Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

detection models without ir problems #1982

Open
wants to merge 8 commits into
base: develop
Choose a base branch
from
Open

detection models without ir problems #1982

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
8c29a9b
detection models without ir problems
lunaticsst Sep 11, 2024
17a9ef2
Merge branch 'develop' of github.com:PaddlePaddle/PaddleX into for_de…
lunaticsst Sep 12, 2024
0b69dae
export model path
lunaticsst Sep 12, 2024
eceda47
change names
lunaticsst Sep 12, 2024
0e158a1
change names
lunaticsst Sep 12, 2024
7da873d
change predict imgs
lunaticsst Sep 12, 2024
823412d
add CenterNet models
lunaticsst Sep 12, 2024
b3fce25
Merge branch 'develop' into for_detection
Sunting78 Sep 14, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,7 +70,7 @@ PaddleX 3.0 覆盖了 16 条产业级模型产线，其中 9 条基础产线可
<td>通用目标检测</td>
<td>目标检测</td>
<td>PicoDet-S<br/>PicoDet-L<details>
<summary><b>more</b></summary><br/>PP-YOLOE_plus-S<br/>PP-YOLOE_plus-M<br/>PP-YOLOE_plus-L<br/>PP-YOLOE_plus-X<br/>RT-DETR-L<br/>RT-DETR-H<br/>RT-DETR-X<br/>RT-DETR-R18<br/>RT-DETR-R50<br/>YOLOv3-DarkNet53<br/>YOLOv3-MobileNetV3<br/>YOLOv3-ResNet50_vd_DCN<br/>YOLOX-L<br/>YOLOX-M<br/>YOLOX-N<br/>YOLOX-S<br/>YOLOX-T<br/>YOLOX-X</details></td>
<summary><b>more</b></summary><br/>PicoDet-XS<br/>PicoDet-M<br/>PP-YOLOE_plus-S<br/>PP-YOLOE_plus-M<br/>PP-YOLOE_plus-L<br/>PP-YOLOE_plus-X<br/>RT-DETR-L<br/>RT-DETR-H<br/>RT-DETR-X<br/>RT-DETR-R18<br/>RT-DETR-R50<br/>YOLOv3-DarkNet53<br/>YOLOv3-MobileNetV3<br/>YOLOv3-ResNet50_vd_DCN<br/>YOLOX-L<br/>YOLOX-M<br/>YOLOX-N<br/>YOLOX-S<br/>YOLOX-T<br/>YOLOX-X<br/>FCOS-ResNet50<br/>DETR-R50<br/>PP-YOLOE-vehicle-L<br/>PP-YOLOE-vehicle-S<br/>PicoDet-LCNet_x2_5<br/>PP-YOLOE-human-S<br/>PP-YOLOE-human-L<br/>PP-YOLOE+_SOD-L<br/>PP-YOLOE+_SOD-S<br/>PP-YOLOE+_SOD-largesize-L</details></td>
</tr>
<tr>
<td>基础产线</td>
Expand Down
21 changes: 21 additions & 0 deletions docs/tutorials/models/support_model_list.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -115,6 +115,9 @@
| PP-YOLOE_plus-M | [PP-YOLOE_plus-M.yaml](../../../paddlex/configs/object_detection/PP-YOLOE_plus-M.yaml)|
| PP-YOLOE_plus-L | [PP-YOLOE_plus-L.yaml](../../../paddlex/configs/object_detection/PP-YOLOE_plus-L.yaml)|
| PP-YOLOE_plus-X | [PP-YOLOE_plus-X.yaml](../../../paddlex/configs/object_detection/PP-YOLOE_plus-X.yaml)|
| PP-YOLOE+_SOD-L | [PP-YOLOE+_SOD-L.yaml](../../../paddlex/configs/object_detection/PP-YOLOE+_SOD-L.yaml)|
| PP-YOLOE+_SOD-S | [PP-YOLOE+_SOD-S.yaml](../../../paddlex/configs/object_detection/PP-YOLOE+_SOD-S.yaml)|
| PP-YOLOE+_SOD-largesize-L | [PP-YOLOE+_SOD-largesize-L.yaml](../../../paddlex/configs/object_detection/PP-YOLOE+_SOD-largesize-L.yaml)|
### 2. RT-DETR 系列
| 模型名称 | config |
| :--- | :---: |
Expand All @@ -128,6 +131,9 @@
| :--- | :---: |
| PicoDet-S | [PicoDet-S.yaml](../../../paddlex/configs/object_detection/PicoDet-S.yaml)|
| PicoDet-L | [PicoDet-L.yaml](../../../paddlex/configs/object_detection/PicoDet-L.yaml)|
| PicoDet-M | [PicoDet-M.yaml](../../../paddlex/configs/object_detection/PicoDet-M.yaml)|
| PicoDet-XS | [PicoDet-XS.yaml](../../../paddlex/configs/object_detection/PicoDet-XS.yaml)|
| PicoDet-LCNet_x2_5 | [PicoDet-LCNet_x2_5.yaml](../../../paddlex/configs/object_detection/PicoDet-LCNet_x2_5.yaml)|
### 4. YOLOv3 系列
| 模型名称 | config |
| :--- | :---: |
Expand All @@ -143,6 +149,21 @@
| YOLOX-S | [YOLOX-S.yaml](../../../paddlex/configs/object_detection/YOLOX-S.yaml)|
| YOLOX-T | [YOLOX-T.yaml](../../../paddlex/configs/object_detection/YOLOX-T.yaml)|
| YOLOX-X | [YOLOX-X.yaml](../../../paddlex/configs/object_detection/YOLOX-X.yaml)|
### 6. FCOS 系列
| 模型名称 | config |
| :--- | :---: |
| FCOS-ResNet50 | [FCOS-ResNet50.yaml](../../../paddlex/configs/object_detection/FCOS-ResNet50.yaml)|
### 7. DETR 系列
| 模型名称 | config |
| :--- | :---: |
| DETR-R50 | [DETR-R50.yaml](../../../paddlex/configs/object_detection/DETR-R50.yaml)|
### 8. PP-YOLOE 系列
| 模型名称 | config |
| :--- | :---: |
| PP-YOLOE-vehicle-L | [PP-YOLOE-vehicle-L.yaml](../../../paddlex/configs/object_detection/PP-YOLOE-vehicle-L.yaml)|
| PP-YOLOE-vehicle-S | [PP-YOLOE-vehicle-S.yaml](../../../paddlex/configs/object_detection/PP-YOLOE-vehicle-S.yaml)|
| PP-YOLOE-human-L | [PP-YOLOE-human-L.yaml](../../../paddlex/configs/object_detection/PP-YOLOE-human-L.yaml)|
| PP-YOLOE-human-S | [PP-YOLOE-human-S.yaml](../../../paddlex/configs/object_detection/PP-YOLOE-human-S.yaml)|
## 三、实例分割
### 1.Mask-RT-DETR 系列
| 模型名称 | config |
Expand Down
37 changes: 37 additions & 0 deletions paddlex/configs/object_detection/DETR-R50.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,37 @@
Global:
model: DETR-R50
mode: check_dataset # check_dataset/train/evaluate/predict
dataset_dir: "/paddle/dataset/paddlex/det/det_coco_examples"
device: gpu:0,1,2,3
output: "output"

