Using the Model

Predicting the ages of a set of menhaden scale images

Running the Menhaden Ageing Model is straightforward and only requires two commands: one to pro-process the images and a second to run the age inference model. You will, however, need to modify a configurations.yml file. A sample is provided below, while the contents of this file are explained in more detail in the model options.

Configuration File

A configurations.yml file is an easy way to control model performance. The most important settings in this file to pay attention to are:

The directory containing the scale images to process
The directory where you want the model output file to be written
The directory containing the trained model weights (i.e., the best_model.pth file) and, if desired, the Segment Anything Model weights. If you simply cloned the repo and have not moved anything around, the trained model weights file will be alongside the model script in the scripts subdirectory in the cloned repository. The SAM weights will be wherever you saved them upon downloading them.

Absolute file paths are generally recommended to avoid unintended behavior but will vary from computer to computer.

This YAML file is structured as key: value pairs. The order in which these entries are presented in the file does not matter, but all keys need to be included and match exactly as expected. For example:

configuration.yml

# --------------------------------------------------------------------------------------------
# Configuration for pre-processsing scale images (crop, pad, and normalization)
# --------------------------------------------------------------------------------------------

# -----Paths and general options-----
raw_image_path: "G:/Shared drives/NMFS SEFSC FATES Advanced Technology/BIOLOGY_LIFE_HISTORY_DATA/age_testing/images"
preprocessed_image_path: "G:/Shared drives/NMFS SEFSC FATES Advanced Technology/BIOLOGY_LIFE_HISTORY_DATA/age_testing/cropped"
input_type: ".tif"
output_type: ".jpg"
segment: "sam"

# -----Binary Threshold segmentation parameters-----
binary_threshold: 100

# -----Segment Anything Model (SAM) parameters-----
points_per_side: 16
stability_score_thresh: 0.93
downsample: 0.5
sam_model_type: "vit_b"
sam_weights_path: "C:/Users/matt.grossi/Documents/GitHubRepos/FATES-BLH-OtolithAgeing/Menhaden Scales Aging/Inference Script/sam_vit_b_01ec64.pth"

# -----Cropping and padding parameters-----
pad: 0.2
bottom_pad: 0.4

# -----Normalization options-----
normalization: "clahe"
invert: True

# --------------------------------------------------------------------------------------------
# Configuration for age inference 
# --------------------------------------------------------------------------------------------

# -----Model paths-----
image_path: "G:/Shared drives/NMFS SEFSC FATES Advanced Technology/BIOLOGY_LIFE_HISTORY_DATA/age_testing/cropped"
model_path: "C:/Users/matt.grossi/Documents/GitHubRepos/FATES-BLH-OtolithAgeing/Menhaden Scales Aging/Chapter 2 - Inference on Images/best_model.pth"
out_path: "G:/Shared drives/NMFS SEFSC FATES Advanced Technology/BIOLOGY_LIFE_HISTORY_DATA/age_testing/model_predictions/inference_results.csv"

Running the model

First we need to activate the virtual environment we previously configured. In a terminal window, type:

conda activate scaleageing

Tip

If you named your virtual environment something other than “scaleageing”, invoke that name instead.

Navigate into the directory containing the Scale_Aging_Inference_Script_Image_Only.py script. If you simply cloned the repo and have not moved anything around, this will in the scripts subdirectory in the cloned repository.

Run the model as described in the usage instructions:

python Scale_Raw_Image_Preprocessing.py --config_path <config_dir>
python Scale_Aging_Inference_Script_Image_Only.py --config_path <config_dir>

where <config_dir> is the path to the configuration file containing model settings presented above.