1

I am working with https://github.com/tensorflow/models/tree/master/research/object_detection, where I have loaded the following model using pipeline config:

import tensorflow as tf
from object_detection.utils import config_util
from object_detection.builders import model_builder

tf.keras.backend.clear_session()
pipeline_config = 'models/research/object_detection/configs/tf2/ssd_resnet50_v1_fpn_640x640_coco17_tpu-8.config'
configs = config_util.get_configs_from_pipeline_file(pipeline_config)
model_config = configs['model']
detection_model = model_builder.build(model_config=model_config, is_training=False)

detection_model.summary()  # AttributeError: 'SSDMetaArch' object has no attribute 'summary'

I have also tried restoring the weights / variables, but to no avail

image, shapes = detection_model.preprocess(tf.zeros([1, 640, 640, 3]))
prediction_dict = detection_model.predict(image, shapes)
detection_model.postprocess(prediction_dict, shapes)

for variable in detection_model.variables:
    variable.summary()  # Throws AttributeError, since none of these have .summary()

I have tensorflow version 2.10.1.

Improve this question
Related questions
1
Different image sizes as inputs for Tensorflow 2 Object Detection API
3
How do you export a frozen inference graph in Tensorflow 2.x Object Detection API?
5
Early stopping Tensorflow object detection API
Load 2 more related questions Show fewer related questions

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.