Update 3.2_yolov4tiny_from_colab.py

Ildaron · web-flow · commit a745d7d2a6e8 · 2021-10-08T09:23:18.000+09:00
diff --git a/3.YoloV4/3.2_yolov4tiny_from_colab.py b/3.YoloV4/3.2_yolov4tiny_from_colab.py
@@ -15,9 +15,6 @@
 
 
 
-#---------------------------------------------------#
-#   获得类和先验框
-#---------------------------------------------------#
 def get_classes(classes_path):
     '''loads the classes'''
     with open(classes_path) as f:
@@ -32,9 +29,7 @@ def get_anchors(anchors_path):
     anchors = [float(x) for x in anchors.split(',')]
     return np.array(anchors).reshape(-1, 2)
 
-#---------------------------------------------------#
-#   训练数据生成器
-#---------------------------------------------------#
+
 def data_generator(annotation_lines, batch_size, input_shape, anchors, num_classes, mosaic=False, random=True):
     n = len(annotation_lines)
     i = 0
@@ -63,75 +58,49 @@ def data_generator(annotation_lines, batch_size, input_shape, anchors, num_class
         y_true = preprocess_true_boxes(box_data, input_shape, anchors, num_classes)
         yield [image_data, *y_true], np.zeros(batch_size)
 
-#---------------------------------------------------#
-#   读入xml文件，并输出y_true
-#---------------------------------------------------#
+
 def preprocess_true_boxes(true_boxes, input_shape, anchors, num_classes):
     assert (true_boxes[..., 4]<num_classes).all(), 'class id must be less than num_classes'
-    # 一共有两个特征层数
+
     num_layers = len(anchors)//3
-    #-----------------------------------------------------------#
-    #   13x13的特征层对应的anchor是[81,82], [135,169], [344,319]
-    #   26x26的特征层对应的anchor是[23,27], [37,58], [81,82]
-    #-----------------------------------------------------------#
+
     anchor_mask = [[6,7,8], [3,4,5], [0,1,2]] if num_layers==3 else [[3,4,5], [1,2,3]]
 
-    #-----------------------------------------------------------#
-    #   获得框的坐标和图片的大小
-    #-----------------------------------------------------------#
+
     true_boxes = np.array(true_boxes, dtype='float32')
     input_shape = np.array(input_shape, dtype='int32') 
-    #-----------------------------------------------------------#
-    #   通过计算获得真实框的中心和宽高
-    #   中心点(m,n,2) 宽高(m,n,2)
-    #-----------------------------------------------------------#
+
     boxes_xy = (true_boxes[..., 0:2] + true_boxes[..., 2:4]) // 2
     boxes_wh = true_boxes[..., 2:4] - true_boxes[..., 0:2]
-    #-----------------------------------------------------------#
-    #   将真实框归一化到小数形式
-    #-----------------------------------------------------------#
+
     true_boxes[..., 0:2] = boxes_xy/input_shape[::-1]
     true_boxes[..., 2:4] = boxes_wh/input_shape[::-1]
 
-    # m为图片数量，grid_shapes为网格的shape
+
     m = true_boxes.shape[0]
     grid_shapes = [input_shape//{0:32, 1:16, 2:8}[l] for l in range(num_layers)]
-    #-----------------------------------------------------------#
-    #   y_true的格式为(m,13,13,3,85)(m,26,26,3,85)(m,52,52,3,85)
-    #-----------------------------------------------------------#
+
     y_true = [np.zeros((m,grid_shapes[l][0],grid_shapes[l][1],len(anchor_mask[l]),5+num_classes),
         dtype='float32') for l in range(num_layers)]
 
-    #-----------------------------------------------------------#
-    #   [6,2] -> [1,6,2]
-    #-----------------------------------------------------------#
+
     anchors = np.expand_dims(anchors, 0)
     anchor_maxes = anchors / 2.
     anchor_mins = -anchor_maxes
 
-    #-----------------------------------------------------------#
-    #   长宽要大于0才有效
-    #-----------------------------------------------------------#
+
     valid_mask = boxes_wh[..., 0]>0
 
     for b in range(m):
-        # 对每一张图进行处理
+       
         wh = boxes_wh[b, valid_mask[b]]
         if len(wh)==0: continue
-        #-----------------------------------------------------------#
-        #   [n,2] -> [n,1,2]
-        #-----------------------------------------------------------#
+
         wh = np.expand_dims(wh, -2)
         box_maxes = wh / 2.
         box_mins = -box_maxes
 
