main/
|
| 53 |
|
| 54 |
## Files
|
| 55 |
|
| 56 |
-
- `
|
| 57 |
- `config.yaml`: configuration for this checkpoint.
|
| 58 |
- `LICENSE`: MIT license.
|
| 59 |
|
|
|
|
| 32 |
|
| 33 |
```bash
|
| 34 |
hf download weiwb/PEMOLA \
|
| 35 |
+
--include "mask2former_pemola_cityscapes_olac/*" \
|
| 36 |
--local-dir checkpoints
|
| 37 |
|
| 38 |
python predict.py \
|
| 39 |
+
--config checkpoints/mask2former_pemola_cityscapes_olac/config.yaml \
|
| 40 |
+
--weights checkpoints/mask2former_pemola_cityscapes_olac/mask2former_pemola_cityscapes_olac.pth \
|
| 41 |
--input /path/to/image.png \
|
| 42 |
--output-dir output/pemola-city-predictions \
|
| 43 |
--cam-dir /path/to/cam_pt \
|
|
|
|
| 49 |
|
| 50 |
For Cityscapes, CAM filenames and label keys must include `_leftImg8bit` when the input filename does.
|
| 51 |
|
| 52 |
+
The [Swin-L classifier](https://huggingface.co/weiwb/PEMOLA/blob/main/swin_l_384_occlusion_coco_olac/README.md) supplies label-prediction and CAM-generation commands. CAM preparation uses matching original and background-blackened images.
|
| 53 |
|
| 54 |
## Files
|
| 55 |
|
| 56 |
+
- `mask2former_pemola_cityscapes_olac.pth`: model state dictionary under the `model` key.
|
| 57 |
- `config.yaml`: configuration for this checkpoint.
|
| 58 |
- `LICENSE`: MIT license.
|
| 59 |
|
{pemola-cityscapes-olac β mask2former_pemola_cityscapes_olac}/config.yaml
RENAMED
|
@@ -383,7 +383,7 @@ MODEL:
|
|
| 383 |
QK_SCALE: null
|
| 384 |
USE_CHECKPOINT: false
|
| 385 |
WINDOW_SIZE: 7
|
| 386 |
-
WEIGHTS:
|
| 387 |
OUTPUT_DIR: ./output
|
| 388 |
SEED: 618
|
| 389 |
SOLVER:
|
|
|
|
| 383 |
QK_SCALE: null
|
| 384 |
USE_CHECKPOINT: false
|
| 385 |
WINDOW_SIZE: 7
|
| 386 |
+
WEIGHTS: mask2former_pemola_cityscapes_olac.pth
|
| 387 |
OUTPUT_DIR: ./output
|
| 388 |
SEED: 618
|
| 389 |
SOLVER:
|
pemola-cityscapes-olac/model_final.pth β mask2former_pemola_cityscapes_olac/mask2former_pemola_cityscapes_olac.pth
RENAMED
|
File without changes
|
{pemola-cityscapes-olac β mask2former_pemola_cityscapes_olac}/run_metrics.json
RENAMED
|
File without changes
|
{pemola-coco-olac β mask2former_pemola_coco_olac}/LICENSE
RENAMED
|
File without changes
|
{pemola-coco-olac β mask2former_pemola_coco_olac}/README.md
RENAMED
|
@@ -32,12 +32,12 @@ Install the [PEMOLA environment](https://github.com/wenbo-wei/PEMOLA#installatio
|
|
| 32 |
|
| 33 |
```bash
|
| 34 |
hf download weiwb/PEMOLA \
|
| 35 |
-
--include "
|
| 36 |
--local-dir checkpoints
|
| 37 |
|
| 38 |
python predict.py \
|
| 39 |
-
--config checkpoints/
|
| 40 |
-
--weights checkpoints/
|
| 41 |
--input /path/to/image.jpg \
|
| 42 |
--output-dir output/pemola-coco-predictions \
|
| 43 |
--cam-dir /path/to/cam_pt \
|
|
@@ -47,11 +47,11 @@ python predict.py \
|
|
| 47 |
|
| 48 |
For `image.jpg`, provide `cam_pt/image.pt` and a label JSON entry such as `{"image": "mid"}`. CAMs are two-dimensional tensors; labels are `low`, `mid`, or `high`.
