?在使用TensorFlow的object_detection模塊問題記錄：

• 配置：window10
• tensorflow-gpu
• protoc3.8版本下載地址：https://github.com/protocolbuffers/protobuf/releases

1. ?ImportError: No module named 'object_detection' 問題：

①將自己下載的models-master模塊添加進去系統環境變量

②在F:\Anaconda\envs\自己環境下的\Lib\site-packages ?這個文件夾目錄下，寫一個.pth文件，內容為兩條路徑

2.protoc.exe運行報錯：

同樣，將protoc.exe添加進系統環境變量

3."protoc object_detection/protos/*.proto --python_out=."命令錯誤：

object_detection/protos/*.proto: No such file or directory

4.cannot import name 'anchor_generator_pb2' from 'object_detection.protos

問題3和問題4都是屬于下面對應的一系列*pb2.py文件沒有生成成功

解決方法：

我的是protoc3.8版本，網上說下載protoc3.4版本就不會報錯，但是我的還是有問題，最后我在github的issues找到了一個解決方法：

https://github.com/tensorflow/models/issues/2930

就是一個一個的CMD執行（直接復制下面的30行代碼到CMD可以一次性全執行完）把 *.proto文件執行生成 ***pb2.py文件。

方便復制粘貼直接貼上：

            
              protoc object_detection/protos/anchor_generator.proto --python_out=.
protoc object_detection/protos/argmax_matcher.proto --python_out=.
protoc object_detection/protos/bipartite_matcher.proto --python_out=.
protoc object_detection/protos/box_coder.proto --python_out=.
protoc object_detection/protos/box_predictor.proto --python_out=.
protoc object_detection/protos/calibration.proto --python_out=.
protoc object_detection/protos/eval.proto --python_out=.
protoc object_detection/protos/faster_rcnn.proto --python_out=.
protoc object_detection/protos/faster_rcnn_box_coder.proto --python_out=.
protoc object_detection/protos/grid_anchor_generator.proto --python_out=.
protoc object_detection/protos/hyperparams.proto --python_out=.
protoc object_detection/protos/image_resizer.proto --python_out=.
protoc object_detection/protos/input_reader.proto --python_out=.
protoc object_detection/protos/keypoint_box_coder.proto --python_out=.
protoc object_detection/protos/losses.proto --python_out=.
protoc object_detection/protos/matcher.proto --python_out=.
protoc object_detection/protos/mean_stddev_box_coder.proto --python_out=.
protoc object_detection/protos/model.proto --python_out=.
protoc object_detection/protos/multiscale_anchor_generator.proto --python_out=.
protoc object_detection/protos/optimizer.proto --python_out=.
protoc object_detection/protos/pipeline.proto --python_out=.
protoc object_detection/protos/post_processing.proto --python_out=.
protoc object_detection/protos/preprocessor.proto --python_out=.
protoc object_detection/protos/region_similarity_calculator.proto --python_out=.
protoc object_detection/protos/square_box_coder.proto --python_out=.
protoc object_detection/protos/ssd.proto --python_out=.
protoc object_detection/protos/ssd_anchor_generator.proto --python_out=.
protoc object_detection/protos/string_int_label_map.proto --python_out=.
protoc object_detection/protos/train.proto --python_out=.
            
          

測試是否成功：

            
              python object_detection/builders/model_builder_test.py
            
          

參考文獻：

object_detection配置相關:https://blog.csdn.net/Zlase/article/details/78734138