-        #-----------------------------------------------------------#
-        #   计算所有真实框和先验框的交并比
-        #   intersect_area  [n,6]
-        #   box_area        [n,1]
-        #   anchor_area     [1,6]
-        #   iou             [n,6]
-        #-----------------------------------------------------------#
+
         intersect_mins = np.maximum(box_mins, anchor_mins)
         intersect_maxes = np.minimum(box_maxes, anchor_maxes)
         intersect_wh = np.maximum(intersect_maxes - intersect_mins, 0.)
@@ -141,141 +110,76 @@ def preprocess_true_boxes(true_boxes, input_shape, anchors, num_classes):
         anchor_area = anchors[..., 0] * anchors[..., 1]
 
         iou = intersect_area / (box_area + anchor_area - intersect_area)
-        #-----------------------------------------------------------#
-        #   维度是[n,] 感谢 消尽不死鸟 的提醒
-        #-----------------------------------------------------------#
+
         best_anchor = np.argmax(iou, axis=-1)
 
         for t, n in enumerate(best_anchor):
-            #-----------------------------------------------------------#
-            #   找到每个真实框所属的特征层
-            #-----------------------------------------------------------#
+
             for l in range(num_layers):
                 if n in anchor_mask[l]:
-                    #-----------------------------------------------------------#
-                    #   floor用于向下取整，找到真实框所属的特征层对应的x、y轴坐标
-                    #-----------------------------------------------------------#
+
                     i = np.floor(true_boxes[b,t,0] * grid_shapes[l][1]).astype('int32')
                     j = np.floor(true_boxes[b,t,1] * grid_shapes[l][0]).astype('int32')
-                    #-----------------------------------------------------------#
-                    #   k指的的当前这个特征点的第k个先验框
-                    #-----------------------------------------------------------#
+
                     k = anchor_mask[l].index(n)
-                    #-----------------------------------------------------------#
-                    #   c指的是当前这个真实框的种类
-                    #-----------------------------------------------------------#
+
                     c = true_boxes[b, t, 4].astype('int32')
-                    #-----------------------------------------------------------#
-                    #   y_true的shape为(m,13,13,3,85)(m,26,26,3,85)(m,52,52,3,85)
-                    #   最后的85可以拆分成4+1+80，4代表的是框的中心与宽高、
-                    #   1代表的是置信度、80代表的是种类
-                    #-----------------------------------------------------------#
+
                     y_true[l][b, j, i, k, 0:4] = true_boxes[b, t, 0:4]
                     y_true[l][b, j, i, k, 4] = 1
                     y_true[l][b, j, i, k, 5+c] = 1
 
     return y_true
 
-#----------------------------------------------------#
-#   检测精度mAP和pr曲线计算参考视频
-#   https://www.bilibili.com/video/BV1zE411u7Vw
-#----------------------------------------------------#
+
 if __name__ == "__main__":
-    #----------------------------------------------------#
-    #   获得图片路径和标签
-    #----------------------------------------------------#
+
     annotation_path = '/content/drive/MyDrive/yolov4_tiny/yolov4-tiny-keras-master/new_train.txt'
-    #------------------------------------------------------#
-    #   训练后的模型保存的位置，保存在logs文件夹里面
-    #------------------------------------------------------#
+
     log_dir = 'logs/'
-    #----------------------------------------------------#
-    #   classes和anchor的路径，非常重要
-    #   训练前一定要修改classes_path，使其对应自己的数据集
-    #----------------------------------------------------#
+
     classes_path = '/content/drive/MyDrive/yolov4_tiny/yolov4-tiny-keras-master/voc_classes.txt'    
     anchors_path = '/content/drive/MyDrive/yolov4_tiny/yolov4-tiny-keras-master/yolo_anchors.txt'
-    #------------------------------------------------------#
-    #   权值文件请看README，百度网盘下载
-    #   训练自己的数据集时提示维度不匹配正常
-    #   预测的东西都不一样了自然维度不匹配
-    #------------------------------------------------------#
+
     weights_path = '/content/drive/MyDrive/yolov4_tiny/yolov4-tiny-keras-master/yolov4_tiny_weights_voc.h5'
-    #------------------------------------------------------#
-    #   训练用图片大小
-    #   一般在416x416和608x608选择
-    #------------------------------------------------------#
+
     input_shape = (416,416)
-    #------------------------------------------------------#
-    #   是否对损失进行归一化，用于改变loss的大小
-    #   用于决定计算最终loss是除上batch_size还是除上正样本数量
-    #------------------------------------------------------#
+
     normalize = False
 
-    #----------------------------------------------------#
-    #   获取classes和anchor
-    #----------------------------------------------------#
     class_names = get_classes(classes_path)
     anchors = get_anchors(anchors_path)
-    #------------------------------------------------------#
-    #   一共有多少类和多少先验框
-    #------------------------------------------------------#
     num_classes = len(class_names)
     num_anchors = len(anchors)
-    #------------------------------------------------------#
-    #   Yolov4的tricks应用
-    #   mosaic 马赛克数据增强 True or False 
-    #   实际测试时mosaic数据增强并不稳定，所以默认为False
-    #   Cosine_scheduler 余弦退火学习率 True or False
-    #   label_smoothing 标签平滑 0.01以下一般 如0.01、0.005
-    #------------------------------------------------------#
     mosaic = False
     Cosine_scheduler = False
     label_smoothing = 0
 
