almost done

@@ -12,8 +12,10 @@ import video_util as videoutil
 MODEL_PATH = "/mnt/e/khuhub/2015104192/web/backend/yt8m/esot3ria/model/inference_model/segment_inference_model"
 VOCAB_PATH = "/mnt/e/khuhub/2015104192/web/backend/yt8m/vocabulary.csv"
 VIDEO_TAGS_PATH = "/mnt/e/khuhub/2015104192/web/backend/yt8m/esot3ria/segment_tags.csv"
+VIDEO_IDS_PATH = "/mnt/e/khuhub/2015104192/web/backend/yt8m/esot3ria/videoIds.csv"
 TAG_VECTOR_MODEL_PATH = "/mnt/e/khuhub/2015104192/web/backend/yt8m/esot3ria/tag_vectors.model"
 VIDEO_VECTOR_MODEL_PATH = "/mnt/e/khuhub/2015104192/web/backend/yt8m/esot3ria/video_vectors.model"
+VIDEO_ID_MODEL_PATH = "/mnt/e/khuhub/2015104192/web/backend/yt8m/esot3ria/videoId_vectors.model"
 SEGMENT_LABEL_PATH = "/mnt/e/khuhub/2015104192/web/backend/yt8m/segment_label_ids.csv"
  
 # Define parameters.
@@ -228,8 +230,8 @@ def inference_pb(file_path, threshold):
         
         # 5. Create recommend videos info, Combine results.
         recommend_video_ids = recommender.recommend_videos(tag_result, inputVideoTagResults, TAG_VECTOR_MODEL_PATH,
-                                                           VIDEO_VECTOR_MODEL_PATH, VIDEO_TOP_K)
-        video_result = [videoutil.getVideoInfo(ids, VIDEO_TAGS_PATH, TAG_TOP_K) for ids in recommend_video_ids]
+                                                           VIDEO_VECTOR_MODEL_PATH, VIDEO_ID_MODEL_PATH, VIDEO_TOP_K)
+        video_result = [videoutil.getVideoInfo(ids, VIDEO_TAGS_PATH, TAG_TOP_K,False) for ids in recommend_video_ids]
 
         inference_result = {
             "tag_result": tag_result,

@@ -6,7 +6,7 @@ import pandas as pd
 import math
 import activation as ac
 
-def recommend_videos(tags, segments, tag_model_path, video_model_path, top_k):
+def recommend_videos(tags, segments, tag_model_path, video_model_path, video_id_model, top_k):
     # 이 함수에서 모든걸 다 함
     # tags는 label val 로 묶인 문자열 리스트임
     # tags의 길이는 segment의 길이
@@ -17,11 +17,12 @@ def recommend_videos(tags, segments, tag_model_path, video_model_path, top_k):
     #segments는 클래스 확률 클래스 확률... 일케 저장되어 있음
     tag_vectors = Word2Vec.load(tag_model_path).wv
     video_vectors = Word2Vec().wv.load(video_model_path)
+    video_ids = Word2Vec().wv.load(video_id_model)
     error_tags = []
     maxSimilarSegment = 0
     maxSimilarity = -1
-    
-    kernel = [np.zeros(100) for i in range(0,5)]
+    print('prev len',len(segments))
+    kernel = [np.zeros(100) for i in range(0,9)]
     tagKernel = []
     #우선은 비교를 뜰 입력 영상의 단일 비디오벡터를 구함
     video_vector = np.zeros(100)
@@ -41,27 +42,39 @@ def recommend_videos(tags, segments, tag_model_path, video_model_path, top_k):
                 error_tags.append(tag)
     
     #각 세그먼트마다 비교를 떠서 인덱스를 저장
-    currentIndex = 0
-    for segment in segments:
-        segment_vector = np.zeros(100)
-        segTags = [segment[i] for i in range(0,len(segment),2)]
-        segProbs = [float(segment[i]) for i in range(1,len(segment),2)]#ac.softmax([float(segment[i]) for i in range(1,len(segment),2)])
+    midpos = math.floor(len(kernel)/2)
+    for i in range(0,midpos):
+        segments.insert(0,segments[0])
+        segments.append(segments[len(segments)-1])
         
