Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.

Graph contains 0 node after executing

yu__jia
Beginner
455 Views

Hi, everyone, I converted my trained VGG16 model parameters .meta, index, data to .pb format by freezing, and then reported the following error when performing model optimization

 

python mo_tf.py --input_model E:\VGG16\FLOPS_unchanged\train_logs_vgg16_layers_1\frozen_model.pb --batch 1 --data_type FP16 --output_dir E:\VGG16\FLOPS_unchanged\train_logs_vgg16_layers_1

E1130 21:17:00.961202 10816 main.py:307] Exception occurred during running replacer "REPLACEMENT_ID" (<class 'extensions.front.output_cut.OutputCut'>): Graph contains 0 node after executing <class 'extensions.front.output_cut.OutputCut'>. It considered as error because resulting IR will be empty which is not usual

 

However when I use the following command,

python mo_tf.py --input_meta_graph E:\VGG16\FLOPS_unchanged\train_logs_vgg16_layers_1\model.ckpt-951.meta --batch 1 --data_type FP16

I get another error:

E1130 21:49:50.934771   504 main.py:307] Unexpected exception happened during extracting attributes for node case/cond/is_jpeg/Substr/Switch.
Original exception message: 'ascii' codec can't decode byte 0xff in position 0: ordinal not in range(128)

What should I do ? Thanks.

0 Kudos
0 Replies
Reply