Create an image classifier
TF-Slim provides state of the art image classification networks, including networks pretrained on ImageNet. TF-Slim is the basis for both the TensorFlow Object Detection API and TensorFlow Hub image classification modules.
TF-Slim is deprecated and no longer supported by the TensorFlow team. Nonetheless, it’s an important library that provides state of the art pretrained networks used by teams and engineers from Google and other organizations.
Create a project
Initialize a project environment
When working with projects, we recommend using a Guild environment to isolate project runs and installed Python packages. This ensures that work in one project does not conflict with work in other projects.
At a command prompt, ensure that you’re in the project directory:
Use the init command to initialize a Guild environment:
Guild prompts you before initialzing the environment in the project
env directory with the default Python runtime and TensorFlow version
for your system.
Enter to confirm.
Guild creates a new Python virtual environment in the project
env, which contains the Python runtime, installed
Python packages, and project Guild home.
A project environment must be activated using the operation system
Activate the project environment:
When an environment is activated in a command console, the command
prompt shows the environment name in the format
(<env name>) <default
prompt>. The environment name is the project directory name by
default but can be set using the
‑‑name when running guild
You must activate the project environment using
guild‑env each time you open a new command console for project
Verify that the environment is activated using the check command:
Guild shows environment details, including the location of Guild
home, which is identified by
guild_home in the
Confirm that the path for
guild_home is in the project directory
env/.guild. If it is in a different location, verify the steps
above to ensure that your project environment is initialized and