PramaLLC
/

BEN2

Image Segmentation

background-remove

mask-generation

Dichotomous image segmentation

background remove

remove background

model_hub_mixin

pytorch_model_hub_mixin

background removal

background-removal

Model card Files Files and versions

MaxwellMeyer commited on Jan 29, 2025

Commit

d8358da

·

verified ·

1 Parent(s): 764ae38

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -51,7 +51,7 @@ file = "./image.png" # input image
 model = model.BEN_Base().to(device).eval() #init pipeline
-model.loadcheckpoints("./BEN_Base2.pth")
 image = Image.open(file)
 foreground = model.inference(image, refine_foreground=False,) #Refine foreground is an extract postprocessing step that increases inference time but can improve matting edges. The default value is False.
@@ -74,7 +74,7 @@ device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 model = model.BEN_Base().to(device).eval() #init pipeline
-model.loadcheckpoints("./BEN_Base2.pth")
 file1 = "./image1.png" # input image1
 file2 = "./image2.png" # input image2
@@ -113,7 +113,7 @@ file = "./image.png" # input image
 model = model.BEN_Base().to(device).eval() #init pipeline
-model.loadcheckpoints("./BEN_Base2.pth")

 model = model.BEN_Base().to(device).eval() #init pipeline
+model.loadcheckpoints("./BEN2_Base.pth")
 image = Image.open(file)
 foreground = model.inference(image, refine_foreground=False,) #Refine foreground is an extract postprocessing step that increases inference time but can improve matting edges. The default value is False.
 model = model.BEN_Base().to(device).eval() #init pipeline
+model.loadcheckpoints("./BEN2_Base.pth")
 file1 = "./image1.png" # input image1
 file2 = "./image2.png" # input image2
 model = model.BEN_Base().to(device).eval() #init pipeline
+model.loadcheckpoints("./BEN2_Base.pth")