Error in Roboflow-TensorFlow2-Object-Detection.ipynb

Search before asking

• I have searched the Roboflow Notebooks issues and found no similar bug report.

Notebook name

Roboflow-TensorFlow2-Object-Detection.ipynb

Bug

Environment

Google Colab

Minimal Reproducible Example

#prepare
pipeline_fname = '/content/models/research/deploy/' + base_pipeline_file
fine_tune_checkpoint = '/content/models/research/deploy/' + model_name + '/checkpoint/ckpt-0'

Update the path to your label map file

label_map_pbtxt_fname = '/content/models/research/deploy/Beyond-Vision-Detection-1/train/cells_label_map.pbtxt' # Adjust this path if necessary

def get_num_classes(pbtxt_fname):
from object_detection.utils import label_map_util
label_map = label_map_util.load_labelmap(pbtxt_fname)
categories = label_map_util.convert_label_map_to_categories(
label_map, max_num_classes=90, use_display_name=True)
category_index = label_map_util.create_category_index(categories)
return len(category_index.keys())
num_classes = get_num_classes(label_map_pbtxt_fname)

Additional

No response

Are you willing to submit a PR?

• Yes I'd like to help by submitting a PR!

Open Roboflow-TensorFlow2-Object-Detection.ipynb in Google Colab and run the reported get_num_classes example using the label map path shown in the issue. Compare the failure with the attached screenshot and trace the notebook cell that loads the label map. Done means the affected object-detection setup runs without the reported error.