无法导入模型model_main（从object_detection导入model_main）

问题描述 投票：0回答：1

我正在尝试从 object_detection 导入包 model_main 但它抛出了类似的错误

Traceback (most recent call last):   File "../LearningSpace/ObJTEST01/main.py", line 9, in <module>     from object_detection import model_main   File "../anaconda3/envs/ObJTESTV01/lib/python3.10/site-packages/object_detection/model_main.py", line 26, in <module>     from object_detection import model_lib   File "../anaconda3/envs/ObJTESTV01/lib/python3.10/site-packages/object_detection/model_lib.py", line 27, in <module>     from object_detection import eval_util   File "../anaconda3/envs/ObJTESTV01/lib/python3.10/site-packages/object_detection/eval_util.py", line 35, in <module>     slim = tf.contrib.slim AttributeError: module 'tensorflow' has no attribute 'contrib'

我的代码：

import tensorflow as tf
from object_detection.utils import config_util
from object_detection.protos import pipeline_pb2
from google.protobuf import text_format
import os
import requests
import shutil
import tarfile
from object_detection import model_main

CUSTOM_MODEL_NAME = 'my_ssd_mobnet'
PRETRAINED_MODEL_NAME = 'ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8'
PRETRAINED_MODEL_URL = 'http://download.tensorflow.org/models/object_detection/tf2/20200711/ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8.tar.gz'
TF_RECORD_SCRIPT_NAME = 'generate_tfrecord.py'
LABEL_MAP_NAME = 'label_map.pbtxt'

paths = {
    'WORKSPACE_PATH': os.path.join('Tensorflow', 'workspace'),
    'SCRIPTS_PATH': os.path.join('Tensorflow','scripts'),
    'APIMODEL_PATH': os.path.join('Tensorflow','models'),
    'ANNOTATION_PATH': os.path.join('Tensorflow', 'workspace','annotations'),
    'IMAGE_PATH': os.path.join('Tensorflow', 'workspace','images'),
    'MODEL_PATH': os.path.join('Tensorflow', 'workspace','models'),
    'PRETRAINED_MODEL_PATH': os.path.join('Tensorflow', 'workspace','pre-trained-models'),
    'CHECKPOINT_PATH': os.path.join('Tensorflow', 'workspace','models',CUSTOM_MODEL_NAME),
    'OUTPUT_PATH': os.path.join('Tensorflow', 'workspace','models',CUSTOM_MODEL_NAME, 'export'),
    'TFJS_PATH':os.path.join('Tensorflow', 'workspace','models',CUSTOM_MODEL_NAME, 'tfjsexport'),
    'TFLITE_PATH':os.path.join('Tensorflow', 'workspace','models',CUSTOM_MODEL_NAME, 'tfliteexport'),
    'PROTOC_PATH':os.path.join('Tensorflow','protoc')
 }

files = {
    'PIPELINE_CONFIG':os.path.join('Tensorflow', 'workspace','models', CUSTOM_MODEL_NAME, 'pipeline.config'),
    'TF_RECORD_SCRIPT': os.path.join(paths['SCRIPTS_PATH'], TF_RECORD_SCRIPT_NAME),
    'LABELMAP': os.path.join(paths['ANNOTATION_PATH'], LABEL_MAP_NAME)
}

for path in paths.values():
    if not os.path.exists(path):
        if os.name == 'posix' or os.name == 'nt':  # Checks if the OS is POSIX-compliant (Unix-like) or Windows (nt)
            os.makedirs(path, exist_ok=True)  # Creates the directory/directories if they do not exist




# def download_file(url, local_filename):
#     with requests.get(url, stream=True) as r:
#         r.raise_for_status()
#         with open(local_filename, 'wb') as f:
#             for chunk in r.iter_content(chunk_size=8192):
#                 f.write(chunk)
#     return local_filename
#
#
# if os.name == 'posix' or os.name == 'nt':
#     local_filename = PRETRAINED_MODEL_NAME + '.tar.gz'
#     download_file(PRETRAINED_MODEL_URL, local_filename)
#     target_path = os.path.join(paths['PRETRAINED_MODEL_PATH'], local_filename)
#     shutil.move(local_filename, target_path)
#     with tarfile.open(target_path) as tar:
#         tar.extractall(path=paths['PRETRAINED_MODEL_PATH'])
#     os.remove(target_path)


labels = [{'name':'licence', 'id':1}]

with open(files['LABELMAP'], 'w') as f:
    for label in labels:
        f.write('item { \n')
        f.write('\tname:\'{}\'\n'.format(label['name']))
        f.write('\tid:{}\n'.format(label['id']))
        f.write('}\n')

