Image Slicer¶
v2¶
Class: ImageSlicerBlockV2
(there are multiple versions of this block)
Source: inference.core.workflows.core_steps.transformations.image_slicer.v2.ImageSlicerBlockV2
Warning: This block has multiple versions. Please refer to the specific version for details. You can learn more about how versions work here: Versioning
This block enables Slicing Adaptive Inference (SAHI) technique in Workflows providing implementation for first step of procedure - making slices out of input image.
To use the block effectively, it must be paired with detection model (object-detection or instance segmentation) running against output images from this block. At the end - Detections Stitch block must be applied on top of predictions to merge them as if the prediction was made against input image, not its slices.
We recommend adjusting the size of slices to match the model's input size and the scale of objects in the dataset the model was trained on. Models generally perform best on data that is similar to what they encountered during training. The default size of slices is 640, but this might not be optimal if the model's input size is 320, as each slice would be downsized by a factor of two during inference. Similarly, if the model's input size is 1280, each slice will be artificially up-scaled. The best setup should be determined experimentally based on the specific data and model you are using.
To learn more about SAHI please visit Roboflow blog which describes the technique in details, yet not in context of Roboflow workflows.
Changes compared to v1¶
-
All crops generated by slicer will be of equal size
-
No duplicated crops will be created
Type identifier¶
Use the following identifier in step "type"
field: roboflow_core/image_slicer@v2
to add the block as
as step in your workflow.
Properties¶
Name | Type | Description | Refs |
---|---|---|---|
name |
str |
Enter a unique identifier for this step.. | ❌ |
slice_width |
int |
Width of each slice, in pixels. | ✅ |
slice_height |
int |
Height of each slice, in pixels. | ✅ |
overlap_ratio_width |
float |
Overlap ratio between consecutive slices in the width dimension. | ✅ |
overlap_ratio_height |
float |
Overlap ratio between consecutive slices in the height dimension. | ✅ |
The Refs column marks possibility to parametrise the property with dynamic values available
in workflow
runtime. See Bindings for more info.
Available Connections¶
Compatible Blocks
Check what blocks you can connect to Image Slicer
in version v2
.
- inputs:
Depth Estimation
,Classification Label Visualization
,Stability AI Image Generation
,Camera Calibration
,Ellipse Visualization
,SIFT
,Blur Visualization
,Circle Visualization
,Dot Visualization
,Image Blur
,Clip Comparison
,Background Color Visualization
,Line Counter
,Stitch Images
,Image Slicer
,Absolute Static Crop
,Distance Measurement
,SIFT Comparison
,Color Visualization
,Pixelate Visualization
,Identify Outliers
,Label Visualization
,Stability AI Inpainting
,Polygon Zone Visualization
,Relative Static Crop
,Keypoint Visualization
,Bounding Box Visualization
,Template Matching
,Mask Visualization
,Model Comparison Visualization
,Pixel Color Count
,Image Preprocessing
,Line Counter Visualization
,Detections Consensus
,Grid Visualization
,SIFT Comparison
,Image Convert Grayscale
,Halo Visualization
,Trace Visualization
,Corner Visualization
,Polygon Visualization
,Triangle Visualization
,Image Contours
,Perspective Correction
,Dynamic Crop
,Crop Visualization
,Camera Focus
,Reference Path Visualization
,Identify Changes
,Image Slicer
,Line Counter
,Image Threshold
- outputs:
LMM
,Depth Estimation
,Classification Label Visualization
,Camera Calibration
,LMM For Classification
,Clip Comparison
,Instance Segmentation Model
,Stitch Images
,CogVLM
,Image Slicer
,Roboflow Dataset Upload
,Absolute Static Crop
,Multi-Label Classification Model
,Object Detection Model
,Florence-2 Model
,QR Code Detection
,OpenAI
,Label Visualization
,Single-Label Classification Model
,Qwen2.5-VL
,Roboflow Dataset Upload
,Detections Stitch
,Bounding Box Visualization
,Llama 3.2 Vision
,Model Comparison Visualization
,Pixel Color Count
,Object Detection Model
,VLM as Classifier
,Moondream2
,Image Convert Grayscale
,Halo Visualization
,Buffer
,Triangle Visualization
