轉自:https://blog.csdn.net/Patrick_Lxc/article/details/80615433 感謝博主
第一步:下載VOC2007數據集,把所有文件夾裏面的東西刪除,保留所有文件夾的名字。
像這樣:
第二步:把你所有的圖片都複製到JPEGImages裏面
像這樣:
第三步:生成Annotations下的文件
工具:LabelImg ,鏈接:https://pan.baidu.com/s/1GJFYcFm5Zlb-c6tIJ2N4hw 密碼:h0i5
像這樣:
第四步:生成ImageSets/Main/4個文件。在VOC2007下建個文件test.py,然後運行
像這樣:
test.py代碼:
import os import random trainval_percent = 0.1 train_percent = 0.9 xmlfilepath = 'Annotations' txtsavepath = 'ImageSets\Main' total_xml = os.listdir(xmlfilepath) num = len(total_xml) list = range(num) tv = int(num * trainval_percent) tr = int(tv * train_percent) trainval = random.sample(list, tv) train = random.sample(trainval, tr) ftrainval = open('ImageSets/Main/trainval.txt', 'w') ftest = open('ImageSets/Main/test.txt', 'w') ftrain = open('ImageSets/Main/train.txt', 'w') fval = open('ImageSets/Main/val.txt', 'w') for i in list: name = total_xml[i][:-4] + '\n' if i in trainval: ftrainval.write(name) if i in train: ftest.write(name) else: fval.write(name) else: ftrain.write(name) ftrainval.close() ftrain.close() fval.close() ftest.close()
第五步:生成yolo3所需的train.txt,val.txt,test.txt
VOC2007數據集製作完成,但是,yolo3並不直接用這個數據集,開心麼?
需要的運行voc_annotation.py ,classes以三個顏色爲例,你的數據集記得改
運行之後,會在主目錄下多生成三個txt文件,
像這樣:
手動刪除2007_,
第六步:修改參數文件yolo3.cfg
註明一下,這個文件是用於轉換官網下載的.weights文件用的。訓練自己的網絡並不需要去管他。詳見readme
IDE裏直接打開cfg文件,ctrl+f搜 yolo, 總共會搜出3個含有yolo的地方,睜開你的卡姿蘭大眼睛,3個yolo!!
每個地方都要改3處,filters:3*(5+len(classes));
classes: len(classes) = 3,這裏以紅、黃、藍三個顏色爲例
random:原來是1,顯存小改爲0
第七步:修改model_data下的文件,放入你的類別,coco,voc這兩個文件都需要修改。
像這樣:
第八步:修改代碼,準備訓練。代碼以yolo3模型爲目標,tiny_yolo不考慮。
爲什麼說這篇文章是從頭開始訓練?代碼原作者在train.py做了兩件事情:
1、會加載預先對coco數據集已經訓練完成的yolo3權重文件,
像這樣:
2、凍結了開始到最後倒數第N層(源代碼爲N=-2),
像這樣:
但是,你和我想訓練的東西,coco裏沒有啊,所以,就乾脆從頭開始訓練吧
對train.py做了一下修改,直接複製替換原文件就可以了,細節大家自己看吧,直接運行,loss達到10幾的時候效果就可以了
train.py:
""" 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.callbacks import TensorBoard, ModelCheckpoint, EarlyStopping from yolo3.model import preprocess_true_boxes, yolo_body, tiny_yolo_body, yolo_loss from yolo3.utils import get_random_data def _main(): annotation_path = 'train.txt' log_dir = 'logs/000/' classes_path = 'model_data/voc_classes.txt' anchors_path = 'model_data/yolo_anchors.txt' class_names = get_classes(classes_path) anchors = get_anchors(anchors_path) input_shape = (416,416) # multiple of 32, hw model = create_model(input_shape, anchors, len(class_names) ) train(model, annotation_path, input_shape, anchors, len(class_names), log_dir=log_dir) def train(model, annotation_path, input_shape, anchors, num_classes, log_dir='logs/'): model.compile(optimizer='adam', loss={ 'yolo_loss': lambda y_true, y_pred: y_pred}) 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=True, period=1) batch_size = 10 val_split = 0.1 with open(annotation_path) as f: lines = f.readlines() np.random.shuffle(lines) num_val = int(len(lines)*val_split) num_train = len(lines) - num_val print('Train on {} samples, val on {} samples, with batch size {}.'.format(num_train, num_val, batch_size)) model.fit_generator(data_generator_wrap(lines[:num_train], batch_size, input_shape, anchors, num_classes), steps_per_epoch=max(1, num_train//batch_size), validation_data=data_generator_wrap(lines[num_train:], batch_size, input_shape, anchors, num_classes), validation_steps=max(1, num_val//batch_size), epochs=500, initial_epoch=0) model.save_weights(log_dir + 'trained_weights.h5') def get_classes(classes_path): with open(classes_path) as f: class_names = f.readlines() class_names = [c.strip() for c in class_names] return class_names def get_anchors(anchors_path): with open(anchors_path) as f: anchors = f.readline() anchors = [float(x) for x in anchors.split(',')] return np.array(anchors).reshape(-1, 2) def create_model(input_shape, anchors, num_classes, load_pretrained=False, freeze_body=False, weights_path='model_data/yolo_weights.h5'): 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, 2:8}[l], w//{0:32, 1:16, 2:8}[l], \ num_anchors//3, num_classes+5)) for l in range(3)] model_body = yolo_body(image_input, num_anchors//3, num_classes) print('Create 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: # Do not freeze 3 output layers. num = len(model_body.layers)-7 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': 0.5})( [*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): n = len(annotation_lines) np.random.shuffle(annotation_lines) i = 0 while True: image_data = [] box_data = [] for b in range(batch_size): i %= n image, box = get_random_data(annotation_lines[i], input_shape, random=True) image_data.append(image) box_data.append(box) i += 1 image_data = np.array(image_data) box_data = np.array(box_data) y_true = preprocess_true_boxes(box_data, input_shape, anchors, num_classes) yield [image_data, *y_true], np.zeros(batch_size) def data_generator_wrap(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()
第九步:預測圖片。修改了yolo.py下的預測圖片的函數,將檢測的圖片都儲存在了outdir裏
''' def detect_img(yolo): while True: img = input('Input image filename:') try: image = Image.open(img) except: print('Open Error! Try again!') continue else: r_image = yolo.detect_image(image) r_image.show() yolo.close_session() ''' import glob def detect_img(yolo): path = "D:\VOCdevkit\VOC2007\JPEGImages\*.jpg" outdir = "D:\\VOCdevkit\VOC2007\SegmentationClass" for jpgfile in glob.glob(path): img = Image.open(jpgfile) img = yolo.detect_image(img) img.save(os.path.join(outdir, os.path.basename(jpgfile))) yolo.close_session()