var_list = [v for v in tf.trainable_variables() if v.name.find("conv") != -1]

[953585130]

I tried to modify the code to fine-tune (my own dataset), but it always failed. How should I modify it?

saver = tf.train.Saver(weights.values() + biases.values()) init = tf.global_variables_initializer()

Create a session for running Ops on the Graph.

sess = tf.Session( config=tf.ConfigProto(allow_soft_placement=True) ) sess.run(init) if os.path.isfile(model_filename) and use_pretrained_model: saver.restore(sess, model_filename)

please help!