Purvang Lapsiwala

nfnets: training error

1

First of all, thank you for great publish nfnets. I have started deeging deep in to implementation, where I have some questions. Unfortunately I am not able to run experiment.py....

Error when doing inference using tf-trt converted frozen model

1

**Description** A clear and concise description of what the bug is. Object detection model trained using tensorflow 1.14. I am able to deploy frozen graph to triton server and perform...

Memory leak: tf1 trained saved_model in tf2 for prediction

6

# Prerequisites Please answer the following questions for yourself before submitting an issue. - [ ] I am using the latest TensorFlow Model Garden release and TensorFlow 2. - [...

Error model predict method

9

### 🐛 Describe the bug After successful training, I am trying to do prediction on locally stored image but getting following error. ``` [2023-06-13 04:18:01] INFO - checkpoint_utils.py - Successfully...

Much Higher inference time using converted onnx model

1

# Ask a Question ### Question ``` I am converting tensorflow 1.14 trained tensorflow object detection model to onnx and running inference. I am using tensorflow/tensorflow:1.14.0-gpu-py3 docker image. using onnxruntime-gpu==1.1...

json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 1 column 2 (char 1)

3

**Describe the bug** Hi, Trying to run joebiden.py from tutorial directory and getting above mentioned error. **To Reproduce** Steps to reproduce the behavior: For macos, changed headers = { "User-Agent":...

I followed guide from "https://on-demand.gputechconf.com/gtc-cn/2019/pdf/CN9456/presentation.pdf". I am able to produce tensorrt based graph def but when I load and run on to image using converted graph, due to key error,...