InvalidArgumentError of evaluate_model in show-attend-and-tell
LidaGuan opened this issue · comments
Can anyone help me to solve this problem?
In the evaluate_model.py , when I run the solver.test(data, split='val') . I got the error like this:
INFO:tensorflow:Restoring parameters from ./model/lstm/model-19
InvalidArgumentError Traceback (most recent call last)
in ()
----> 1 solver.test(data, split='val')
/home/guanlida/show-attend-and-tell-tensorflow/core/solver.pyc in test(self, data, split, attention_visualization, save_sampled_captions)
195 features_batch, image_files = sample_coco_minibatch(data, self.batch_size)
196 feed_dict = { self.model.features: features_batch }
--> 197 alps, bts, sam_cap = sess.run([alphas, betas, sampled_captions], feed_dict) # (N, max_len, L), (N, max_len)
198 decoded = decode_captions(sam_cap, self.model.idx_to_word)
199
/home/guanlida/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in run(self, fetches, feed_dict, options, run_metadata)
787 try:
788 result = self._run(None, fetches, feed_dict, options_ptr,
--> 789 run_metadata_ptr)
790 if run_metadata:
791 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
/home/guanlida/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _run(self, handle, fetches, feed_dict, options, run_metadata)
995 if final_fetches or final_targets:
996 results = self._do_run(handle, final_targets, final_fetches,
--> 997 feed_dict_string, options, run_metadata)
998 else:
999 results = []
/home/guanlida/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
1130 if handle is None:
1131 return self._do_call(_run_fn, self._session, feed_dict, fetch_list,
-> 1132 target_list, options, run_metadata)
1133 else:
1134 return self._do_call(_prun_fn, self._session, handle, feed_dict,
/home/guanlida/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _do_call(self, fn, *args)
1150 except KeyError:
1151 pass
-> 1152 raise type(e)(node_def, op, message)
1153
1154 def _extend_graph(self):
InvalidArgumentError: transpose expects a vector of size 1. But input(1) is a vector of size 2
[[Node: transpose_1 = Transpose[T=DT_FLOAT, Tperm=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](Squeeze, transpose_1/perm)]]
Caused by op u'transpose_1', defined at:
File "/home/guanlida/anaconda2/lib/python2.7/runpy.py", line 174, in _run_module_as_main
"main", fname, loader, pkg_name)
File "/home/guanlida/anaconda2/lib/python2.7/runpy.py", line 72, in _run_code
exec code in run_globals
File "/home/guanlida/anaconda2/lib/python2.7/site-packages/ipykernel_launcher.py", line 16, in
app.launch_new_instance()
File "/home/guanlida/anaconda2/lib/python2.7/site-packages/traitlets/config/application.py", line 658, in launch_instance
app.start()
File "/home/guanlida/anaconda2/lib/python2.7/site-packages/ipykernel/kernelapp.py", line 477, in start
ioloop.IOLoop.instance().start()
File "/home/guanlida/anaconda2/lib/python2.7/site-packages/zmq/eventloop/ioloop.py", line 177, in start
super(ZMQIOLoop, self).start()
File "/home/guanlida/anaconda2/lib/python2.7/site-packages/tornado/ioloop.py", line 888, in start
handler_func(fd_obj, events)
File "/home/guanlida/anaconda2/lib/python2.7/site-packages/tornado/stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "/home/guanlida/anaconda2/lib/python2.7/site-packages/zmq/eventloop/zmqstream.py", line 440, in _handle_events
self._handle_recv()
File "/home/guanlida/anaconda2/lib/python2.7/site-packages/zmq/eventloop/zmqstream.py", line 472, in _handle_recv
self._run_callback(callback, msg)
File "/home/guanlida/anaconda2/lib/python2.7/site-packages/zmq/eventloop/zmqstream.py", line 414, in _run_callback
callback(*args, **kwargs)
File "/home/guanlida/anaconda2/lib/python2.7/site-packages/tornado/stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "/home/guanlida/anaconda2/lib/python2.7/site-packages/ipykernel/kernelbase.py", line 283, in dispatcher
return self.dispatch_shell(stream, msg)
File "/home/guanlida/anaconda2/lib/python2.7/site-packages/ipykernel/kernelbase.py", line 235, in dispatch_shell
handler(stream, idents, msg)
File "/home/guanlida/anaconda2/lib/python2.7/site-packages/ipykernel/kernelbase.py", line 399, in execute_request
user_expressions, allow_stdin)
File "/home/guanlida/anaconda2/lib/python2.7/site-packages/ipykernel/ipkernel.py", line 196, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "/home/guanlida/anaconda2/lib/python2.7/site-packages/ipykernel/zmqshell.py", line 533, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "/home/guanlida/anaconda2/lib/python2.7/site-packages/IPython/core/interactiveshell.py", line 2717, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "/home/guanlida/anaconda2/lib/python2.7/site-packages/IPython/core/interactiveshell.py", line 2827, in run_ast_nodes
if self.run_code(code, result):
File "/home/guanlida/anaconda2/lib/python2.7/site-packages/IPython/core/interactiveshell.py", line 2881, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "", line 1, in
solver.test(data, split='val')
File "core/solver.py", line 188, in test
alphas, betas, sampled_captions = self.model.build_sampler(max_len=20) # (N, max_len, L), (N, max_len)
File "core/model.py", line 216, in build_sampler
betas = tf.transpose(tf.squeeze(beta_list), (1, 0)) # (N, T)
File "/home/guanlida/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 1285, in transpose
ret = gen_array_ops.transpose(a, perm, name=name)
File "/home/guanlida/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/gen_array_ops.py", line 3658, in transpose
result = _op_def_lib.apply_op("Transpose", x=x, perm=perm, name=name)
File "/home/guanlida/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 767, in apply_op
op_def=op_def)
File "/home/guanlida/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2506, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/home/guanlida/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1269, in init
self._traceback = _extract_stack()
InvalidArgumentError (see above for traceback): transpose expects a vector of size 1. But input(1) is a vector of size 2
[[Node: transpose_1 = Transpose[T=DT_FLOAT, Tperm=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](Squeeze, transpose_1/perm)]]
In this program, when I try using the whole dataset of MS COCO, I found that I got memory error on my GPU (NVIDIA TITAN XP), so I only use 10% of the train data to train the model and set the batch_size from 128 to 1 in the train.py. I completed the train.py and got the model in the lstm file. But when I want to run the evaluate_model finally, I change the dim_hidden from 1500 to 1024 and in the In[4]
solver = CaptioningSolver(model, data, data, n_epochs=15, batch_size=1, update_rule='adam', learning_rate=0.0025, print_every=2000, save_every=1, image_path='./image/val2014_resized', pretrained_model=None, model_path='./model/lstm', test_model='./model/lstm/model-19', print_bleu=False, log_path='./log/')
I changed the batch to 1 and the test_model from lstm3 to lstm(because there is not a file named lstm3). Those are my all change and I think when I changed the parameter, the shape or the dimension of the tensor has changed, so I got this error.
I have already solved the problem. And I find that I shouldn't change the batch_size in the model since the shape of the tensor will change. So if your memory is not enough, rather than change the batch_size, you only need to change the number of the train dataset. This code is fantastic and I will lean it further.
I have same problem, when batch_size=128,it works, but batch_size=1,
tensorflow transpose expects a vector of size 1. But input(1) is a vector of size 2
which means this code failed:
betas = tf.transpose(tf.squeeze(beta_list), (1, 0)) # (N, T)
do you know the reason? and when you just want to test 1 picture, how to do it?
and @yunjey can you give some advise? thx