Tensorflow object detection API 訓練自己的資料集
環境:win10
Anaconda3 tensorflow 1.9.0
上篇運行了demo之後,打算訓練自己的資料集,但是沒有完全成功,不過反覆弄了好幾次後,這些步驟還是熟了的,把遇到的問題也貼出來,有人會的話幫我解答下
一、準備資料集
資料集用 LabelImg 標註會會生成相應的xml檔案,具體不在詳述,我是直接找了之前用過的一個車的資料集(300張做訓練集,60張做測試集),但是這裡除了原圖跟xml檔案外,還需要.cvs和.record檔案,生成這兩個檔案的python程式碼如下(參考的博主有提供,這裡我做個簡單的註釋,不懂可以問)
注:.cvs和.record檔案這兩個檔案訓練集train和測試集test都需要有,所以下面的程式碼裡修改資料集路徑就可以成相應的檔案啦,也就是這些python指令碼分別要操作訓練集跟測試集,最後生成4個檔案
1.生成.cvs檔案python指令碼
#生成.cvs檔案pyhon指令碼 # -*- coding: utf-8 -*- """ Created on Tue Jan 16 00:52:02 2018 @author: Xiang Guo #博主,感謝 將資料夾內所有XML檔案的資訊記錄到CSV檔案中 """ import os import glob import pandas as pd import xml.etree.ElementTree as ET os.chdir('D:\\RaniFile\\CarModelYHQ\\test') #資料集路徑 path = 'D:\\RaniFile\\CarModelYHQ\\test' #生成的.cvs檔案路徑 def xml_to_csv(path): xml_list = [] for xml_file in glob.glob(path + '/*.xml'): tree = ET.parse(xml_file) root = tree.getroot() for member in root.findall('object'): value = (root.find('filename').text, int(root.find('size')[0].text), int(root.find('size')[1].text), member[0].text, int(member[4][0].text), int(member[4][1].text), int(member[4][2].text), int(member[4][3].text) ) xml_list.append(value) column_name = ['filename', 'width', 'height', 'class', 'xmin', 'ymin', 'xmax', 'ymax'] xml_df = pd.DataFrame(xml_list, columns=column_name) return xml_df def main(): image_path = path xml_df = xml_to_csv(image_path) xml_df.to_csv('tv_vehicle_labels.csv', index=None) #第一個引數是生成的檔名 print('Successfully converted xml to csv.') main()
2.生成.recored檔案python指令碼
程式碼裡原博主非常用心的寫了使用方法,我在這裡在說一下吧
## --csv_input=引數表示.cvs路徑及檔名 --output_path=引數表示生成的檔名
##
python generate_tfrecord.py --csv_input=data/tv_vehicle_labels.csv --output_path=train.record
python generate_tfrecord.py --csv_input=data/test_labels.csv --output_path=test.record
#生成.recored檔案python指令碼 # -*- coding: utf-8 -*- """ Created on Tue Jan 16 01:04:55 2018 @author: Xiang Guo 由CSV檔案生成TFRecord檔案 """ """ Usage: # From tensorflow/models/ # Create train data: python generate_tfrecord.py --csv_input=data/tv_vehicle_labels.csv --output_path=train.record # Create test data: python generate_tfrecord.py --csv_input=data/test_labels.csv --output_path=test.record """ import os import io import pandas as pd import tensorflow as tf from PIL import Image from object_detection.utils import dataset_util from collections import namedtuple, OrderedDict os.chdir('D:\\RaniFile\\myproject\\tensorflow\\models\\research\\object_detection') #這個跟路徑下面會用到還會再接一段,包括執行時候引數的路徑的路徑也是接著這個 flags = tf.app.flags flags.DEFINE_string('csv_input', '', 'Path to the CSV input') flags.DEFINE_string('output_path', '', 'Path to output TFRecord') FLAGS = flags.FLAGS # TO-DO replace this with label map #注意將對應的label改成自己的類別!!!!!!!!!! def class_text_to_int(row_label): if row_label == 'sedan': return 1 elif row_label == 'van': return 2 elif row_label == 'SUV': return 3 elif row_label == 'truck': return 4 elif row_label == 'minibus': return 5 elif row_label == 'hatchback': return 6 elif row_label == 'tricycle': return 7 elif row_label == 'bus': return 8 else: 0 def split(df, group): data = namedtuple('data', ['filename', 'object']) gb = df.groupby(group) return [data(filename, gb.get_group(x)) for filename, x in zip(gb.groups.keys(), gb.groups)] def