VINOD KUMAR DEVARAMPATI comments

Results 5 comments of


                                            VINOD KUMAR DEVARAMPATI

ckpt to pb

--output_layer=model_0/feature_fusion/Conv_7/Sigmoid,model_0/feature_fusion/concat_3

Image Classification example with TensorRT 7 and TF 2.1 running into problems

use the nvidia tensorflow container nvcr.io/nvidia/tensorflow:20.01-tf2-py3. this is working fine for image classification models although object detection is segmentation fault for NMS.

Object Detection example with TRT7 and TF2.1 issues

I am having different issue for the command : python object_detection.py --input_saved_model_dir $HOME/trt/obj_models/ssd_mobilenet_v2_coco_2018_03_29/saved_model/ --output_saved_model_dir $HOME/trt/obj_out_dir --optimize_offline --data_dir $HOME/trt/coco_data/val2017 --annotation_path $HOME/trt/coco_data/annotations/instances_val2017.json --batch_size 1 --use_trt --mode benchmark --precision FP32 --input_size 640 CUDA...

Object Detection example with TRT7 and TF2.1 issues

@aaroey : is this known issue? I am facing the segmentation issue even in latest Tensorflow container from NGC **20.01-tf1-py3**

Object Detection example with TRT7 and TF2.1 issues

Now I moved to nvcr.io/nvidia/tensorflow:20.02-tf2-py3 and tried with TF object detection models. Here the result for Frcnn. Although it is working, I am seeing lot of latency variation with thermal...