Update app.py

app.py

@@ -10,27 +10,35 @@ import pandas as pd
 import pickle
 import pickletools
 from transformers import AutoTokenizer, CLIPTextModelWithProjection
+from sklearn.preprocessing import normalize, OneHotEncoder
 
 # loading the train dataset
-# with open('clip_train.pkl', 'rb') as f: 
-#     temp_d = pickletools.dis(f)
+with open('clip_train.pkl', 'rb') as f: 
+    temp_d = pickle.load(f)
     # train_xv = temp_d['image'].astype(np.float64)   # Array of image features : np ndarray
     # train_xt = temp_d['text'].astype(np.float64)    # Array of text features : np ndarray
     # train_yv  = temp_d['label']                     # Array of labels 
-    # train_yt  = temp_d['label']                     # Array of labels 
+    train_yt  = temp_d['label']                     # Array of labels 
     # ids = list(temp_d['ids'])                       # image names == len(images)
 
-train_yt = np.load("train_yt.npy")
+# train_yt = np.load("train_yt.npy")
 
 # loading the test dataset
-# with open('clip_test.pkl', 'rb') as f:
-    # temp_d = pickletools.dis(f)
+with open('clip_test.pkl', 'rb') as f:
+    temp_d = pickle.load(f)
     # test_xv = temp_d['image'].astype(np.float64)
     # test_xt = temp_d['text'].astype(np.float64)
     # test_yv = temp_d['label']
-    # test_yt = temp_d['label']
+    test_yt = temp_d['label']
 
-test_xt = np.load("test_xt.npy")
+# test_xt = np.load("test_xt.npy")
+
+enc = OneHotEncoder(sparse=False)
+enc.fit(np.concatenate((train_yt, test_yt)).reshape((-1, 1)))
+# train_yv = enc.transform(self.train_yv.reshape((-1, 1))).astype(np.float64)
+# test_yv = enc.transform(self.test_yv.reshape((-1, 1))).astype(np.float64)
+# train_yt = enc.transform(self.train_yt.reshape((-1, 1))).astype(np.float64)
+test_yt = enc.transform(self.test_yt.reshape((-1, 1))).astype(np.float64)
 
 # Map the image ids to the corresponding image URLs
 image_map_name = 'pascal_dataset.csv'