ImportError：无法导入名称“model_lib_v2”我正在使用 Colab

Question

我正在尝试训练 TF2 进行对象检测。当我运行 model_main_tf2.py

!python model_main_tf2.py --pipeline_config_path=training/ssd_efficientdet_d0_512x512_coco17_tpu-8.config --model_dir=training --alsologtostderr

我收到以下错误：

2021-02-21 16:46:31.616633: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.10.1
Traceback (most recent call last):
  File "model_main_tf2.py", line 32, in <module>
    from object_detection import model_lib_v2
ImportError: cannot import name 'model_lib_v2'

如何导入？我使用 Colab 并完成了很多交易。我不希望它从一开始就被抹去或破坏。你有什么意见？

COLAB 代码：

from google.colab import drive
drive.mount('/content/gdrive')

%cd /content/gdrive/MyDrive/Yeni/Object_detection/models-master/research/object_detection

!python generate_tfrecord.py --csv_input=images/train_labels.csv --image_dir=images/train --output_path=train.record

!python generate_tfrecord.py --csv_input=images/test_labels.csv --image_dir=images/test --output_path=test.record

!python generate_labelmap.py

%cd /content/gdrive/MyDrive/Yeni/Object_detection/models-master/research/object_detection

!python model_main_tf2.py --pipeline_config_path=training/ssd_efficientdet_d0_512x512_coco17_tpu-8.config --model_dir=training --alsologtostderr

和 model_main_tf2.py 代码：

r"""Creates and runs TF2 object detection models.

For local training/evaluation run:
PIPELINE_CONFIG_PATH=path/to/pipeline.config
MODEL_DIR=/tmp/model_outputs
NUM_TRAIN_STEPS=10000
SAMPLE_1_OF_N_EVAL_EXAMPLES=1
python model_main_tf2.py -- \
  --model_dir=$MODEL_DIR --num_train_steps=$NUM_TRAIN_STEPS \
  --sample_1_of_n_eval_examples=$SAMPLE_1_OF_N_EVAL_EXAMPLES \
  --pipeline_config_path=$PIPELINE_CONFIG_PATH \
  --alsologtostderr
"""
from absl import flags
import tensorflow.compat.v2 as tf
from object_detection import model_lib_v2

flags.DEFINE_string('pipeline_config_path', None, 'Path to pipeline config '
                    'file.')
flags.DEFINE_integer('num_train_steps', None, 'Number of train steps.')
flags.DEFINE_bool('eval_on_train_data', False, 'Enable evaluating on train '
                  'data (only supported in distributed training).')
flags.DEFINE_integer('sample_1_of_n_eval_examples', None, 'Will sample one of '
                     'every n eval input examples, where n is provided.')
flags.DEFINE_integer('sample_1_of_n_eval_on_train_examples', 5, 'Will sample '
                     'one of every n train input examples for evaluation, '
                     'where n is provided. This is only used if '
                     '`eval_training_data` is True.')
flags.DEFINE_string(
    'model_dir', None, 'Path to output model directory '
                       'where event and checkpoint files will be written.')
flags.DEFINE_string(
    'checkpoint_dir', None, 'Path to directory holding a checkpoint.  If '
    '`checkpoint_dir` is provided, this binary operates in eval-only mode, '
    'writing resulting metrics to `model_dir`.')

flags.DEFINE_integer('eval_timeout', 3600, 'Number of seconds to wait for an'
                     'evaluation checkpoint before exiting.')

flags.DEFINE_bool('use_tpu', False, 'Whether the job is executing on a TPU.')
flags.DEFINE_string(
    'tpu_name',
    default=None,
    help='Name of the Cloud TPU for Cluster Resolvers.')
flags.DEFINE_integer(
    'num_workers', 1, 'When num_workers > 1, training uses '
    'MultiWorkerMirroredStrategy. When num_workers = 1 it uses '
    'MirroredStrategy.')
flags.DEFINE_integer(
    'checkpoint_every_n', 1000, 'Integer defining how often we checkpoint.')
flags.DEFINE_boolean('record_summaries', True,
                     ('Whether or not to record summaries during'
                      ' training.'))

FLAGS = flags.FLAGS


def main(unused_argv):
  flags.mark_flag_as_required('model_dir')
  flags.mark_flag_as_required('pipeline_config_path')
  tf.config.set_soft_device_placement(True)

  if FLAGS.checkpoint_dir:
    model_lib_v2.eval_continuously(
        pipeline_config_path=FLAGS.pipeline_config_path,
        model_dir=FLAGS.model_dir,
        train_steps=FLAGS.num_train_steps,
        sample_1_of_n_eval_examples=FLAGS.sample_1_of_n_eval_examples,
        sample_1_of_n_eval_on_train_examples=(
            FLAGS.sample_1_of_n_eval_on_train_examples),
        checkpoint_dir=FLAGS.checkpoint_dir,
        wait_interval=300, timeout=FLAGS.eval_timeout)
  else:
    if FLAGS.use_tpu:
      # TPU is automatically inferred if tpu_name is None and
      # we are running under cloud ai-platform.
      resolver = tf.distribute.cluster_resolver.TPUClusterResolver(
          FLAGS.tpu_name)
      tf.config.experimental_connect_to_cluster(resolver)
      tf.tpu.experimental.initialize_tpu_system(resolver)
      strategy = tf.distribute.experimental.TPUStrategy(resolver)
    elif FLAGS.num_workers > 1:
      strategy = tf.distribute.experimental.MultiWorkerMirroredStrategy()
    else:
      strategy = tf.compat.v2.distribute.MirroredStrategy()

    with strategy.scope():
      model_lib_v2.train_loop(
          pipeline_config_path=FLAGS.pipeline_config_path,
          model_dir=FLAGS.model_dir,
          train_steps=FLAGS.num_train_steps,
          use_tpu=FLAGS.use_tpu,
          checkpoint_every_n=FLAGS.checkpoint_every_n,
          record_summaries=FLAGS.record_summaries)

if __name__ == '__main__':
  tf.compat.v1.app.run()

Answer 1

试试这个

import os
os.environ['PYTHONPATH']+=":/content/models"
os.environ['PYTHONPATH']+=":/content/models/research"

打电话之前

!python model_main_tf2.py --pipeline_config_path=training/ssd_efficientdet_d0_512x512_coco17_tpu-8.config --model_dir=training --alsologtostderr