-        for tag, weight in zip(segTags,segProbs):
-            if tag in tag_vectors.vocab:
-                segment_vector = segment_vector + (tag_vectors[tag] * float(weight))
-            else:
-                # Pass if tag is unknown
-                if tag not in error_tags:
-                    error_tags.append(tag)
-                    
-        #비디오 벡터와 세그먼트 벡터 비교
-        similarity = cos_sim(video_vector, segment_vector) #cos_sim(video_vector, segment_vector)#
+    currentIndex = midpos
+    for si in range(midpos,len(segments) - midpos - 1):
+        similarity = 0        
+        for segi in range(-1,2):
+            segment = segments[si + segi]
+            segment_vector = np.zeros(100)
+            segTags = [segment[i] for i in range(0,len(segment),2)]
+            segProbs = [float(segment[i]) for i in range(1,len(segment),2)]#ac.softmax([float(segment[i]) for i in range(1,len(segment),2)])
+            
+            for tag, weight in zip(segTags,segProbs):
+                if tag in tag_vectors.vocab:
+                    segment_vector = segment_vector + (tag_vectors[tag] * float(weight))
+                else:
+                    # Pass if tag is unknown
+                    if tag not in error_tags:
+                        error_tags.append(tag)
+                        
+            #비디오 벡터와 세그먼트 벡터 비교
+            #similarity = similarity + cos_sim(video_vector, segment_vector) #cos_sim(video_vector, segment_vector)#
 
-        for currentSegmentTag, videoVectorTag in zip(segTags,videoTagList):
-            if(currentSegmentTag in tag_vectors.vocab) and (videoVectorTag in tag_vectors.vocab):
-                similarity = similarity + tag_vectors.similarity(currentSegmentTag,videoVectorTag)
-        
+            for currentSegmentTag, videoVectorTag,videoVectorTagPred in zip(segTags,videoTagList,tag_preds):
+                if(currentSegmentTag in tag_vectors.vocab) and (videoVectorTag in tag_vectors.vocab):
+                    prob = float(videoVectorTagPred)
+                    if videoVectorTag not in segTags:
+                        prob = 0
+                    similarity = similarity + (tag_vectors.similarity(currentSegmentTag,videoVectorTag) * prob)
+                
+                
         if similarity >= maxSimilarity:
             maxSimilarSegment = currentIndex
             maxSimilarity = similarity
@@ -71,7 +84,7 @@ def recommend_videos(tags, segments, tag_model_path, video_model_path, top_k):
                 maxSimilarSegment =  len(segments) - int(len(kernel)/2) - 1
         #세그먼트 인덱스 증가
         currentIndex = currentIndex + 1
-
+    print('maxSimilarSegment',maxSimilarSegment,'len',len(segments))
     #커널 생성    
     for k in range (0,len(kernel)):
         segment = segments[maxSimilarSegment - math.floor(len(kernel)/2) + k]
@@ -139,11 +152,11 @@ def recommend_videos(tags, segments, tag_model_path, video_model_path, top_k):
             tagList.append([row[i].split(":")[0],row[i].split(":")[1]])
         segmentTagList.append(tagList)
     
-    similar_ids = []
-    for i in range(0,top_k):
-        similar_ids.append(minimunVideoIds[i][0])
+    #similar_ids = []
+    #for i in range(0,top_k):
+    #    similar_ids.append(minimunVideoIds[i][0])
       
-    #similar_ids = [x[0] for x in video_vectors.similar_by_vector(video_vector, top_k)]
+    similar_ids = [x[0] for x in video_ids.similar_by_vector(video_vector, top_k)]
     print('results =' ,similar_ids)
     return similar_ids
  