,Time in Zone
,Keypoint Detection Model
,Reference Path Visualization
,Perspective Correction
,Dynamic Crop
,Camera Focus
,VLM as Detector
,Florence-2 Model
,OpenAI
,Google Vision OCR
,VLM as Detector
,Stability AI Image Generation
,Ellipse Visualization
,SIFT
,Blur Visualization
,Circle Visualization
,Image Blur
,Dot Visualization
,CLIP Embedding Model
,Background Color Visualization
,Gaze Detection
,Multi-Label Classification Model
,Single-Label Classification Model
,Byte Tracker
,Color Visualization
,Pixelate Visualization
,Dominant Color
,Clip Comparison
,Google Gemini
,Keypoint Detection Model
,Stability AI Inpainting
,VLM as Classifier
,Polygon Zone Visualization
,Relative Static Crop
,Detections Stabilizer
,OCR Model
,Keypoint Visualization
,Template Matching
,Mask Visualization
,SmolVLM2
,Image Preprocessing
,Line Counter Visualization
,Anthropic Claude
,SIFT Comparison
,YOLO-World Model
,Trace Visualization
,Instance Segmentation Model
,Corner Visualization
,Polygon Visualization
,Segment Anything 2 Model
,Barcode Detection
,Crop Visualization
,Image Contours
,Image Slicer
,Image Threshold
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Image Slicer
in version v2
has.
Bindings
-
input
image
(image
): The input image for this step..slice_width
(integer
): Width of each slice, in pixels.slice_height
(integer
): Height of each slice, in pixels.overlap_ratio_width
(float_zero_to_one
): Overlap ratio between consecutive slices in the width dimension.overlap_ratio_height
(float_zero_to_one
): Overlap ratio between consecutive slices in the height dimension.
-
output
slices
(image
): Image in workflows.
Example JSON definition of step Image Slicer
in version v2
{
"name": "<your_step_name_here>",
"type": "roboflow_core/image_slicer@v2",
"image": "$inputs.image",
"slice_width": 320,
"slice_height": 320,
"overlap_ratio_width": 0.2,
"overlap_ratio_height": 0.2
}
v1¶
Class: ImageSlicerBlockV1
(there are multiple versions of this block)
Source: inference.core.workflows.core_steps.transformations.image_slicer.v1.ImageSlicerBlockV1
Warning: This block has multiple versions. Please refer to the specific version for details. You can learn more about how versions work here: Versioning
This block enables Slicing Adaptive Inference (SAHI) technique in Workflows providing implementation for first step of procedure - making slices out of input image.
To use the block effectively, it must be paired with detection model (object-detection or instance segmentation) running against output images from this block. At the end - Detections Stitch block must be applied on top of predictions to merge them as if the prediction was made against input image, not its slices.
We recommend adjusting the size of slices to match the model's input size and the scale of objects in the dataset the model was trained on. Models generally perform best on data that is similar to what they encountered during training. The default size of slices is 640, but this might not be optimal if the model's input size is 320, as each slice would be downsized by a factor of two during inference. Similarly, if the model's input size is 1280, each slice will be artificially up-scaled. The best setup should be determined experimentally based on the specific data and model you are using.
To learn more about SAHI please visit Roboflow blog which describes the technique in details, yet not in context of Roboflow workflows.
Type identifier¶
Use the following identifier in step "type"
field: roboflow_core/image_slicer@v1
to add the block as
as step in your workflow.
Properties¶
Name | Type | Description | Refs |
---|---|---|---|
name |
str |
Enter a unique identifier for this step.. | ❌ |
slice_width |
int |
Width of each slice, in pixels. | ✅ |
slice_height |
int |
Height of each slice, in pixels. | ✅ |
overlap_ratio_width |
float |
Overlap ratio between consecutive slices in the width dimension. | ✅ |
overlap_ratio_height |
float |
Overlap ratio between consecutive slices in the height dimension. | ✅ |
The Refs column marks possibility to parametrise the property with dynamic values available
in workflow
runtime. See Bindings for more info.
Available Connections¶
Compatible Blocks
Check what blocks you can connect to Image Slicer
in version v1
.
