# 快速开始 ## 1. 安装环境 - python版本: 2.7 OR >=3.4 - TensorFlow版本: 开源TF >= 1.8([安装](https://www.tensorflow.org/install/)) OR PAI-TF ## 2. 安装步骤 - pip install cython - pip install http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/release/easy_vision-1.0.7-py2.py3-none-any.whl - 验证: ```python import easy_vision ``` 如下安装第三方库下载缓慢，可以采取如下方式更改pip源加速 新建 ~/.config/pip/pip.conf 文件 ```shell [global] index-url = https://pypi.tuna.tsinghua.edu.cn/simple ``` ## 3. 使用步骤 ### 3.1 数据准备 下载pascal数据集(在当前目录): ```shell osscmd downloadallobject oss://pai-vision-data-hz/data/voc0712_tfrecord/ data/voc0712_tfrecord --host=oss-cn-zhangjiakou.aliyuncs.com # or use oss util, 需要在配置文件中设置host为oss-cn-zhangjiakou.aliyuncs.com ossutil cp -r oss://pai-vision-data-hz/data/voc0712_tfrecord/ data/voc0712_tfrecord ``` 下载resnet50预训练模型(在当前目录): ```powershell mkdir -p pretrained_models/ ossutil cp -r oss://pai-vision-data-hz/pretrained_models/resnet_v1d_50/ pretrained_models/resnet_v1d_50 ``` ### 3.2 启动训练任务 **普通配置模式** ```python import easy_vision easy_vision.train_and_evaluate(easy_vision.RFCN_SAMPLE_CONFIG) ``` **参数配置模式** ```python import easy_vision param_config = """ --model_type RFCN --backbone resnet_v1d_50 --num_classes 20 --model_dir experiments/pascal_voc/resnet50_rfcn_model --train_data data/voc0712_tfrecord/voc0712_part_*.tfrecord --test_data data/voc0712_tfrecord/VOC2007_test.tfrecord --num_test_example 2 --train_batch_size 32 --test_batch_size 1 --image_min_sizes 600 --image_max_sizes 1024 --lr_type exponential_decay --initial_learning_rate 0.001 --decay_epochs 20 --staircase true""" easy_vision.train_and_evaluate_with_param_config(param_config) ``` **PS模式** 需要在具有至少两张GPU卡的机器上才能运行，一共需要启动3个子进程，分别是ps(parameter server), master(训练过程，负责写summary，保存checkpoint, 定期evaluation)，worker(训练过程)，脚本如下: ```python #-*- encoding:utf-8 -*- import multiprocessing import sys import os import easy_vision import json import logging import subprocess import time # train config under distributed settings config=easy_vision.RFCN_DISTRIBUTE_SAMPLE_CONFIG print('config path: %s' % config) # cluster spec TF_CONFIG={'cluster':{ 'ps': ['localhost:12921'], 'master': ['localhost:12922'], 'worker': ['localhost:12923'] } } def job(task, gpu): task_name = task['type'] # redirect python log and tf log to log_file_name # [logs/master.log, logs/worker.log, logs/ps.log] log_file_name = "logs/%s.log" % task_name TF_CONFIG['task'] = task os.environ['TF_CONFIG'] = json.dumps(TF_CONFIG) os.environ['CUDA_VISIBLE_DEVICES'] = gpu train_cmd = 'python -m easy_vision.python.train_eval --pipeline_config_path %s' % config logging.info('%s > %s 2>&1 ' % (train_cmd, log_file_name)) with open(log_file_name, 'w') as lfile: return subprocess.Popen(train_cmd.split(' '), stdout= lfile, stderr=subprocess.STDOUT) if __name__ == '__main__': procs = {} # start ps job on cpu task = {'type':'ps', 'index':0} procs['ps'] = job(task, '') # start master job on gpu 0 task = {'type':'master', 