Add pipeline

pipeline.py

@@ -0,0 +1,64 @@
+# from scipy.special import softmax
+import tensorflow as tf
+
+class PreTrainedPipeline():
+    def __init__(self):
+        sequence_input = tf.keras.Input(shape=(300), name='input')
+        x = tf.keras.layers.Dense(2048, activation="LeakyReLU")(sequence_input)
+        x = tf.keras.layers.Dense(1024, activation="LeakyReLU")(x)
+        x = tf.keras.layers.Dense(512, activation="LeakyReLU")(x)
+        x = tf.keras.layers.Dense(128, activation="LeakyReLU")(x)
+        x = tf.keras.layers.Dense(512, activation="LeakyReLU")(x)
+        x = tf.keras.layers.Dense(1024, activation="LeakyReLU")(x)
+        x = tf.keras.layers.Dense(2048, activation="LeakyReLU")(x)
+        outputs = tf.keras.layers.Dense(300, activation="tanh")(x)
+
+        model = tf.keras.Model(sequence_input, outputs)
+
+        model.compile(optimizer="Adamax", loss="cosine_similarity")
+
+    def __call__(self):
+        return {
+            "text": "Hi!!!"
+        }
+ 
+# def RevDict(sent,flag,model): 
+#     """ 
+#     This function recieves a sentence from the user, and turns back top_10 (for flag=0) or top_100 (for flag=1) predictions. 
+#     the input sentence will be normalized, and stop words will be removed 
+#     """ 
+     
+#     normalizer = Normalizer() 
+#     X_Normalized = normalizer.normalize(sent) 
+#     X_Tokens = word_tokenize(X_Normalized) 
+#     stopwords = [normalizer.normalize(x.strip()) for x in codecs.open(r"stopwords.txt",'r','utf-8').readlines()] 
+#     X_Tokens = [t for t in X_Tokens if t not in stopwords] 
+#     preprocessed = [' '.join(X_Tokens)][0] 
+#     sent_ids = sent2id([preprocessed]) 
+#     output=np.array((model.predict(sent_ids.reshape((1,20))).tolist()[0])) 
+#     distances=distance.cdist(output.reshape((1,300)), comparison_matrix, "cosine")[0] 
+#     min_index_100 = distances.argsort()[:100] 
+#     min_index_10 = distances.argsort()[:10] 
+ 
+#     temp=[] 
+#     if flag == 0: 
+#         for i in range(10): 
+#             temp.append(id2h[str(min_index_10[i])]) 
+#     elif flag == 1: 
+#         for i in range(100): 
+#             temp.append(id2h[str(min_index_100[i])]) 
+     
+#     for i in range(len(temp)): 
+#         print(temp[i])
+
+# def sent2id(sents): 
+#     sents_id=np.zeros((len(sents),20)) 
+#     for j in tqdm(range(len(sents))): 
+#         for i,word in enumerate(sents[j].split()): 
+#             try: 
+#                 sents_id[j,i] = t2id[word] 
+#             except: 
+#                 sents_id[j,i] = t2id['UNK'] 
+#             if i==19: 
+#                 break 
+#     return sents_id