yolov8自己写train.py
yolo8自己写的train.py会运行报错，命令提示符里面就可以运行，环境安装的pip install -e .
- 这篇文章讲的很详细，请看：yolov5train.py注释
- 除此之外, 这篇博客: yolov3详细解释（内附代码详细说明）中的 train.py 部分也许能够解决你的问题, 你可以仔细阅读以下内容或跳转源博客中阅读:
""" Retrain the YOLO model for your own dataset. """ import numpy as np import keras.backend as K from keras.layers import Input, Lambda from keras.models import Model from keras.optimizers import Adam from keras.callbacks import TensorBoard, ModelCheckpoint, ReduceLROnPlateau, EarlyStopping from yolo3.model import preprocess_true_boxes, yolo_body, tiny_yolo_body, yolo_loss from yolo3.utils import get_random_data #主函数 def _main(): annotation_path = 'train.txt' log_dir = 'logs/000/' classes_path = 'model_data/voc_classes.txt' anchors_path = 'model_data/yolo_anchors.txt' #得到类名，类总数，锚框 class_names = get_classes(classes_path) num_classes = len(class_names) anchors = get_anchors(anchors_path) input_shape = (416,416) # multiple of 32, hw #判断是否用tiny_body is_tiny_version = len(anchors)==6 # default setting if is_tiny_version: #建立模型 model = create_tiny_model(input_shape, anchors, num_classes, freeze_body=2, weights_path='model_data/tiny_yolo_weights.h5') else: #建立模型 model = create_model(input_shape, anchors, num_classes, freeze_body=2, weights_path='model_data/yolo_weights.h5') # make sure you know what you freeze #设置日志路径 logging = TensorBoard(log_dir=log_dir) #设置检查点，3回检查一次，按验证集损失对比 保留最号的 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=True, period=3) #学习衰减率 monitor 监测值 factor 缩放学习率的值，学习率将以lr = lr*factor的形式被减少 #当patience个epoch过去而模型性能不提升时，学习率减少的动作会被触发 reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.1, patience=3, verbose=1) #早停 min_delta增大或减小的阈值，只有大于这个部分才算作improvement #能够容忍多少个epoch内都没有improvement early_stopping = EarlyStopping(monitor='val_loss', min_delta=0, patience=10, verbose=1) #分给验证集的比例 val_split = 0.1 with open(annotation_path) as f: lines = f.readlines() np.random.seed(10101) np.random.shuffle(lines) np.random.seed(None) #分配训练集和验证集的数量 num_val = int(len(lines)*val_split) num_train = len(lines) - num_val # Train with frozen layers first, to get a stable loss. # Adjust num epochs to your dataset. This step is enough to obtain a not bad model. #先用冰冻层进行训练，得到稳定的损失。 #调整num epoch到您的数据集。这一步足以获得一个不错的模型。 if True: #设置优化器 loss设置不太懂？？？？？？？？？？？？？？？？？？？？？？？？？？？？？？？？？？？？/ model.compile(optimizer=Adam(lr=1e-3), loss={ # use custom yolo_loss Lambda layer. 'yolo_loss': lambda y_true, y_pred: y_pred}) batch_size = 32 print('Train on {} samples, val on {} samples, with batch size {}.'.format(num_train, num_val, batch_size)) #设置训练器 model.fit_generator(data_generator_wrapper(lines[:num_train], batch_size, input_shape, anchors, num_classes), steps_per_epoch=max(1, num_train//batch_size), validation_data=data_generator_wrapper(lines[num_train:], batch_size, input_shape, anchors, num_classes), validation_steps=max(1, num_val//batch_size), epochs=50, initial_epoch=0, callbacks=[logging, checkpoint]) model.save_weights(log_dir + 'trained_weights_stage_1.h5') # Unfreeze and continue training, to fine-tune. # Train longer if the result is not good. #解冻并继续训练，以进行微调。 #如果效果不好，就多训练。 if True: #将模型层全部解冻 for i in range(len(model.layers)): model.layers[i].trainable = True model.compile(optimizer=Adam(lr=1e-4), loss={'yolo_loss': lambda y_true, y_pred: y_pred}) # recompile to apply the change print('Unfreeze all of the layers.') batch_size = 32 # note that more GPU memory is required after unfreezing the body print('Train on {} samples, val on {} samples, with batch size {}.'.format(num_train, num_val, batch_size)) model.fit_generator(data_generator_wrapper(lines[:num_train], batch_size, input_shape, anchors, num_classes), steps_per_epoch=max(1, num_train//batch_size), validation_data=data_generator_wrapper(lines[num_train:], batch_size, input_shape, anchors, num_classes), validation_steps=max(1, num_val//batch_size), epochs=100, initial_epoch=50, callbacks=[logging, checkpoint, reduce_lr, early_stopping]) model.save_weights(log_dir + 'trained_weights_final.h5') # Further training if needed. #如有需要，可接受进一步训练。 #在_main中应用，得到类名一个列表 def get_classes(classes_path): '''loads the classes''' with open(classes_path) as f: class_names = f.readlines() class_names = [c.strip() for c in class_names] return class_names #在_main中应用，得到锚框(9,2)维度 或者 (6,2)维度 def get_anchors(anchors_path): '''loads the anchors from a file''' with open(anchors_path) as f: anchors = f.readline() anchors = [float(x) for x in anchors.split(',')] return np.array(anchors).reshape(-1, 2) #在_train 中应用 def create_model(input_shape, anchors, num_classes, load_pretrained=True, freeze_body=2, weights_path='model_data/yolo_weights.h5'): '''create the training model''' #参数解释：load_pretrained 是否下载预训练， #freeze_body 是否冻结预训练的层 1代表冻结darknet 2代表冻结yolo_body除3个检测层的其他层 K.clear_session() # get a new session #占位参数 image_input 在经过Input后 shape会变成四个维度 多加一个batch_size维度 (None,None,None,3) image_input = Input(shape=(None, None, 3)) h, w = input_shape#(416,416) num_anchors = len(anchors) #得到占位 y_true y_true = [Input(shape=(h//{0:32, 1:16, 2:8}[l], w//{0:32, 1:16, 2:8}[l], \ num_anchors//3, num_classes+5)) for l in range(3)] #建立模型本体 model_body = yolo_body(image_input, num_anchors//3, num_classes) print('Create YOLOv3 model with {} anchors and {} classes.'.format(num_anchors, num_classes)) #是否加载预训练权重 if load_pretrained: model_body.load_weights(weights_path, by_name=True, skip_mismatch=True) print('Load weights {}.'.format(weights_path)) #是否冻结 代表不训练这些层 if freeze_body in [1, 2]: # Freeze darknet53 body or freeze all but 3 output layers. #冻结暗网53的身体或冻结除3个输出层以外的所有层。 num = (185, len(model_body.layers)-3)[freeze_body-1] for i in range(num): model_body.layers[i].trainable = False print('Freeze the first {} layers of total {} layers.'.format(num, len(model_body.layers))) #设置损失函数 *的作用是进行迭代，将列表中的元素按第一维度迭代处出来，实际就是减少一个维度 model_loss = Lambda(yolo_loss, output_shape=(1,), name='yolo_loss', arguments={'anchors': anchors, 'num_classes': num_classes, 'ignore_thresh': 0.5})( [*model_body.output, *y_true]) #将Model 中 [model_body.input, *y_true]设置为输入 model_loss设置为输出 model = Model([model_body.input, *y_true], model_loss) return model #在_train 中应用 与create_model相似 def create_tiny_model(input_shape, anchors, num_classes, load_pretrained=True, freeze_body=2, weights_path='model_data/tiny_yolo_weights.h5'): '''create the training model, for Tiny YOLOv3''' K.clear_session() # get a new session image_input = Input(shape=(None, None, 3)) h, w = input_shape num_anchors = len(anchors) 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)] model_body = tiny_yolo_body(image_input, num_anchors//2, num_classes) print('Create Tiny YOLOv3 model with {} anchors and {} classes.'.format(num_anchors, num_classes)) if load_pretrained: model_body.load_weights(weights_path, by_name=True, skip_mismatch=True) print('Load weights {}.'.format(weights_path)) if freeze_body in [1, 2]: # Freeze the darknet body or freeze all but 2 output layers. num = (20, len(model_body.layers)-2)[freeze_body-1] for i in range(num): model_body.layers[i].trainable = False print('Freeze the first {} layers of total {} layers.'.format(num, len(model_body.layers))) model_loss = Lambda(yolo_loss, output_shape=(1,), name='yolo_loss', arguments={'anchors': anchors, 'num_classes': num_classes, 'ignore_thresh': 0.7})( [*model_body.output, *y_true]) model = Model([model_body.input, *y_true], model_loss) return model def data_generator(annotation_lines, batch_size, input_shape, anchors, num_classes): '''data generator for fit_generator''' #读取所有的数据行 n = len(annotation_lines) i = 0 while True: image_data = [] box_data = [] #对batch_size中的每一行数据进行处理 for b in range(batch_size): #洗牌 打乱 if i==0: np.random.shuffle(annotation_lines) #得到经过调整后的数据 image, box = get_random_data(annotation_lines[i], input_shape, random=True) image_data.append(image) box_data.append(box) #确保i在n里 也保证i一直增大 i = (i+1) % n image_data = np.array(image_data) box_data = np.array(box_data) #对输入进行预处理 得到y_true y_true = preprocess_true_boxes(box_data, input_shape, anchors, num_classes) #yield作用是输出后继续循环 yield [image_data, *y_true], np.zeros(batch_size) def data_generator_wrapper(annotation_lines, batch_size, input_shape, anchors, num_classes): n = len(annotation_lines) if n==0 or batch_size<=0: return None return data_generator(annotation_lines, batch_size, input_shape, anchors, num_classes) if __name__ == '__main__': _main()