CheckDataset:
convert:
enable: False
src_dataset_type: null
split:
enable: False
train_percent: null
val_percent: null

Train:
num_classes: 4
epochs_iters: 50
batch_size: 2
learning_rate: #0.08
pretrain_weight_path: null
warmup_steps: #100
resume_path: null
log_interval: 10
eval_interval: 1

Evaluate:
weight_path: "output/best_model.pdparams"
log_interval: 10

Predict:
model_dir: "output/best_model"
input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png"
kernel_option:
run_mode: paddle
batch_size: 1
37 changes: 37 additions & 0 deletions paddlex/configs/object_detection/FCOS-ResNet50.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,37 @@
Global:
model: FCOS-ResNet50
mode: check_dataset # check_dataset/train/evaluate/predict
dataset_dir: "/paddle/dataset/paddlex/det/det_coco_examples"
device: gpu:0,1,2,3
output: "output"

CheckDataset:
convert:
enable: False
src_dataset_type: null
split:
enable: False
train_percent: null
val_percent: null

Train:
num_classes: 4
epochs_iters: 50
batch_size: 4
learning_rate: 0.002
pretrain_weight_path: null
warmup_steps: # 100
resume_path: null
log_interval: 10
eval_interval: 1

Evaluate:
weight_path: "output/best_model.pdparams"
log_interval: 10

Predict:
model_dir: "output/best_model"
input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png"
kernel_option:
run_mode: paddle
batch_size: 1
37 changes: 37 additions & 0 deletions paddlex/configs/object_detection/PP-YOLOE+_SOD-L.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,37 @@
Global:
model: PP-YOLOE+_SOD-L
mode: check_dataset # check_dataset/train/evaluate/predict
dataset_dir: "/paddle/dataset/paddlex/det/det_coco_examples"
device: gpu:0,1,2,3
output: "output"

CheckDataset:
convert:
enable: False
src_dataset_type: null
split:
enable: False
train_percent: null
val_percent: null

Train:
num_classes: 4
epochs_iters: 50
batch_size: 2
learning_rate: 0.001
pretrain_weight_path: null
warmup_steps: #100
resume_path: null
log_interval: 10
eval_interval: 1