|
| 49 |
|
| 50 |
-
The [Swin-L classifier](https://huggingface.co/weiwb/PEMOLA/blob/main/
|
| 51 |
|
| 52 |
## Files
|
| 53 |
|
| 54 |
-
- `
|
| 55 |
- `config.yaml`: configuration for this checkpoint.
|
| 56 |
- `LICENSE`: MIT license.
|
| 57 |
|
|
|
|
| 32 |
|
| 33 |
```bash
|
| 34 |
hf download weiwb/PEMOLA \
|
| 35 |
+
--include "mask2former_pemola_coco_olac/*" \
|
| 36 |
--local-dir checkpoints
|
| 37 |
|
| 38 |
python predict.py \
|
| 39 |
+
--config checkpoints/mask2former_pemola_coco_olac/config.yaml \
|
| 40 |
+
--weights checkpoints/mask2former_pemola_coco_olac/mask2former_pemola_coco_olac.pth \
|
| 41 |
--input /path/to/image.jpg \
|
| 42 |
--output-dir output/pemola-coco-predictions \
|
| 43 |
--cam-dir /path/to/cam_pt \
|
|
|
|
| 47 |
|
| 48 |
For `image.jpg`, provide `cam_pt/image.pt` and a label JSON entry such as `{"image": "mid"}`. CAMs are two-dimensional tensors; labels are `low`, `mid`, or `high`.
|
| 49 |
|
| 50 |
+
The [Swin-L classifier](https://huggingface.co/weiwb/PEMOLA/blob/main/swin_l_384_occlusion_coco_olac/README.md) supplies label-prediction and CAM-generation commands. CAM preparation uses matching original and background-blackened images.
|
| 51 |
|
| 52 |
## Files
|
| 53 |
|
| 54 |
+
- `mask2former_pemola_coco_olac.pth`: model state dictionary under the `model` key.
|
| 55 |
- `config.yaml`: configuration for this checkpoint.
|
| 56 |
- `LICENSE`: MIT license.
|
| 57 |
|
{pemola-coco-olac β mask2former_pemola_coco_olac}/config.yaml
RENAMED
|
@@ -371,7 +371,7 @@ MODEL:
|
|
| 371 |
QK_SCALE: null
|
| 372 |
USE_CHECKPOINT: false
|
| 373 |
WINDOW_SIZE: 7
|
| 374 |
-
WEIGHTS:
|
| 375 |
OUTPUT_DIR: ./output
|
| 376 |
SEED: 618
|
| 377 |
SOLVER:
|
|
|
|
| 371 |
QK_SCALE: null
|
| 372 |
USE_CHECKPOINT: false
|
| 373 |
WINDOW_SIZE: 7
|
| 374 |
+
WEIGHTS: mask2former_pemola_coco_olac.pth
|
| 375 |
OUTPUT_DIR: ./output
|
| 376 |
SEED: 618
|
| 377 |
SOLVER:
|
pemola-coco-olac/model_final.pth β mask2former_pemola_coco_olac/mask2former_pemola_coco_olac.pth
RENAMED
|
File without changes
|
{pemola-coco-olac β mask2former_pemola_coco_olac}/run_metrics.json
RENAMED
|
File without changes
|
{maskdino-coco-olac β maskdino_coco_olac}/LICENSE
RENAMED
|
File without changes
|
{maskdino-coco-olac β maskdino_coco_olac}/README.md
RENAMED
|
@@ -31,15 +31,15 @@ Use the dedicated [Mask DINO implementation](https://github.com/wenbo-wei/MaskDI
|
|
| 31 |
|
| 32 |
```bash
|
| 33 |
hf download weiwb/PEMOLA \
|
| 34 |
-
--include "
|
| 35 |
--local-dir checkpoints
|
| 36 |
|
| 37 |
export DETECTRON2_DATASETS=datasets/data
|
| 38 |
python train_net.py \
|
| 39 |
-
--config-file checkpoints/
|
| 40 |
--num-gpus 1 \
|
| 41 |
--eval-only \
|
| 42 |
-
MODEL.WEIGHTS checkpoints/
|
| 43 |
DATASETS.TEST '("coco_olac_val",)'
|
| 44 |
```
|
| 45 |
|
|
@@ -47,7 +47,7 @@ The configuration uses the implementation's `MODEL.OAM` options, with `PE_MODULA
|
|
| 47 |
|
| 48 |
## Files
|
| 49 |
|
| 50 |
-
- `
|
| 51 |
- `config.yaml`: configuration for this checkpoint.
