comment batch generating

ocr.py

@@ -5,7 +5,7 @@ from PIL import Image, ImageDraw
 from transformers import AutoProcessor, Kosmos2_5ForConditionalGeneration
 
 repo = "microsoft/kosmos-2.5"
-device = "cuda:1"
+device = "cuda:0"
 dtype = torch.bfloat16
 model = Kosmos2_5ForConditionalGeneration.from_pretrained(repo, device_map=device, torch_dtype=dtype)
 processor = AutoProcessor.from_pretrained(repo)
@@ -22,12 +22,12 @@ raw_width, raw_height = image.size
 scale_height = raw_height / height
 scale_width = raw_width / width
 
-# bs > 1, batch decoding sample
-inputs = processor(text=[prompt, prompt], images=[image,image], return_tensors="pt")
-height, width = inputs.pop("height"), inputs.pop("width")
-raw_width, raw_height = image.size
-scale_height = raw_height / height[0]
-scale_width = raw_width / width[0]
+# bs > 1, batch generation
+# inputs = processor(text=[prompt, prompt], images=[image,image], return_tensors="pt")
+# height, width = inputs.pop("height"), inputs.pop("width")
+# raw_width, raw_height = image.size
+# scale_height = raw_height / height[0]
+# scale_width = raw_width / width[0]
 
 inputs = {k: v.to(device) if v is not None else None for k, v in inputs.items()}
 inputs["flattened_patches"] = inputs["flattened_patches"].to(dtype)