Update app.py

app.py

@@ -425,10 +425,10 @@ def draw_boxes(image, bounds, color='yellow', width=2):
 def inference(img, lang):
     reader = easyocr.Reader(lang)
     bounds = reader.readtext(img.name)
-    im = PIL.Image.open(img.name)
-    draw_boxes(im, bounds)
-    im.save('result.jpg')
-    return ['result.jpg', pd.DataFrame(bounds).iloc[: , 1:]]
+    #im = PIL.Image.open(img.name)
+    #draw_boxes(im, bounds)
+    #im.save('result.jpg')
+    return [pd.DataFrame(bounds).iloc[: , 1:]]
 
 def compute_tfidf_embeddings(documents1, documents2):
     # Combine both lists of words into a single list
@@ -449,22 +449,27 @@ def compute_tfidf_embeddings(documents1, documents2):
 import requests
 import base64
 def extract_eval(image1,image2,image3,image4):
-    print(image1)
-    ideal_text=extract(image1)
-    print("Extracting Ideal Text \n")
-    print(ideal_text)
-    submitted_text=extract(image3)
-    print("Extracting Submitted Text \n")
-    print(submitted_text)
-    a,b=sim(ideal_text,submitted_text)
-    print(a)
-    text_sim_score=b
+    # print(image1)
+    # ideal_text=extract(image1)
+    # print("Extracting Ideal Text \n")
+    # print(ideal_text)
+    # submitted_text=extract(image3)
+    # print("Extracting Submitted Text \n")
+    # print(submitted_text)
+    # a,b=sim(ideal_text,submitted_text)
+    # print(a)
+    # text_sim_score=b
     model = ResNet50(include_top=False, weights='imagenet', pooling='avg')
     diagram_1_embed=return_image_embedding(model,image2)
     diagram_2_embed=return_image_embedding(model,image4)
-    diagram_embed_sim_score=util.pytorch_cos_sim(embedding_1, embedding_2)
+    diagram_embed_sim_score=util.pytorch_cos_sim(diagram_1_embed, diagram_2_embed)
     print("Diagram Embedding Similarity Score \n")
     print(diagram_embed_sim_score)
+    diagram_1_text=inference(image2,'en')
+    diagram_2_text=inference(image4,'en')
+    print(diagram_1_text)
+    print(diagram_2_text)
+