|
| 52 |
- `LICENSE`: Apache License 2.0, following the Mask DINO source project.
|
| 53 |
|
|
|
|
| 31 |
|
| 32 |
```bash
|
| 33 |
hf download weiwb/PEMOLA \
|
| 34 |
+
--include "maskdino_coco_olac/*" \
|
| 35 |
--local-dir checkpoints
|
| 36 |
|
| 37 |
export DETECTRON2_DATASETS=datasets/data
|
| 38 |
python train_net.py \
|
| 39 |
+
--config-file checkpoints/maskdino_coco_olac/config.yaml \
|
| 40 |
--num-gpus 1 \
|
| 41 |
--eval-only \
|
| 42 |
+
MODEL.WEIGHTS checkpoints/maskdino_coco_olac/maskdino_coco_olac.pth \
|
| 43 |
DATASETS.TEST '("coco_olac_val",)'
|
| 44 |
```
|
| 45 |
|
|
|
|
| 47 |
|
| 48 |
## Files
|
| 49 |
|
| 50 |
+
- `maskdino_coco_olac.pth`: model state dictionary under the `model` key.
|
| 51 |
- `config.yaml`: configuration for this checkpoint.
|
| 52 |
- `LICENSE`: Apache License 2.0, following the Mask DINO source project.
|
| 53 |
|
{maskdino-coco-olac β maskdino_coco_olac}/config.yaml
RENAMED
|
@@ -379,7 +379,7 @@ MODEL:
|
|
| 379 |
QK_SCALE: null
|
| 380 |
USE_CHECKPOINT: false
|
| 381 |
WINDOW_SIZE: 7
|
| 382 |
-
WEIGHTS: ./
|
| 383 |
OUTPUT_DIR: ./output/maskdino_r50
|
| 384 |
SEED: 618
|
| 385 |
SOLVER:
|
|
|
|
| 379 |
QK_SCALE: null
|
| 380 |
USE_CHECKPOINT: false
|
| 381 |
WINDOW_SIZE: 7
|
| 382 |
+
WEIGHTS: ./maskdino_coco_olac.pth
|
| 383 |
OUTPUT_DIR: ./output/maskdino_r50
|
| 384 |
SEED: 618
|
| 385 |
SOLVER:
|
maskdino-coco-olac/model_final.pth β maskdino_coco_olac/maskdino_coco_olac.pth
RENAMED
|
File without changes
|
{pemola-maskdino-coco-olac β maskdino_pemola_coco_olac}/LICENSE
RENAMED
|
File without changes
|
{pemola-maskdino-coco-olac β maskdino_pemola_coco_olac}/README.md
RENAMED
|
@@ -31,15 +31,15 @@ Use the dedicated [Mask DINO implementation](https://github.com/wenbo-wei/MaskDI
|
|
| 31 |
|
| 32 |
```bash
|
| 33 |
hf download weiwb/PEMOLA \
|
| 34 |
-
--include "
|
| 35 |
--local-dir checkpoints
|
| 36 |
|
| 37 |
export DETECTRON2_DATASETS=datasets/data
|
| 38 |
python train_net.py \
|
| 39 |
-
--config-file checkpoints/
|
| 40 |
--num-gpus 1 \
|
| 41 |
--eval-only \
|
| 42 |
-
MODEL.WEIGHTS checkpoints/
|
| 43 |
DATASETS.TEST '("coco_olac_val",)'
|
| 44 |
```
|
| 45 |
|
|
@@ -49,7 +49,7 @@ The configuration uses the implementation's `MODEL.OAM` options, with `PE_MODULA
|
|
| 49 |
|
| 50 |
## Files
|
| 51 |
|
| 52 |
-
- `
|
| 53 |
- `config.yaml`: configuration for this checkpoint.
