No gradient provided for any variable error

[maithal]

Hi,

I am trying to run this attack method but I am facing an issue in training the mnist model. I am constantly getting the ValueError stating the Adam optimizer isn't receiving any gradient. Please find the error below:

Traceback (most recent call last):
File "/home/Documents/Query-based-blackbox-attack/my_train.py", line 59, in
main(args.model, args.type)
File "/home/Documents/Query-based-blackbox-attack/my_train.py", line 36, in main
tf_train(x, y, model, X_train, Y_train, data_gen, None, None)
File "/home/Documents/Query-based-blackbox-attack/tf_utils.py", line 86, in tf_train
optimizer = tf.train.AdamOptimizer().minimize(loss)
File "/home/Desktop/my_project/venv/lib/python3.6/site-packages/tensorflow/python/training/optimizer.py", line 421, in minimize
([str(v) for _, v in grads_and_vars], loss))
ValueError: No gradients provided for any variable, check your graph for ops that do not support gradients, between variables ["<tf.Variable 'convolution2d_1_W:0' shape=(8, 8, 1, 64) dtype=float32_ref>", "<tf.Variable 'convolution2d_1_b:0' shape=(64,) dtype=float32_ref>", "<tf.Variable 'convolution2d_2_W:0' shape=(6, 6, 64, 128) dtype=float32_ref>", "<tf.Variable 'convolution2d_2_b:0' shape=(128,) dtype=float32_ref>", "<tf.Variable 'convolution2d_3_W:0' shape=(5, 5, 128, 128) dtype=float32_ref>", "<tf.Variable 'convolution2d_3_b:0' shape=(128,) dtype=float32_ref>", "<tf.Variable 'dense_1_W:0' shape=(128, 10) dtype=float32_ref>", "<tf.Variable 'dense_1_b:0' shape=(10,) dtype=float32_ref>"] and loss Tensor("Mean:0", shape=(), dtype=float32, device=/device:GPU:0).

Please help me with this error.