efficientdet_d4_coco17_tpu-32 is exclusive only for TPU or can use with GPU

[DevLob-zz]

Prerequisites

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

• [efficientdet_d4_coco17_tpu-32 ] I am using the latest TensorFlow Model Garden release and TensorFlow 2.
• [ Yes] I am reporting the issue to the correct repository. (Model Garden official or research directory)
• [ Yes] I checked to make sure that this issue has not been filed already.

1. The entire URL of the file you are using

https://github.com/tensorflow/models/tree/master/official/...

2. Describe the bug

while trying to learn my dataset with efficientdet_d4_coco17_tpu-32 I have only GPU and this raised an error with me

From merging shape 0 with other shapes. for '{{node EfficientDet-D4/bifpn/node_02/1_dn_lvl_6/combine/stack}} = Pack[N=2, T=DT_FLOAT, axis=-1](EfficientDet-D4/bifpn/node_00/0_up_lvl_6/input_0_up_lvl_5/downsample_max_x2/MaxPool, EfficientDet-D4/bifpn/node_02/1_dn_lvl_6/input_0_up_lvl_7/nearest_neighbor_upsampling_x2/nearest_neighbor_upsampling/Reshape)' with input shapes: [1,13,13,224], [1,14,14,224].

is this should only with TPU

3. Steps to reproduce

Steps to reproduce the behavior.

as mentioned in the Bug

4. Expected behavior

Is this can be useable by GPU

5. Additional context

Include any logs that would be helpful to diagnose the problem.

6. System information

• Windows 10
• TensorFlow installed from (source or binary):Source
• TensorFlow version (use command below):2.2.0
• Python version:3.6.12
• Bazel version (if compiling from source):
• GCC/Compiler version (if compiling from source):
• CUDA/cuDNN version:10.1
• GPU model and memory: GeForce GTX 1660 Ti , 6 GB