Eager Few Shot Object Detection Colab notebook not wokring

[rickwierenga]

Prerequisites

Please answer the following questions for yourself before submitting an issue.

• [ ] I am using the latest TensorFlow Model Garden release and TensorFlow 2. (tutorial recommends 2.2.0)
• [x] I am reporting the issue to the correct repository. (Model Garden official or research directory)
• [x] I checked to make sure that this issue has not already been filed.

1. The entire URL of the file you are using

https://github.com/tensorflow/models/blob/master/research/object_detection/colab_tutorials/eager_few_shot_od_training_tf2_colab.ipynb

2. Describe the bug

Colab tutorial does not work. Cell starting with tf.keras.backend.clear_session() gives the following error.

Building model and restoring weights for fine-tuning...
---------------------------------------------------------------------------
UnimplementedError                        Traceback (most recent call last)
[<ipython-input-17-5906ad4ff27f>](https://lhmbecrxdw-496ff2e9c6d22116-0-colab.googleusercontent.com/outputframe.html?vrz=colab-20220922-060051-RC00_476055999#) in <module>
     37 # Run model through a dummy image so that variables are created
     38 image, shapes = detection_model.preprocess(tf.zeros([1, 640, 640, 3]))
---> 39 prediction_dict = detection_model.predict(image, shapes)
     40 _ = detection_model.postprocess(prediction_dict, shapes)
     41 print('Weights restored!')

3 frames
[/usr/local/lib/python3.7/dist-packages/object_detection/models/ssd_resnet_v1_fpn_keras_feature_extractor.py](https://lhmbecrxdw-496ff2e9c6d22116-0-colab.googleusercontent.com/outputframe.html?vrz=colab-20220922-060051-RC00_476055999#) in _extract_features(self, preprocessed_inputs)
    222 
    223     image_features = self.classification_backbone(
--> 224         ops.pad_to_multiple(preprocessed_inputs, self._pad_to_multiple))
    225 
    226     feature_block_list = []

UnimplementedError: Exception encountered when calling layer "conv1_conv" "                 f"(type Conv2D).

{{function_node __wrapped__Conv2D_device_/job:localhost/replica:0/task:0/device:GPU:0}} DNN library is not found. [Op:Conv2D]

Call arguments received by layer "conv1_conv" "                 f"(type Conv2D):
  • inputs=tf.Tensor(shape=(1, 646, 646, 3), dtype=float32)

3. Steps to reproduce

1 download notebook 2 upload notebook to colab 3 hit run

4. Expected behavior

run without error

5. Additional context

-

6. System information

default colab, latest (?)

• OS Platform and Distribution (e.g., Linux Ubuntu 16.04):
• Mobile device name if the issue happens on a mobile device:
• TensorFlow installed from (source or binary):
• TensorFlow version (use command below):
• Python version:
• Bazel version (if compiling from source):
• GCC/Compiler version (if compiling from source):
• CUDA/cuDNN version:
• GPU model and memory:

[rickwierenga]

This fixes it.

!apt install --allow-change-held-packages libcudnn8=8.1.0.77-1+cuda11.2

[google-ml-butler[bot]]

Are you satisfied with the resolution of your issue? Yes No

[sineeli]

As the problem is resolved closing the issue.

Thank you.