|
| 54 |
- `LICENSE`: Apache License 2.0, following the Mask DINO source project.
|
| 55 |
|
|
|
|
| 31 |
|
| 32 |
```bash
|
| 33 |
hf download weiwb/PEMOLA \
|
| 34 |
+
--include "maskdino_pemola_coco_olac/*" \
|
| 35 |
--local-dir checkpoints
|
| 36 |
|
| 37 |
export DETECTRON2_DATASETS=datasets/data
|
| 38 |
python train_net.py \
|
| 39 |
+
--config-file checkpoints/maskdino_pemola_coco_olac/config.yaml \
|
| 40 |
--num-gpus 1 \
|
| 41 |
--eval-only \
|
| 42 |
+
MODEL.WEIGHTS checkpoints/maskdino_pemola_coco_olac/maskdino_pemola_coco_olac.pth \
|
| 43 |
DATASETS.TEST '("coco_olac_val",)'
|
| 44 |
```
|
| 45 |
|
|
|
|
| 49 |
|
| 50 |
## Files
|
| 51 |
|
| 52 |
+
- `maskdino_pemola_coco_olac.pth`: model state dictionary under the `model` key.
|
| 53 |
- `config.yaml`: configuration for this checkpoint.
|
| 54 |
- `LICENSE`: Apache License 2.0, following the Mask DINO source project.
|
| 55 |
|
{pemola-maskdino-coco-olac β maskdino_pemola_coco_olac}/config.yaml
RENAMED
|
@@ -379,7 +379,7 @@ MODEL:
|
|
| 379 |
QK_SCALE: null
|
| 380 |
USE_CHECKPOINT: false
|
| 381 |
WINDOW_SIZE: 7
|
| 382 |
-
WEIGHTS: ./
|
| 383 |
OUTPUT_DIR: ./output/pemola_maskdino_r50
|
| 384 |
SEED: 618
|
| 385 |
SOLVER:
|
|
|
|
| 379 |
QK_SCALE: null
|
| 380 |
USE_CHECKPOINT: false
|
| 381 |
WINDOW_SIZE: 7
|
| 382 |
+
WEIGHTS: ./maskdino_pemola_coco_olac.pth
|
| 383 |
OUTPUT_DIR: ./output/pemola_maskdino_r50
|
| 384 |
SEED: 618
|
| 385 |
SOLVER:
|
pemola-maskdino-coco-olac/model_final.pth β maskdino_pemola_coco_olac/maskdino_pemola_coco_olac.pth
RENAMED
|
File without changes
|
{pemola-occlusion-swin-l β swin_l_384_occlusion_coco_olac}/LICENSE
RENAMED
|
File without changes
|
{pemola-occlusion-swin-l β swin_l_384_occlusion_coco_olac}/README.md
RENAMED
|
@@ -33,7 +33,7 @@ Install the [PEMOLA environment](https://github.com/wenbo-wei/PEMOLA#installatio
|
|
| 33 |
|
| 34 |
```bash
|
| 35 |
hf download weiwb/PEMOLA \
|
| 36 |
-
--include "
|
| 37 |
--local-dir checkpoints
|
| 38 |
|
| 39 |
mkdir -p output/occlusion-inference
|
|
@@ -41,8 +41,8 @@ printf '{}\n' > output/occlusion-inference/empty_labels.json
|
|
| 41 |
|
| 42 |
torchrun --standalone --nnodes=1 --nproc_per_node=1 \
|
| 43 |
occ_cls_predict.py \
|
| 44 |
-
--cfg checkpoints/
|
| 45 |
-
--resume checkpoints/
|
| 46 |
