Very low validation accuracy using imagenet_classification.py
xlvy opened this issue · 0 comments
xlvy commented
Run environment:
-
docker version: nvcr.io/nvidia/tensorflow:20.01-tf2-py3 with tensorflow version 2.0 and TensorRT 7.0
-
Validation TFRecord files: https://github.com/tensorflow/models/blob/master/research/slim/datasets/build_imagenet_data.py
-
Model: TF2.0 Resnet_50 hub model https://tfhub.dev/tensorflow/resnet_50/classification/1
-
preprocess_method: vgg
Why is the accuracy only 0.1%? Is there something wrong?