create_tf_example(group, path): with tf.gfile.GFile(os.path.join(path, '{}'.format(group.filename)), 'rb') as fid: encoded_jpg = fid.read() encoded_jpg_io = io.BytesIO(encoded_jpg) image = Image.open(encoded_jpg_io) width, height = image.size filename = group.filename.encode('utf8') image_format = b'jpg' xmins = [] xmaxs = [] ymins = [] ymaxs = [] classes_text = [] classes = [] for index, row in group.object.iterrows(): xmins.append(row['xmin'] / width) xmaxs.append(row['xmax'] / width) ymins.append(row['ymin'] / height) ymaxs.append(row['ymax'] / height) classes_text.append(row['class'].encode('utf8')) classes.append(class_text_to_int(row['class'])) tf_example = tf.train.Example(features=tf.train.Features(feature={ 'image/height': dataset_util.int64_feature(height), 'image/width': dataset_util.int64_feature(width), 'image/filename': dataset_util.bytes_feature(filename), 'image/source_id': dataset_util.bytes_feature(filename), 'image/encoded': dataset_util.bytes_feature(encoded_jpg), 'image/format': dataset_util.bytes_feature(image_format), 'image/object/bbox/xmin': dataset_util.float_list_feature(xmins), 'image/object/bbox/xmax': dataset_util.float_list_feature(xmaxs), 'image/object/bbox/ymin': dataset_util.float_list_feature(ymins), 'image/object/bbox/ymax': dataset_util.float_list_feature(ymaxs), 'image/object/class/text': dataset_util.bytes_list_feature(classes_text), 'image/object/class/label': dataset_util.int64_list_feature(classes), })) return tf_example def main(_): writer = tf.python_io.TFRecordWriter(FLAGS.output_path) path = os.path.join(os.getcwd(), 'myimages\\test') #第二個引數,這個原圖路徑接著前面那個註釋的路徑的 examples = pd.read_csv(FLAGS.csv_input) grouped = split(examples, 'filename') for group in grouped: tf_example = create_tf_example(group, path) writer.write(tf_example.SerializeToString()) writer.close() output_path = os.path.join(os.getcwd(), FLAGS.output_path) print('Successfully created the TFRecords: {}'.format(output_path)) if __name__ == '__main__': tf.app.run()
這裡面的路徑如果有點糾結理不清地話,可以先是這執行下,找不到會報錯,然後慢慢改。。。我就是這樣的,其實python程式碼仔細看看也不難理解
3.建一個.pbtxt檔案,裡面寫類別,我的檔名是tv_vehicle_detection.pbtxt
#這個id跟name,要跟上不一個生成.record腳本里面的那個類別一致
item {
id: 1
name: 'sedan'
}
...
...
item {
id: 8
name: 'bus'
}
好了資料集的準備到此就做完了
二、配置檔案與模型
先列一下資料夾,這些檔案都是 object_detection這個資料夾下,相信執行過demo的同學對這個檔案的位置應該很熟悉了
-mydata/
--test_labels.csv #這些檔案都在上一步準備好了
--test.record
--train_labels.csv
--train.record
--tv_vehicle_detection.pbtxt
-myimages/
--test/ #測試集圖片
---testingimages.jpg
--train/ #訓練集圖片
---testingimages.jpg
-mytraining
接下來要配置模型檔案了
1.下載所需預訓練模型COCO-trained models
我用的是ssd_mobilenet_v1_coco_2018_01_28.tar.gz所以下面配置都以它為例講,下載下來後解壓就行
2.把裡面的model.ckpt、model.ckpt.data-00000-of-00001、model.ckpt.index這三個檔案都放到mydata資料夾下
3.把pipeline.config檔案放到mytraining資料夾下,裡面一些引數要配置(之後有時間仔細讀下這個配置檔案,寫個註釋吧)
model {
ssd {
num_classes: 8 #類別個數,我的標籤一共是有8類
image_resizer {
fixed_shape_resizer {
height: 300
width: 300
}
}
feature_extractor {
type: "ssd_mobilenet_v1" #模型名稱
depth_multiplier: 1.0
min_depth: 16
conv_hyperparams {
regularizer {
l2_regularizer {
weight: 3.99999989895e-05
}
}
initializer {
truncated_normal_initializer {
mean: 0.0
stddev: 0.0299999993294
}
}
activation: RELU_6
batch_norm {
decay: 0.999700009823
center: true
