Model accuracy(inference) is almost zero for resnet50 using tensorflow cpp api
I am using tensorflow cpp api to do inference for imagenet 2012 validation dataset using resnet50 model. I have saved the pre-trained model(on resnet50) using model=tf.keras.applications.ResNet50(weights='imagenet') save_path = '/home/parveen/Models/models/resnet50_v1_saved_model' tf.saved_model.save(model, save_path) Saved model is in .pb format.