when i try to run inference on a batch of images the results are very different

[ernstgoyer]

e.g.
batch_size 1 -- correct prediction with 94.8%
for the same image with batch_size 2
prediction goes down to 29%
finetuned model resnet_v2_101 with 4 classes
training batch_size was 4
tensorflow 1.14
ubuntu 18.04

[tensorflowbutler]

Thank you for your post. We noticed you have not filled out the following field in the issue template. Could you update them if they are relevant in your case, or leave them as N/A? Thanks.
What is the top-level directory of the model you are using
Have I written custom code
OS Platform and Distribution
TensorFlow installed from
TensorFlow version
Bazel version
CUDA/cuDNN version
GPU model and memory
Exact command to reproduce

[ernstgoyer]

System information
What is the top-level directory of the model you are using: slim
Have I written custom code (as opposed to using a stock example script provided in TensorFlow): yes
OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Linux Ubuntu 18.04
TensorFlow installed from (source or binary): source
TensorFlow version (use command below): 1.13.1
Bazel version (if compiling from source):
CUDA/cuDNN version: 10.0
GPU model and memory: Nvidia Titan RTX
Exact command to reproduce: N/A