Update files/functions.py

files/functions.py

@@ -50,6 +50,26 @@ print(os.popen(f'cat /etc/issue').read())
 print(os.popen(f'apt search tesseract').read())
 import pytesseract
 
+## model / feature extractor / tokenizer
+
+from transformers import LayoutLMv2ForTokenClassification # LayoutXLMTokenizerFast, 
+
+import torch
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# model
+# tokenizer = LayoutXLMTokenizerFast.from_pretrained(model_id)
+model = LayoutLMv2ForTokenClassification.from_pretrained(model_id);
+model.to(device);
+
+# feature extractor
+from transformers import LayoutLMv2FeatureExtractor
+feature_extractor = LayoutLMv2FeatureExtractor(apply_ocr=False)
+
+# tokenizer
+from transformers import AutoTokenizer
+tokenizer = AutoTokenizer.from_pretrained(tokenizer_id)
+
 ## Key parameters
 
 # categories colors
@@ -231,8 +251,8 @@ def set_image_dpi_resize(image):
     length_x, width_y = image.size
     factor = min(1, float(1024.0 / length_x))
     size = int(factor * length_x), int(factor * width_y)
-    image_resize = image.resize(size, Image.Resampling.LANCZOS)
-    # image_resize = image.resize(size, Image.LANCZOS)
+    # image_resize = image.resize(size, Image.Resampling.LANCZOS)
+    image_resize = image.resize(size, Image.LANCZOS)
     temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='1.png')
     temp_filename = temp_file.name
     image_resize.save(temp_filename, dpi=(300, 300))