CODEWITHSUNDEEP
tensorflowtensorflow-servingimagenet
Shuhei Kishi
Shuhei Kishi

Reputation: 109

How to use model.ckpt and inception v-3 to predict images?

Now I'm in front of the problem about inception v-3 and checkpoint data. I have been tackling with updating inception-v3's checkpoint data by my images, reading the git page below and succeeded to make new checkpoint data.

https://github.com/tensorflow/models/tree/master/inception

I thought at first just by little change of the code, I can use those checkpoint data to recognise new image datas like the below url.

https://www.tensorflow.org/versions/master/tutorials/image_recognition/index.html

I thought at first that "classify.py" or something reads the new check point datas and just by "python classify.py -image something.png", the program recognises the image data. But It doesn't.... I really need a help. thanks.

Upvotes: 1

Views: 3392

Answers (2)

Elena0987
Elena0987

Reputation: 101

To have input .pb file, during training, import also tf.train.write_graph(sess.graph.as_graph_def(), 'path_to_folder', 'input_graph.pb',False)

If you have downloaded the inception v3 source code, in the inception_train.py, add the line I wrote above, under saver.save(sess, checkpoint_path, global_step=step). (Where you save the checkpoint/s)

Hope this helps!

Upvotes: 4

Pete Warden
Pete Warden

Reputation: 2878

To use your checkpoints and model in something like the label_image example, you'll need to run the tensorflow/python/tools/freeze_graph script to convert your variables into constants stored inside the GraphDef. That's how we created the graph file used in that sample code, for example.

Upvotes: 3

Related Questions