Tensorflow Object Detection API

1 开发环境搭建

  1.1 Dependencies

# For CPU
pip install tensorflow==1.10
# For GPU
pip install tensorflow-gpu==1.10

pip install --user Cython
pip install --user contextlib2
pip install --user pillow
pip install --user lxml
pip install --user jupyter
pip install --user matplotlib

  1.2 COCO API installation

git clone https://github.com/cocodataset/cocoapi.git
cd cocoapi/PythonAPI
make
cp -r pycocotools <path_to_tensorflow>/models/research/

  1.3 Protobuf Compilation

# From tensorflow/models/research/
protoc object_detection/protos/*.proto --python_out=.

  1.4 Add Libraries to PYTHONPATH

# From tensorflow/models/research/
export PYTHONPATH=$PYTHONPATH:`pwd`:`pwd`/slim

  1.5 Testing the Installation

python object_detection/builders/model_builder_test.py

 

 

Error

ValueError: Tensor conversion requested dtype string for Tensor with dtype float32: 'Tensor("arg0:0", shape=(), dtype=float32, device=/device:CPU:0)'