Running and Verification

After building and installing TensorFlow 2.13.0, use the built-in test cases to verify its basic functions. This document uses the image recognition test case to verify TensorFlow.

1. Query the installation information.

   1	pip3 list | grep tensorflow

   

   If the command output displays the preceding information, TensorFlow 2.13.0 is installed.

2. Verify the basic function of image recognition in the root directory of the TensorFlow source code, for example, /path/to/tensorflow.

   1 2 3 4

   cd /path/to/tensorflow curl -L "https://storage.googleapis.com/download.tensorflow.org/models/inception_v3_2016_08_28_frozen.pb.tar.gz" | tar -C tensorflow/examples/label_image/data -xz wget -P tensorflow/examples/label_image/data/ https://www.tensorflow.org/images/cropped_panda.jpg --no-check-certificate python3 tensorflow/examples/label_image/label_image.py --image=tensorflow/examples/label_image/data/cropped_panda.jpg

   The command output is:

   

   There is the highest probability that tensorflow/examples/label_image/data/cropped_panda.jpg is identified as a giant panda.

   

   Test reference: https://github.com/tensorflow/tensorflow/blob/v2.13.0/tensorflow/examples/label_image/README.md.