@@ -199,12 +212,14 @@ def differenceMax(arrs, _kernel, w2v, videoTaglist):
         convResult = 0 
         processed_vocabNum = 1
         for i in range(0, s):
-            #if i == midpos:
-            if(_kernel[i][0] not in arrs[j - midpos + i][0:2][0]):# and ((videoTaglist[0] not in arrs[j - midpos + i][0:2])) and ((videoTaglist[1] not in arrs[j - midpos + i][0:5])):
+            if(_kernel[i][0] not in arrs[j - midpos + i][0]):# and ((videoTaglist[0] not in arrs[j - midpos + i][0:2])) and ((videoTaglist[1] not in arrs[j - midpos + i][0:5])):
                 continue
             for ind in range(0,5):
                 if(arrs[j - midpos + i][ind][0] in w2v.vocab) and (_kernel[i][ind] in w2v.vocab):
-                    convResult = convResult + (w2v.similarity(arrs[j - midpos + i][ind][0],_kernel[i][ind]) * float(arrs[j - midpos + i][ind][1]))
+                    prob = float(arrs[j - midpos + i][ind][1])
+                    if arrs[j - midpos + i][ind][0] not in videoTaglist:
+                        prob = 0
+                    convResult = convResult + (w2v.similarity(arrs[j - midpos + i][ind][0],_kernel[i][ind]) * prob)
                     processed_vocabNum = processed_vocabNum + 1
 
         if prevMax < convResult:

@@ -16,7 +16,7 @@ def getURL(vid_id):
 
 print(getURL('nzwW'))
 
-def getVideoInfo(vid_id, video_tags_path, top_k):
+def getVideoInfo(vid_id, video_tags_path, top_k, isPerVideo):
     print("vid_id = ",vid_id)
     video_url = getURL(vid_id[0:4])
 
@@ -31,8 +31,9 @@ def getVideoInfo(vid_id, video_tags_path, top_k):
         if video_url == "":
             for x in video_tags:
                 video_url = video_url + ' ' + x
-                
-    video_url = video_url + '\nThe similar point is : ' + str(float(vid_id[5:]) * 5)
+    
+    if isPerVideo == False:          
+        video_url = video_url + '\nThe similar point is : ' + str(float(vid_id[5:]) * 5)
 
     return {
         "video_url": video_url,

@@ -24,8 +24,8 @@ if __name__ == '__main__':
     video_vectors = Word2Vec().wv   # Empty model
 
     # Load video recommendation tags.
-    video_tags = pd.read_csv('./segment_tags.csv', encoding='utf-8',error_bad_lines=False)
-
+    #video_tags = pd.read_csv('./segment_tags.csv', encoding='utf-8',error_bad_lines=False)
+    video_tags = pd.read_csv('./videoIds.csv', encoding='utf-8',error_bad_lines=False)
     # Define batch variables.
     batch_video_ids = []
     batch_video_vectors = []
@@ -64,7 +64,7 @@ if __name__ == '__main__':
     print(error_tags)
     print(len(error_tags))
 
-    video_vectors.save("video_vectors.model")
+    video_vectors.save("videoId_vectors.model")
 
     # Usage
     # video_vectors = Word2Vec().wv.load("video_vectors.model")

@@ -395,6 +395,197 @@ def inference(reader, train_dir, data_pattern, out_file_location, batch_size,
     coord.join(threads)
     sess.close()
 