Evaluate:
weight_path: "output/best_model.pdparams"
log_interval: 10

Predict:
model_dir: "output/best_model"
input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png"
kernel_option:
run_mode: paddle
batch_size: 1
37 changes: 37 additions & 0 deletions paddlex/configs/object_detection/PP-YOLOE+_SOD-S.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,37 @@
Global:
model: PP-YOLOE+_SOD-S
mode: check_dataset # check_dataset/train/evaluate/predict
dataset_dir: "/paddle/dataset/paddlex/det/det_coco_examples"
device: gpu:0,1,2,3
output: "output"

CheckDataset:
convert:
enable: False
src_dataset_type: null
split:
enable: False
train_percent: null
val_percent: null

Train:
num_classes: 4
epochs_iters: 50
batch_size: 2
learning_rate: 0.001
pretrain_weight_path: null
warmup_steps: #100
resume_path: null
log_interval: 10
eval_interval: 1

Evaluate:
weight_path: "output/best_model.pdparams"
log_interval: 10

Predict:
model_dir: "output/best_model"
input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png"
kernel_option:
run_mode: paddle
batch_size: 1
37 changes: 37 additions & 0 deletions paddlex/configs/object_detection/PP-YOLOE+_SOD-largesize-L.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,37 @@
Global:
model: PP-YOLOE+_SOD-largesize-L
mode: check_dataset # check_dataset/train/evaluate/predict
dataset_dir: "/paddle/dataset/paddlex/det/det_coco_examples"
device: gpu:0,1,2,3
output: "output"

CheckDataset:
convert:
enable: False
src_dataset_type: null
split:
enable: False
train_percent: null
val_percent: null

Train:
num_classes: 4
epochs_iters: 10
batch_size: 2
learning_rate: 0.0001
pretrain_weight_path: null
warmup_steps: 100
resume_path: null
log_interval: 3
eval_interval: 1

Evaluate:
weight_path: "output/best_model.pdparams"
log_interval: 10

Predict:
model_dir: "output/best_model"
input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png"
kernel_option:
run_mode: paddle
batch_size: 1
37 changes: 37 additions & 0 deletions paddlex/configs/object_detection/PP-YOLOE-human-L.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,37 @@
Global:
model: PP-YOLOE-human-L
mode: check_dataset # check_dataset/train/evaluate/predict
dataset_dir: "/paddle/dataset/paddlex/det/det_coco_examples"
device: gpu:0,1,2,3
output: "output"

CheckDataset:
convert:
enable: False
src_dataset_type: null
split:
enable: False
train_percent: null
val_percent: null

Train:
num_classes: 4
epochs_iters: 50
batch_size: 2
learning_rate: #0.08
pretrain_weight_path: null
warmup_steps: #100
resume_path: null
log_interval: 10
eval_interval: 1

Evaluate:
weight_path: "output/best_model.pdparams"
log_interval: 10

Predict:
model_dir: "output/best_model"
input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png"
kernel_option:
run_mode: paddle
batch_size: 1
37 changes: 37 additions & 0 deletions paddlex/configs/object_detection/PP-YOLOE-human-S.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,37 @@
Global:
model: PP-YOLOE-human-S
mode: check_dataset # check_dataset/train/evaluate/predict
dataset_dir: "/paddle/dataset/paddlex/det/det_coco_examples"
device: gpu:0,1,2,3
output: "output"

CheckDataset:
convert:
enable: False
src_dataset_type: null
split:
enable: False
train_percent: null
val_percent: null

Train:
num_classes: 4
epochs_iters: 50
batch_size: 2
learning_rate: #0.08
pretrain_weight_path: null
warmup_steps: #100
resume_path: null
log_interval: 10
eval_interval: 1

Evaluate:
weight_path: "output/best_model.pdparams"
log_interval: 10

Predict:
model_dir: "output/best_model"
input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png"
kernel_option:
run_mode: paddle
batch_size: 1
37 changes: 37 additions & 0 deletions paddlex/configs/object_detection/PP-YOLOE-vehicle-L.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,37 @@
Global:
model: PP-YOLOE-vehicle-L
mode: check_dataset # check_dataset/train/evaluate/predict
dataset_dir: "/paddle/dataset/paddlex/det/det_coco_examples"
device: gpu:0,1,2,3
output: "output"

CheckDataset:
convert:
enable: False
src_dataset_type: null
split:
enable: False
train_percent: null
val_percent: null

Train:
num_classes: 4
epochs_iters: 50
batch_size: 2
learning_rate: #0.08
pretrain_weight_path: null
warmup_steps: #100
resume_path: null
log_interval: 10
eval_interval: 1

Evaluate:
weight_path: "output/best_model.pdparams"
log_interval: 10

Predict:
model_dir: "output/best_model"
input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png"
kernel_option:
run_mode: paddle
batch_size: 1
Loading