Update app.py

app.py

@@ -29,8 +29,8 @@ HF_TOKEN = os.environ.get("HF_TOKEN")
 DATASET_REPO_URL = "https://huggingface.co/datasets/pragnakalp/OCR-img-to-text"
 DATA_FILENAME = "ocr_data.csv"
 DATA_FILE = os.path.join("ocr_data", DATA_FILENAME)
-# DATA_FILENAME2 = "ocr_image"
-# DATA_FILE2 = os.mkdir("ocr_data")
+DATA_FILENAME2 = "ocr_image.csv"
+DATA_FILE2 = os.path.join("ocr_image", DATA_FILENAME2)
 HF_TOKEN = os.environ.get("HF_TOKEN")
 DATASET_REPO_ID = "pragnakalp/OCR-img-to-text"
 print("is none?", HF_TOKEN is None)
@@ -117,6 +117,23 @@ def ocr_with_easy(img):
     bounds = reader.readtext('image.png',paragraph="False",detail = 0)
     bounds = ''.join(bounds)
     return bounds
+
+# def store_single_disk(image, image_id, label):
+#     """ Stores a single image as a .png file on disk.
+#         Parameters:
+#         ---------------
+#         image       image array, (32, 32, 3) to be stored
+#         image_id    integer unique ID for image
+#         label       image label
+#     """
+#     Image.fromarray(image).save(disk_dir / f"{image_id}.png")
+
+#     with open(disk_dir / f"{image_id}.csv", "wt") as csvfile:
+#         writer = csv.writer(
+#             csvfile, delimiter=" ", quotechar="|", quoting=csv.QUOTE_MINIMAL
+#         )
+#         writer.writerow([label])
+        
 """
 Generate OCR
 """
@@ -124,7 +141,7 @@ def generate_ocr(Method,img):
     try:
         text_output = ''
         add_csv = []
-        print(img)
+        image_id = 1
         print("Method___________________",Method)
         if Method == 'EasyOCR':
             text_output = ocr_with_easy(img)
@@ -143,6 +160,15 @@ def generate_ocr(Method,img):
             writer.writerow(add_csv)
             commit_url = repo.push_to_hub()
             print(commit_url)
+
+        
+        Image.fromarray(image).save(DATA_FILE2 / f"{image_id}.png")
+        with open(DATA_FILE2, "wt") as csvfile:
+            writer = csv.writer(
+                csvfile, delimiter=" ", quotechar="|", quoting=csv.QUOTE_MINIMAL
+            )
+            writer.writerow([0])
+            
         # try:
         #     dataset = load_dataset("pragnakalp/OCR-img-to-text", streaming=True)
         #     print(dataset.features)