'index':0} procs['master'] = job(task, '0') # start worker job on gpu 1 task = {'type':'worker', 'index':0} procs['worker'] = job(task, '1') num_worker = 2 for k, proc in procs.items(): logging.info('%s pid: %d' %(k, proc.pid)) task_failed = None task_finish_cnt = 0 task_has_finished = {k:False for k in procs.keys()} while True: for k, proc in procs.items(): if proc.poll() is None: if task_failed is not None: logging.error('task %s failed, %s quit' % (task_failed, k)) proc.terminate() if k != 'ps': task_has_finished[k] = True task_finish_cnt += 1 logging.info('task_finish_cnt %d' % task_finish_cnt) else: if not task_has_finished[k]: #process quit by itself if k != 'ps': task_finish_cnt += 1 task_has_finished[k] = True logging.info('task_finish_cnt %d' % task_finish_cnt) if proc.returncode != 0: logging.error('%s failed' %k) task_failed = k else: logging.info('%s run successfuly' % k) if task_finish_cnt >= num_worker: break time.sleep(1) ``` ### 3.3 使用tensorboard观察训练过程 在模型目录下面可以看到保存的模型的checkpoint和event file，通过tensorboard可以查看loss, mAP等相关信息 tensorboard --port 6006 --logdir ${model_dir} [ --host 0.0.0.0 ] - **训练Loss** 如下图所示，loss是总的loss, loss/loss/rcnn_cls是分类loss， loss/loss/rcnn_reg是回归的loss，loss/loss/rpn_cls是RPN(RegionProposalNetwork)的分类loss，loss/loss/rpn_reg是RPN的回归loss。![](../images/quick_start/tensorboard_detection_loss.png) - **测试mAP** 如下图所示，这里使用了两个常用物体检测的metric：PascalBoxes07和PascalBoxes![](../images/quick_start/tensorboard_detection_metric.png) ### 3.4 评估和预测 训练完成之后可以在其它数据集上测试，得到每张图的检测结果 ```python import easy_vision detect_results = easy_vision.predict(easy_vision.RFCN_SAMPLE_CONFIG) ``` 也可以在训练完以后再次评估，评估的结果 ```python import easy_vision eval_metrics = easy_vision.evaluate(easy_vision.RFCN_SAMPLE_CONFIG) ``` ### 3.5 导出模型 EasyVision可以方便地将模型导出成savedmodel格式，方便后续使用python、c++等语言进行预测使用 ```python import easy_vision easy_vision.export(export_dir, easy_vision.RFCN_SAMPLE_CONFIG, checkpoint_path) ``` 导出程序会在export_dir下以当前unix时间戳创建模型目录，把checkpoint导出成[savedmodel](https://www.tensorflow.org/guide/saved_model#build_and_load_a_savedmodel)存放在目录下。 ### 3.6 模型预测 我们提供了savedmodel的python版本的预测器，下面以检测模型为例，其余的如分类、分割、OCR等预测器详见[模型预测文档](predict.md) ```python import easy_vision detector = ev.Detector(saved_model_path) image = np.zeros([640, 480, 3], dtype=np.float32) output_dict = detector.predict([image]) ``` 预测结果以List of Json形式输出，List的Length与输入图像的张数相等，一下为各模型Json结果的示例与说明，Json结果样例如下： ```json { "detection_boxes": [[243.5308074951172, 197.69570922851562, 385.59625244140625, 247.7247772216797], [292.1929931640625, 114.28043365478516, 571.2748413085938, 165.09771728515625]], "detection_scores": [0.9942291975021362, 0.9940272569656372], "detection_classes": [1, 1], "detection_classe_names": ["text", "text"] } ``` ### 3.7 SavedModel评估 评估已导出的savedmodel，metric会打印在控制台中，predictor_eval_config的样例配置参见[sample_config](../sample_config.html#savedmodel) ```python from easy_vision.python.main import predictor_evaluate predictor_evaluate(predictor_eval_config) ```