运行时遇到的困惑

[wy-0]

运行时报错， tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [256] vs. [252] [[{{node gradients/logistic_loss_3/mul_grad/BroadcastGradientArgs}}]] 是在代码的 File "train.py", line 118, in main loss = model.train(sess, [user, tgt, hist, mask, label, LEARNING_RATE]) File "/media/sdb2/AAAA_sdb2/zjp/MGNM/MGNM-main/code/model.py", line 79, in train loss, _ = sess.run([self.loss, self.optimizer], feed_dict=feed_dict)

[wy-0]

@lichenliang-whu I want to ask you some questions about the operation. When I am running, I will report an error of " tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [256] vs. [252] [[{{node gradients/logistic_loss_3/mul_grad/BroadcastGradientArgs}}]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "train.py", line 144, in main() File "train.py", line 118, in main loss = model.train(sess, [user, tgt, hist, mask, label, LEARNING_RATE]) File "/media/sdb2/AAAA_sdb2/zjp/MGNM/MGNM-main/code/model.py", line 79, in train loss, _ = sess.run([self.loss, self.optimizer], feed_dict=feed_dict) File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 950, in run run_metadata_ptr) File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1173, in _run feed_dict_tensor, options, run_metadata) File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1350, in _do_run run_metadata) File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1370, in _do_call raise type(e)(node_def, op, message) tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [256] vs. [252] [[node gradients/logistic_loss_3/mul_grad/BroadcastGradientArgs (defined at /media/sdb2/AAAA_sdb2/zjp/MGNM/MGNM-main/code/model.py:60) ]]

Original stack trace for 'gradients/logistic_loss_3/mul_grad/BroadcastGradientArgs': File "train.py", line 144, in main() File "train.py", line 99, in main model = modelTy(item_count, user_count, DIMENSION, BATCH_SIZE, SEQ_LEN, NEG_NUM, HIDDEN_SIZE, NUM_PREFERENCE, NUM_LAYER, SE_NUM) File "/media/sdb2/AAAA_sdb2/zjp/MGNM/MGNM-main/code/model.py", line 301, in init self.build_multi_ce_loss(self.item_eb, user_eb_list) File "/media/sdb2/AAAA_sdb2/zjp/MGNM/MGNM-main/code/model.py", line 60, in build_multi_ce_loss self.optimizer = tf.train.AdamOptimizer(learning_rate=self.lr).minimize(self.loss) File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/training/optimizer.py", line 403, in minimize grad_loss=grad_loss) File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/training/optimizer.py", line 512, in compute_gradients colocate_gradients_with_ops=colocate_gradients_with_ops) File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/ops/gradients_impl.py", line 158, in gradients unconnected_gradients) File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/ops/gradients_util.py", line 731, in _GradientsHelper lambda: grad_fn(op, *out_grads)) File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/ops/gradients_util.py", line 403, in _MaybeCompile return grad_fn() # Exit early File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/ops/gradients_util.py", line 731, in lambda: grad_fn(op, *out_grads)) File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/ops/math_grad.py", line 1044, in _MulGrad rx, ry = gen_array_ops.broadcast_gradient_args(sx, sy) File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/ops/gen_array_ops.py", line 829, in broadcast_gradient_args "BroadcastGradientArgs", s0=s0, s1=s1, name=name) File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper op_def=op_def) File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func return func(*args, **kwargs) File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3616, in create_op op_def=op_def) File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2005, in init self._traceback = tf_stack.extract_stack()

...which was originally created as op 'logistic_loss_3/mul', defined at: File "train.py", line 144, in main() [elided 1 identical lines from previous traceback] File "/media/sdb2/AAAA_sdb2/zjp/MGNM/MGNM-main/code/model.py", line 301, in init self.build_multi_ce_loss(self.item_eb, user_eb_list) File "/media/sdb2/AAAA_sdb2/zjp/MGNM/MGNM-main/code/model.py", line 51, in build_multi_ce_loss loss.append(tf.reduce_sum(tf.nn.sigmoid_cross_entropy_with_logits(labels=tf.reshape(self.label, (-1, )), logits=tf.reshape(logits_tmp, (-1, ))))) File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/ops/nn_impl.py", line 183, in sigmoid_cross_entropy_with_logits relu_logits - logits * labels, File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 884, in binary_op_wrapper return func(x, y, name=name) File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 1180, in _mul_dispatch return gen_math_ops.mul(x, y, name=name) File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/ops/gen_math_ops.py", line 6490, in mul "Mul", x=x, y=y, name=name) File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper op_def=op_def) File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func return func(*args, **kwargs) File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3616, in create_op op_def=op_def) File "/home/ps/anaconda3/envs/zjp-mgnm/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2005, in init self._traceback = tf_stack.extract_stack() ". How to solve this problem? thank you

[KevinXu-01]

Hi, I also ran into the problem. Have you fixed it? If so, could you please share how you fix it? Thank you in advance!

Edited on Aug. 3, 2023: Hi, I fixed this and opened an issue. You can check it and hope it'll help.

[hchchchchchchc]

Hi, I also ran into the problem. Have you fixed it? If so, could you please share how you fix it? Thank you in advance!

Edited on Aug. 3, 2023: Hi, I fixed this and opened an issue. You can check it and hope it'll help.

Hi, what's the meaning of se_num in this model?

[KevinXu-01]

Hi, I also ran into the problem. Have you fixed it? If so, could you please share how you fix it? Thank you in advance! Edited on Aug. 3, 2023: Hi, I fixed this and opened an issue. You can check it and hope it'll help.

Hi, what's the meaning of se_num in this model?

I have no idea actually, but L21 in train.py says, quote, 'don't care this parameter', so I just left it to 0.

[hchchchchchchc]

Hi, I also ran into the problem. Have you fixed it? If so, could you please share how you fix it? Thank you in advance! Edited on Aug. 3, 2023: Hi, I fixed this and opened an issue. You can check it and hope it'll help.

Hi, what's the meaning of se_num in this model?

I have no idea actually, but L21 in train.py says, quote, 'don't care this parameter', so I just left it to 0.

thank you sir