+
+def inference2(reader, train_dir, data_pattern, out_file_location, batch_size,
+              top_k):
+  """Inference function."""
+  with tf.Session(config=tf.ConfigProto(
+      allow_soft_placement=True)) as sess, gfile.Open(out_file_location,
+                                                      "w+") as out_file:
+    video_id_batch, video_batch, num_frames_batch = get_input_data_tensors(
+        reader, data_pattern, batch_size)
+    inference_model_name = "segment_inference_model" if FLAGS.segment_labels else "inference_model"
+    checkpoint_file = os.path.join(train_dir, "inference_model",
+                                   inference_model_name)
+    if not gfile.Exists(checkpoint_file + ".meta"):
+      raise IOError("Cannot find %s. Did you run eval.py?" % checkpoint_file)
+    meta_graph_location = checkpoint_file + ".meta"
+    logging.info("loading meta-graph: " + meta_graph_location)
+    if FLAGS.output_model_tgz:
+      with tarfile.open(FLAGS.output_model_tgz, "w:gz") as tar:
+        for model_file in glob.glob(checkpoint_file + ".*"):
+          tar.add(model_file, arcname=os.path.basename(model_file))
+        tar.add(os.path.join(train_dir, "model_flags.json"),
+                arcname="model_flags.json")
+      print("Tarred model onto " + FLAGS.output_model_tgz)
+    with tf.device("/cpu:0"):
+      saver = tf.train.import_meta_graph(meta_graph_location,
+                                         clear_devices=True)
+    logging.info("restoring variables from " + checkpoint_file)
+    saver.restore(sess, checkpoint_file)
+    input_tensor = tf.get_collection("input_batch_raw")[0]
+    num_frames_tensor = tf.get_collection("num_frames")[0]
+    predictions_tensor = tf.get_collection("predictions")[0]
+    # Workaround for num_epochs issue.
+    def set_up_init_ops(variables):
+      init_op_list = []
+      for variable in list(variables):
+        if "train_input" in variable.name:
+          init_op_list.append(tf.assign(variable, 1))
+          variables.remove(variable)
+      init_op_list.append(tf.variables_initializer(variables))
+      return init_op_list
+    sess.run(
+        set_up_init_ops(tf.get_collection_ref(tf.GraphKeys.LOCAL_VARIABLES)))
+    coord = tf.train.Coordinator()
+    threads = tf.train.start_queue_runners(sess=sess, coord=coord)
+    num_examples_processed = 0
+    start_time = time.time()
+    whitelisted_cls_mask = None
+    if FLAGS.segment_labels:
+      final_out_file = out_file
+      out_file = tempfile.NamedTemporaryFile()
+      logging.info(
+          "Segment temp prediction output will be written to temp file: %s",
+          out_file.name)
+      if FLAGS.segment_label_ids_file:
+        whitelisted_cls_mask = np.zeros((predictions_tensor.get_shape()[-1],),
+                                        dtype=np.float32)
+        segment_label_ids_file = FLAGS.segment_label_ids_file
+        if segment_label_ids_file.startswith("http"):
+          logging.info("Retrieving segment ID whitelist files from %s...",
+                       segment_label_ids_file)
+          segment_label_ids_file, _ = urllib.request.urlretrieve(
+              segment_label_ids_file)
+        with tf.io.gfile.GFile(segment_label_ids_file) as fobj:
+          for line in fobj:
+            try:
+              cls_id = int(line)
+              whitelisted_cls_mask[cls_id] = 1.
+            except ValueError:
+              # Simply skip the non-integer line.
+              continue
+    out_file.write(u"VideoId,LabelConfidencePairs\n".encode("utf8"))
+    
+    #=========================================
+    #open vocab csv file and store to dictionary
+    #=========================================
+    voca_dict = {}
+    vocabs = codecs.open('./vocabulary.csv', 'r','utf-8')
+    while True:
+      line = vocabs.readline()
+      if not line: break
+      vocab_dict_item = line.split(",")
+      if vocab_dict_item[0] != "Index":
+        voca_dict[vocab_dict_item[0]] = vocab_dict_item[3]
+    vocabs.close()
+    try:
+      while not coord.should_stop():
+        video_id_batch_val, video_batch_val, num_frames_batch_val = sess.run(
+            [video_id_batch, video_batch, num_frames_batch])
+        if FLAGS.segment_labels:
+          results = get_segments(video_batch_val, num_frames_batch_val, 5)
+          video_segment_ids = results["video_segment_ids"]
+          video_id_batch_val = video_id_batch_val[video_segment_ids[:, 0]]
+          video_id_batch_val = np.array([
+              "%s:%d" % (x.decode("utf8"), y)
+              for x, y in zip(video_id_batch_val, video_segment_ids[:, 1])
+          ])
+          video_batch_val = results["video_batch"]
+          num_frames_batch_val = results["num_frames_batch"]
+          if input_tensor.get_shape()[1] != video_batch_val.shape[1]:
+            raise ValueError("max_frames mismatch. Please re-run the eval.py "
+                             "with correct segment_labels settings.")