- inputs:
Depth Estimation
,Classification Label Visualization
,Stability AI Image Generation
,Camera Calibration
,Ellipse Visualization
,SIFT
,Blur Visualization
,Circle Visualization
,Dot Visualization
,Image Blur
,Clip Comparison
,Background Color Visualization
,Line Counter
,Stitch Images
,Image Slicer
,Absolute Static Crop
,Distance Measurement
,SIFT Comparison
,Color Visualization
,Pixelate Visualization
,Identify Outliers
,Label Visualization
,Stability AI Inpainting
,Polygon Zone Visualization
,Relative Static Crop
,Keypoint Visualization
,Bounding Box Visualization
,Template Matching
,Mask Visualization
,Model Comparison Visualization
,Pixel Color Count
,Image Preprocessing
,Line Counter Visualization
,Detections Consensus
,Grid Visualization
,SIFT Comparison
,Image Convert Grayscale
,Halo Visualization
,Trace Visualization
,Corner Visualization
,Polygon Visualization
,Triangle Visualization
,Image Contours
,Perspective Correction
,Dynamic Crop
,Crop Visualization
,Camera Focus
,Reference Path Visualization
,Identify Changes
,Image Slicer
,Line Counter
,Image Threshold
- outputs:
LMM
,Depth Estimation
,Classification Label Visualization
,Camera Calibration
,LMM For Classification
,Clip Comparison
,Instance Segmentation Model
,Stitch Images
,CogVLM
,Image Slicer
,Roboflow Dataset Upload
,Absolute Static Crop
,Multi-Label Classification Model
,Object Detection Model
,Florence-2 Model
,QR Code Detection
,OpenAI
,Label Visualization
,Single-Label Classification Model
,Qwen2.5-VL
,Roboflow Dataset Upload
,Detections Stitch
,Bounding Box Visualization
,Llama 3.2 Vision
,Model Comparison Visualization
,Pixel Color Count
,Object Detection Model
,VLM as Classifier
,Moondream2
,Image Convert Grayscale
,Halo Visualization
,Buffer
,Triangle Visualization
,Time in Zone
,Keypoint Detection Model
,Reference Path Visualization
,Perspective Correction
,Dynamic Crop
,Camera Focus
,VLM as Detector
,Florence-2 Model
,OpenAI
,Google Vision OCR
,VLM as Detector
,Stability AI Image Generation
,Ellipse Visualization
,SIFT
,Blur Visualization
,Circle Visualization
,Image Blur
,Dot Visualization
,CLIP Embedding Model
,Background Color Visualization
,Gaze Detection
,Multi-Label Classification Model
,Single-Label Classification Model
,Byte Tracker
,Color Visualization
,Pixelate Visualization
,Dominant Color
,Clip Comparison
,Google Gemini
,Keypoint Detection Model
,Stability AI Inpainting
,VLM as Classifier
,Polygon Zone Visualization
,Relative Static Crop
,Detections Stabilizer
,OCR Model
,Keypoint Visualization
,Template Matching
,Mask Visualization
,SmolVLM2
,Image Preprocessing
,Line Counter Visualization
,Anthropic Claude
,SIFT Comparison
,YOLO-World Model
,Trace Visualization
,Instance Segmentation Model
,Corner Visualization
,Polygon Visualization
,Segment Anything 2 Model
,Barcode Detection
,Crop Visualization
,Image Contours
,Image Slicer
,Image Threshold
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Image Slicer
in version v1
has.
Bindings
-
input
image
(image
): The input image for this step..slice_width
(integer
): Width of each slice, in pixels.slice_height
(integer
): Height of each slice, in pixels.overlap_ratio_width
(float_zero_to_one
): Overlap ratio between consecutive slices in the width dimension.overlap_ratio_height
(float_zero_to_one
): Overlap ratio between consecutive slices in the height dimension.
-
output
slices
(image
): Image in workflows.
Example JSON definition of step Image Slicer
in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/image_slicer@v1",
"image": "$inputs.image",
"slice_width": 320,
"slice_height": 320,
"overlap_ratio_width": 0.2,
"overlap_ratio_height": 0.2
}