#it is done so no needed
    # import os
    # import subprocess
    #
    # # Assuming paths and files dictionaries are defined as before
    #
    # # Check if the TF_RECORD_SCRIPT does not exist
    # if not os.path.exists(files['TF_RECORD_SCRIPT']):
    #     # Define the command to clone the GitHub repository
    #     clone_command = f"git clone https://github.com/nicknochnack/GenerateTFRecord {paths['SCRIPTS_PATH']}"
    #
    #     # Execute the command
    #     subprocess.run(clone_command, shell=True, check=True)


# import shutil
# import os
#
# # Assuming paths and PRETRAINED_MODEL_NAME are defined as before
#
# # Construct the source path of the pipeline.config file
# source_path = os.path.join(paths['PRETRAINED_MODEL_PATH'], PRETRAINED_MODEL_NAME, 'pipeline.config')
#
# # Construct the destination path for the pipeline.config file
# destination_path = os.path.join(paths['CHECKPOINT_PATH'])
#
# # Copy the file from source to destination
# shutil.copy(source_path, destination_path)
#
# print(f"Copied pipeline.config to {destination_path}")


# def read_file_example(file_path):
#     with tf.io.gfile.GFile(file_path, "r") as f:
#         contents = f.read()
#     return contents
#
# config = read_file_example(files['PIPELINE_CONFIG'])
#
# pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
# with tf.io.gfile.GFile(files['PIPELINE_CONFIG'], "r") as f:
#     proto_str = f.read()
#     text_format.Merge(proto_str, pipeline_config)
# pipeline_config.model.ssd.num_classes = len(labels)
# pipeline_config.train_config.batch_size = 4
# pipeline_config.train_config.fine_tune_checkpoint = os.path.join(paths['PRETRAINED_MODEL_PATH'], PRETRAINED_MODEL_NAME, 'checkpoint', 'ckpt-0')
# pipeline_config.train_config.fine_tune_checkpoint_type = "detection"
# pipeline_config.train_input_reader.label_map_path= files['LABELMAP']
# pipeline_config.train_input_reader.tf_record_input_reader.input_path[:] = [os.path.join(paths['ANNOTATION_PATH'], 'train.record')]
# pipeline_config.eval_input_reader[0].label_map_path = files['LABELMAP']
# pipeline_config.eval_input_reader[0].tf_record_input_reader.input_path[:] = [os.path.join(paths['ANNOTATION_PATH'], 'test.record')]
#
# config_text = text_format.MessageToString(pipeline_config)
# with tf.io.gfile.GFile(files['PIPELINE_CONFIG'], "wb") as f:
#     f.write(config_text)


# TRAINING_SCRIPT = os.path.join(paths['APIMODEL_PATH'], 'research', 'object_detection', 'model_main_tf2.py')
# command = "python {} --model_dir={} --pipeline_config_path={} --num_train_steps=10000".format(TRAINING_SCRIPT, paths['CHECKPOINT_PATH'],files['PIPELINE_CONFIG'])
import subprocess

# Define the command as a string
command = (
    "--model_dir=Tensorflow/workspace/models/my_ssd_mobnet "
    "--pipeline_config_path=Tensorflow/workspace/models/my_ssd_mobnet/pipeline.config "
    "--num_train_steps=10000"
)

套餐：

pip install tensorflow-macos

pip install tensorflow-object-detection-api

我需要使用命令 => command = ( "--model_dir=Tensorflow/workspace/models/my_ssd_mobnet " "--pipeline_config_path=Tensorflow/workspace/models/my_ssd_mobnet/pipeline.config " "--num_train_steps= 来训练模型10000”）我需要训练模型，但我无法使用这些包我应该做什么

我尝试了所有方法都不起作用，所以有人可以帮助我吗

python tensorflow tensorflow2.0 object-detection object-detection-api
1个回答
0
投票

tf.contrib.slim
不是 TensorFlow 2 的一部分，如 TF 文档中所述：https://www.tensorflow.org/guide/migrate。

如果您想使用此特定代码，请找出它支持哪个版本的 TensorFlow。删除当前版本，然后安装正确的版本 (1.x)。

您也可以坚持使用 TF 2.x 并从此处安装 tf-slim：https://github.com/google-research/tf-slim 例如：

pip install git+https://github.com/google-research/tf-slim.git

最新问题
© www.soinside.com 2019 - 2024. All rights reserved.