     K.clear_session()
-    #------------------------------------------------------#
-    #   创建yolo模型
-    #------------------------------------------------------#
+
     image_input = Input(shape=(None, None, 3))
     h, w = input_shape
     print('Create YOLOv4-Tiny model with {} anchors and {} classes.'.format(num_anchors, num_classes))
     model_body = yolo_body(image_input, num_anchors//2, num_classes)
     
-    #------------------------------------------------------#
-    #   载入预训练权重
-    #------------------------------------------------------#
+
     print('Load weights {}.'.format(weights_path))
     model_body.load_weights(weights_path, by_name=True, skip_mismatch=True)
     
-    #------------------------------------------------------#
-    #   在这个地方设置损失，将网络的输出结果传入loss函数
-    #   把整个模型的输出作为loss
-    #------------------------------------------------------#
     y_true = [Input(shape=(h//{0:32, 1:16}[l], w//{0:32, 1:16}[l], num_anchors//2, num_classes+5)) for l in range(2)]
     loss_input = [*model_body.output, *y_true]
     model_loss = Lambda(yolo_loss, output_shape=(1,), name='yolo_loss',
         arguments={'anchors': anchors, 'num_classes': num_classes, 'ignore_thresh': 0.5, 'label_smoothing': label_smoothing, 'normalize':normalize})(loss_input)
 
     model = Model([model_body.input, *y_true], model_loss)
 
-    #-------------------------------------------------------------------------------#
-    #   训练参数的设置
-    #   logging表示tensorboard的保存地址
-    #   checkpoint用于设置权值保存的细节，period用于修改多少epoch保存一次
-    #   reduce_lr用于设置学习率下降的方式
-    #   early_stopping用于设定早停，val_loss多次不下降自动结束训练，表示模型基本收敛
-    #-------------------------------------------------------------------------------#
+
     logging = TensorBoard(log_dir=log_dir)
     checkpoint = ModelCheckpoint(log_dir + 'ep{epoch:03d}-loss{loss:.3f}-val_loss{val_loss:.3f}.h5',
         monitor='val_loss', save_weights_only=True, save_best_only=False, period=1)
     early_stopping = EarlyStopping(monitor='val_loss', min_delta=0, patience=10, verbose=1)
 
-    #----------------------------------------------------------------------#
-    #   验证集的划分在train.py代码里面进行
-    #   2007_test.txt和2007_val.txt里面没有内容是正常的。训练不会使用到。
-    #   当前划分方式下，验证集和训练集的比例为1:9
-    #----------------------------------------------------------------------#
+
     val_split = 0.1
     with open(annotation_path) as f:
         lines = f.readlines()
@@ -285,33 +189,26 @@ def preprocess_true_boxes(true_boxes, input_shape, anchors, num_classes):
     num_val = int(len(lines)*val_split)
     num_train = len(lines) - num_val
     
-    #------------------------------------------------------#
-    #   主干特征提取网络特征通用，冻结训练可以加快训练速度
-    #   也可以在训练初期防止权值被破坏。
-    #   Init_Epoch为起始世代
-    #   Freeze_Epoch为冻结训练的世代
-    #   Epoch总训练世代
-    #   提示OOM或者显存不足请调小Batch_size
-    #------------------------------------------------------#
+
     freeze_layers = 60
     for i in range(freeze_layers): model_body.layers[i].trainable = False
     print('Freeze the first {} layers of total {} layers.'.format(freeze_layers, len(model_body.layers)))
 
-    # 调整非主干模型first
+ 
     if True:
         Init_epoch = 0
         Freeze_epoch = 50
         batch_size = 32
         learning_rate_base = 1e-3
 
         if Cosine_scheduler:
-            # 预热期
+            
             warmup_epoch = int((Freeze_epoch-Init_epoch)*0.2)
-            # 总共的步长
+          
             total_steps = int((Freeze_epoch-Init_epoch) * num_train / batch_size)
-            # 预热步长
+           
             warmup_steps = int(warmup_epoch * num_train / batch_size)
-            # 学习率
+          
             reduce_lr = WarmUpCosineDecayScheduler(learning_rate_base=learning_rate_base,
                                                         total_steps=total_steps,
                                                         warmup_learning_rate=1e-4,
@@ -336,21 +233,21 @@ def preprocess_true_boxes(true_boxes, input_shape, anchors, num_classes):
 
     for i in range(freeze_layers): model_body.layers[i].trainable = True
 
-    # 解冻后训练
+   
     if True:
         Freeze_epoch = 50
         Epoch = 100
         batch_size = 16
         learning_rate_base = 1e-4
 
         if Cosine_scheduler:
-            # 预热期
+     
             warmup_epoch = int((Epoch-Freeze_epoch)*0.2)
-            # 总共的步长
+           
             total_steps = int((Epoch-Freeze_epoch) * num_train / batch_size)
-            # 预热步长
+        
             warmup_steps = int(warmup_epoch * num_train / batch_size)
-            # 学习率
+   
             reduce_lr = WarmUpCosineDecayScheduler(learning_rate_base=learning_rate_base,
                                                         total_steps=total_steps,
                                                         warmup_learning_rate=1e-5,