scale: true
epsilon: 0.0010000000475
train: true
}
}
}
box_coder {
faster_rcnn_box_coder {
y_scale: 10.0
x_scale: 10.0
height_scale: 5.0
width_scale: 5.0
}
}
matcher {
argmax_matcher {
matched_threshold: 0.5
unmatched_threshold: 0.5
ignore_thresholds: false
negatives_lower_than_unmatched: true
force_match_for_each_row: true
}
}
similarity_calculator {
iou_similarity {
}
}
box_predictor {
convolutional_box_predictor {
conv_hyperparams {
regularizer {
l2_regularizer {
weight: 3.99999989895e-05
}
}
initializer {
truncated_normal_initializer {
mean: 0.0
stddev: 0.0299999993294
}
}
activation: RELU_6
batch_norm {
decay: 0.999700009823
center: true
scale: true
epsilon: 0.0010000000475
train: true
}
}
min_depth: 0
max_depth: 0
num_layers_before_predictor: 0
use_dropout: false
dropout_keep_probability: 0.800000011921
kernel_size: 1
box_code_size: 4
apply_sigmoid_to_scores: false
}
}
anchor_generator {
ssd_anchor_generator {
num_layers: 6
min_scale: 0.20000000298
max_scale: 0.949999988079
aspect_ratios: 1.0
aspect_ratios: 2.0
aspect_ratios: 0.5
aspect_ratios: 3.0
aspect_ratios: 0.333299994469
}
}
post_processing {
batch_non_max_suppression {
score_threshold: 0.300000011921
iou_threshold: 0.600000023842
max_detections_per_class: 100
max_total_detections: 100
}
score_converter: SIGMOID
}
normalize_loss_by_num_matches: true
loss {
localization_loss {
weighted_smooth_l1 {
}
}
classification_loss {
weighted_sigmoid {
}
}
hard_example_miner {
num_hard_examples: 3000
iou_threshold: 0.990000009537
loss_type: CLASSIFICATION
max_negatives_per_positive: 3
min_negatives_per_image: 0
}
classification_weight: 1.0
localization_weight: 1.0
}
}
}
train_config { #訓練的一些配置
batch_size: 1 #batch_size大小,改成了1,怕視訊記憶體不足,硬體支援的話可以不改
data_augmentation_options {
random_horizontal_flip {
}
}
data_augmentation_options {
ssd_random_crop {
}
}
optimizer {
rms_prop_optimizer {
learning_rate {
exponential_decay_learning_rate {
initial_learning_rate: 0.00400000018999
decay_steps: 800720
decay_factor: 0.949999988079
}
}
momentum_optimizer_value: 0.899999976158
decay: 0.899999976158
epsilon: 1.0
}
}
fine_tune_checkpoint: "mydata/model.ckpt"
from_detection_checkpoint: true
num_steps: 200000 #訓練迭代次數,當然執行的時候也可以寫引數設定
}
train_input_reader {
label_map_path: "mydata/tv_vehicle_detection.pbtxt" #類別路徑
tf_record_input_reader {
input_path: "mydata/train.record" #訓練集.record檔案路徑
}
}
eval_config {
num_examples: 8000
max_evals: 10
use_moving_averages: false
}
eval_input_reader {
label_map_path: "mydata/tv_vehicle_detection.pbtxt" #類別路徑,同上
shuffle: false
num_readers: 1
tf_record_input_reader {
input_path: "mydata/test.record" #測試集.record檔案路徑
}
}
好了檔案配置也完成了
三、訓練模型
Anaconda Prompt 定位到 models\research\object_detection資料夾下,執行如下命令:
python model_main.py
--pipeline_config_path=mytraining/pipeline.config #pipeline.config路徑
--model_dir=object_detection/mytraining #生成模型的資料夾
--num_train_steps=20000 #訓練20000步
--num_eval_steps=1000 #測試1000步
--alsologtostderr
然後就開始訓練了
tensorboard可以視覺化訓練過程,所以我也試了下, Anaconda Prompt 定位到 models\research\object_detection資料夾下,執行如下命令
tensorboard --logdir='mytraining' #這個資料夾就是存訓練好的模型的那個資料夾
路徑對的話就可以出來,關於tensordboard可以展示還有很多,不過要在程式碼里加上你需要統計的資訊,我就簡單看了下,有興趣的可以仔細研究嘗試
其實我訓練到後面還是出了問題。。。。。(訓練就很慢了,當時就只留了這張截圖,不知道能不能明白問題的意思,有時間在嘗試下。。。。)