运行train_resnet.py时报错

[cly2625]

ValueError: No gradients provided for any variable: ["<tf.Variable 'visual_fc1/weights:0' shape=(36, 300) dtype=float32_ref>", "<tf.Variable 'visual_fc1/biases:0' shape=(300,) dtype=float32_ref>"]. 问题报错在代码时204行中hash_train_op2 = hash_opt2.apply_gradients(list(zip(hash_grads2, var_list2)), global_step=global_step2) 应该是hash_loss有问题，请问您重新执行是否会有相似问题