+        predictions_val, = sess.run([predictions_tensor],
+                                    feed_dict={
+                                        input_tensor: video_batch_val,
+                                        num_frames_tensor: num_frames_batch_val
+                                    })
+        now = time.time()
+        num_examples_processed += len(video_batch_val)
+        elapsed_time = now - start_time
+        logging.info("num examples processed: " + str(num_examples_processed) +
+                     " elapsed seconds: " + "{0:.2f}".format(elapsed_time) +
+                     " examples/sec: %.2f" %
+                     (num_examples_processed / elapsed_time))
+        for line in format_lines(video_id_batch_val, predictions_val, top_k,
+                                 whitelisted_cls_mask):
+          out_file.write(line)
+        out_file.flush()
+    except tf.errors.OutOfRangeError:
+      logging.info("Done with inference. The output file was written to " +
+                   out_file.name)
+    finally:
+      coord.request_stop()
+      if FLAGS.segment_labels:
+        # Re-read the file and do heap sort.
+        # Create multiple heaps.
+        logging.info("Post-processing segment predictions...")
+        segment_id_list = []
+        segment_classes = []
+        cls_result_arr = []
+        cls_score_dict = {}
+        out_file.seek(0, 0)
+        old_seg_name = '0000'
+        counter = 0
+        for line in out_file:
+          counter += 1
+          if counter / 5000 == 0:
+              print(counter, " processed")
+          segment_id, preds = line.decode("utf8").split(",")
+          if segment_id == "VideoId":
+            # Skip the headline.
+            continue
+          preds = preds.split(" ")
+          pred_cls_ids = [int(preds[idx]) for idx in range(0, len(preds), 2)]
+          pred_cls_scores = [float(preds[idx]) for idx in range(1, len(preds), 2)]
+        #=======================================
+          segment_id = str(segment_id.split(":")[0])
+          if segment_id not in segment_id_list:
+            segment_id_list.append(str(segment_id))
+            segment_classes.append("")
+          index = segment_id_list.index(segment_id)
+          
+          if old_seg_name != segment_id:
+            cls_score_dict[segment_id] = {}
+            old_seg_name = segment_id
+          
+          for classes in range(0,len(pred_cls_ids)):#pred_cls_ids:
+                segment_classes[index] = str(segment_classes[index]) + str(pred_cls_ids[classes]) + " " #append classes from new segment
+                if pred_cls_ids[classes] in cls_score_dict[segment_id]:
+                  cls_score_dict[segment_id][pred_cls_ids[classes]] = cls_score_dict[segment_id][pred_cls_ids[classes]] + pred_cls_scores[classes]
+                else:
+                  cls_score_dict[segment_id][pred_cls_ids[classes]] = pred_cls_scores[classes]
+        for segs,item in zip(segment_id_list,segment_classes):
+          print('====== R E C O R D ======')
+          cls_arr = item.split(" ")[:-1]
+          
+          cls_arr = list(map(int,cls_arr))      
+          cls_arr = sorted(cls_arr) #클래스별로 정렬
+          
+          result_string = ""
+          
+          temp = cls_score_dict[segs]
+          temp= sorted(temp.items(), key=operator.itemgetter(1), reverse=True) #밸류값 기준으로 정렬
+          demoninator = float(temp[0][1] + temp[1][1] + temp[2][1] + temp[3][1] + temp[4][1])
+          #for item in temp: 
+          for itemIndex in range(0, top_k):
+            # Normalize tag name
+            segment_tag = str(voca_dict[str(temp[itemIndex][0])])
+            normalized_tag = normalize_tag(segment_tag)
+            result_string = result_string + normalized_tag + ":" + format(temp[itemIndex][1]/demoninator,".3f") + ","
+          
+          cls_result_arr.append(result_string[:-1])
+          logging.info(segs + " : " + result_string[:-1])
+        #=======================================
+        final_out_file.write("vid_id,segment1,segment2,segment3,segment4,segment5\n")
+        for seg_id, class_indcies in zip(segment_id_list, cls_result_arr):
+          final_out_file.write("%s,%s\n" %(seg_id, str(class_indcies)))
+        final_out_file.close()
+      out_file.close()
+    coord.join(threads)
+    sess.close()
+
 def main(unused_argv):
   logging.set_verbosity(tf.logging.INFO)
   if FLAGS.input_model_tgz:
@@ -431,7 +622,7 @@ def main(unused_argv):
     raise ValueError("'input_data_pattern' was not specified. "
                      "Unable to continue with inference.")
 
-  inference(reader, FLAGS.train_dir, FLAGS.input_data_pattern,
+  inference2(reader, FLAGS.train_dir, FLAGS.input_data_pattern,
             FLAGS.output_file, FLAGS.batch_size, FLAGS.top_k)
 
 def normalize(arrs):    
@@ -443,3 +634,4 @@ def normalize(arrs):
 
 if __name__ == "__main__":
   app.run()
+