NameError：未定义名称“SSD_FEATURE_EXTRACTOR_CLASS_MAP”

问题描述

链接 Roboflow： https://blog.roboflow.com/train-a-tensorflow2-object-detection-model/

我正在使用 RobotFlow 的 https://colab.research.google.com/drive/1sLqFKVV94wm-lglFq_0kGo2ciM0kecWD#scrollTo=7Vz2vJeCCyZR&uniqifier=1 来检测图像，但这是一个错误。

我使用的系统要求： Ubuntu 20.04 张量流 2 ssd_mobilenet_v2_fpnlite_640x640_coco17_tpu-8

我遇到bug的命令代码：

import pathlib

filenames = list(pathlib.Path(work_dir + '/training/').glob('*.index'))

filenames.sort()
print(filenames)

#recover our saved model
pipeline_config = pipeline_file
#generally you want to put the last ckpt from training in here
model_dir = str(filenames[-1]).replace('.index','')
configs = config_util.get_configs_from_pipeline_file(pipeline_config)
model_config = configs['model']
detection_model = model_builder.build(
      model_config=model_config,is_training=False)

# Restore checkpoint
ckpt = tf.compat.v2.train.Checkpoint(
      model=detection_model)
ckpt.restore(os.path.join(str(filenames[-1]).replace('.index','')))


def get_model_detection_function(model):
  """Get a tf.function for detection."""

  @tf.function
  def detect_fn(image):
    """Detect objects in image."""

    image,shapes = model.preprocess(image)
    prediction_dict = model.predict(image,shapes)
    detections = model.postprocess(prediction_dict,shapes)

    return detections,prediction_dict,tf.reshape(shapes,[-1])

  return detect_fn

detect_fn = get_model_detection_function(detection_model)

如何修复那个错误？

解决方法

暂无找到可以解决该程序问题的有效方法，小编努力寻找整理中！

如果你已经找到好的解决方法，欢迎将解决方案带上本链接一起发送给小编。

小编邮箱:dio#foxmail.com (将#修改为@）