--data_path /path/to/images_blackbg \
|
| 47 |
--occlusion_ann output/occlusion-inference/empty_labels.json \
|
| 48 |
--batch_size 1 \
|
|
@@ -61,8 +61,8 @@ Provide matching filenames in `/path/to/images` and `/path/to/images_blackbg`, p
|
|
| 61 |
```bash
|
| 62 |
torchrun --standalone --nnodes=1 --nproc_per_node=1 \
|
| 63 |
occ_cls_draw_cam.py \
|
| 64 |
-
--cfg checkpoints/
|
| 65 |
-
--resume checkpoints/
|
| 66 |
--dataset coco \
|
| 67 |
--data_path /path/to/images \
|
| 68 |
--occlusion_ann /path/to/occlusion_labels.json \
|
|
@@ -75,7 +75,7 @@ CAM tensors are written to `output/occlusion-inference/swin_large_patch4_window1
|
|
| 75 |
|
| 76 |
## Files
|
| 77 |
|
| 78 |
-
- `
|
| 79 |
- `config.yaml`: classifier configuration.
|
| 80 |
- `LICENSE`: MIT license.
|
| 81 |
|
|
|
|
| 33 |
|
| 34 |
```bash
|
| 35 |
hf download weiwb/PEMOLA \
|
| 36 |
+
--include "swin_l_384_occlusion_coco_olac/*" \
|
| 37 |
--local-dir checkpoints
|
| 38 |
|
| 39 |
mkdir -p output/occlusion-inference
|
|
|
|
| 41 |
|
| 42 |
torchrun --standalone --nnodes=1 --nproc_per_node=1 \
|
| 43 |
occ_cls_predict.py \
|
| 44 |
+
--cfg checkpoints/swin_l_384_occlusion_coco_olac/config.yaml \
|
| 45 |
+
--resume checkpoints/swin_l_384_occlusion_coco_olac/swin_l_384_occlusion_coco_olac.pth \
|
| 46 |
--data_path /path/to/images_blackbg \
|
| 47 |
--occlusion_ann output/occlusion-inference/empty_labels.json \
|
| 48 |
--batch_size 1 \
|
|
|
|
| 61 |
```bash
|
| 62 |
torchrun --standalone --nnodes=1 --nproc_per_node=1 \
|
| 63 |
occ_cls_draw_cam.py \
|
| 64 |
+
--cfg checkpoints/swin_l_384_occlusion_coco_olac/config.yaml \
|
| 65 |
+
--resume checkpoints/swin_l_384_occlusion_coco_olac/swin_l_384_occlusion_coco_olac.pth \
|
| 66 |
--dataset coco \
|
| 67 |
--data_path /path/to/images \
|
| 68 |
--occlusion_ann /path/to/occlusion_labels.json \
|
|
|
|
| 75 |
|
| 76 |
## Files
|
| 77 |
|
| 78 |
+
- `swin_l_384_occlusion_coco_olac.pth`: model state dictionary under the `model` key.
|
| 79 |
- `config.yaml`: classifier configuration.
|
| 80 |
- `LICENSE`: MIT license.
|
| 81 |
|
{pemola-occlusion-swin-l β swin_l_384_occlusion_coco_olac}/config.yaml
RENAMED
|
File without changes
|
pemola-occlusion-swin-l/ep29.pth β swin_l_384_occlusion_coco_olac/swin_l_384_occlusion_coco_olac.pth
RENAMED
|
File without changes
|