Finetuning Error with PNASNet-5_Large_331

[mumichang]

Prerequisites

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

• [v] I am using the latest TensorFlow Model Garden release and TensorFlow 2.
• [v] I am reporting the issue to the correct repository. (Model Garden official or research directory)
• [v] 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/tree/master/research/slim

2. Describe the bug

Tried to finetune the pre-trained model, PNASNet-5_Large_331 with flowers dataset.
Got the following error,
"Key aux_7/aux_logits/aux_bn0/beta not found in checkpoint"

3. Steps to reproduce

As explained in https://github.com/tensorflow/models/tree/master/research/slim#fine-tuning-a-model-from-an-existing-checkpoint,

python3 train_image_classifier.py
--train_dir=${TRAIN_DIR}
--dataset_dir=${DATASET_DIR}
--dataset_name=flowers
--dataset_split_name=train
--model_name=${MODEL_NAME}
--checkpoint_path=${CHECKPOINT_PATH}
--checkpoint_exclude_scopes=aux_7/aux_logits/FC,final_layer/FC
--trainable_scopes=aux_7/aux_logits/FC,final_layer/FC

4. Expected behavior

May get the following error,
"Key aux_7/aux_logits/aux_bn0/beta not found in checkpoint"

5. Additional context

None

6. System information

• OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Ubuntu 18.04
• Mobile device name if the issue happens on a mobile device:
• TensorFlow installed from (source or binary): source
• TensorFlow version (use command below): 1.15
• Python version: Python 3.6
• Bazel version (if compiling from source): 0.24.1
• GCC/Compiler version (if compiling from source):
• CUDA/cuDNN version: 7.5.0, using rocm
• GPU model and memory: Vega 10 XTX [Radeon Vega Frontier Edition], 16GB