search

UCL-SML / Doubly-Stochastic-DGP

Deep Gaussian Processes with Doubly Stochastic Variational Inference
Apache License 2.0
142 stars 48 forks source link

Error when using 'model.predict_all_layers_full_cov' #20

Open SaremS opened 6 years ago

SaremS commented 6 years ago

Hi,

at first thanks for sharing your work online - I am currently using this for my thesis and it's making things much easier.

However, I am having trouble tracing back the following error:

InvalidArgumentError

Traceback (most recent call last) /usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py in _do_call(self, fn, args) 1321 try: -> 1322 return fn(args) 1323 except errors.OpError as e:

/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py in _run_fn(feed_dict, fetch_list, target_list, options, run_metadata) 1306 return self._call_tf_sessionrun( -> 1307 options, feed_dict, fetch_list, target_list, run_metadata) 1308

/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py in _call_tf_sessionrun(self, options, feed_dict, fetch_list, target_list, run_metadata) 1408 self._session, options, feed_dict, fetch_list, target_list, -> 1409 run_metadata) 1410 else:

InvalidArgumentError: In[0].dim(1) and In[1].dim(1) must be the same: [30,1,30,30] vs [30,80,30,1] [[Node: autoflow/DGP/predict_all_layers_full_cov_10/MatMul = BatchMatMul[T=DT_DOUBLE, adj_x=false, adj_y=false, _device="/job:localhost/replica:0/task:0/device:CPU:0"](autoflow/DGP/predict_all_layers_full_cov_10/Cholesky, autoflow/DGP/predict_all_layers_full_cov_10/strided_slice_4)]]

During handling of the above exception, another exception occurred:

InvalidArgumentError Traceback (most recent call last)

in () ----> 1 full_c2 = m_dgp2.predict_all_layers_full_cov(X_test,30) /usr/local/lib/python3.6/dist-packages/gpflow/decors.py in autoflow_wrapper(obj, *args, **kwargs) 163 _setup_storage(store, *af_args, **af_kwargs) 164 _build_method(method, obj, store) --> 165 return _session_run(session, obj, store, *args, **kwargs) 166 return autoflow_wrapper 167 return autoflow_wrapper_decorator /usr/local/lib/python3.6/dist-packages/gpflow/decors.py in _session_run(session, obj, store, *args, **kwargs) 201 initialize = kwargs.pop('initialize', False) 202 obj.initialize(session=session, force=initialize) --> 203 return session.run(store['result'], **kwargs) 204 205 /usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata) 898 try: 899 result = self._run(None, fetches, feed_dict, options_ptr, --> 900 run_metadata_ptr) 901 if run_metadata: 902 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr) /usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata) 1133 if final_fetches or final_targets or (handle and feed_dict_tensor): 1134 results = self._do_run(handle, final_targets, final_fetches, -> 1135 feed_dict_tensor, options, run_metadata) 1136 else: 1137 results = [] /usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata) 1314 if handle is None: 1315 return self._do_call(_run_fn, feeds, fetches, targets, options, -> 1316 run_metadata) 1317 else: 1318 return self._do_call(_prun_fn, handle, feeds, fetches) /usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args) 1333 except KeyError: 1334 pass -> 1335 raise type(e)(node_def, op, message) 1336 1337 def _extend_graph(self): InvalidArgumentError: In[0].dim(1) and In[1].dim(1) must be the same: [30,1,30,30] vs [30,80,30,1] [[Node: autoflow/DGP/predict_all_layers_full_cov_10/MatMul = BatchMatMul[T=DT_DOUBLE, adj_x=false, adj_y=false, _device="/job:localhost/replica:0/task:0/device:CPU:0"](autoflow/DGP/predict_all_layers_full_cov_10/Cholesky, autoflow/DGP/predict_all_layers_full_cov_10/strided_slice_4)]] Caused by op 'autoflow/DGP/predict_all_layers_full_cov_10/MatMul', defined at: File "/usr/lib/python3.6/runpy.py", line 193, in _run_module_as_main "__main__", mod_spec) File "/usr/lib/python3.6/runpy.py", line 85, in _run_code exec(code, run_globals) File "/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py", line 16, in app.launch_new_instance() File "/usr/local/lib/python3.6/dist-packages/traitlets/config/application.py", line 658, in launch_instance app.start() File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelapp.py", line 486, in start self.io_loop.start() File "/usr/local/lib/python3.6/dist-packages/tornado/platform/asyncio.py", line 127, in start self.asyncio_loop.run_forever() File "/usr/lib/python3.6/asyncio/base_events.py", line 421, in run_forever self._run_once() File "/usr/lib/python3.6/asyncio/base_events.py", line 1426, in _run_once handle._run() File "/usr/lib/python3.6/asyncio/events.py", line 127, in _run self._callback(*self._args) File "/usr/local/lib/python3.6/dist-packages/tornado/platform/asyncio.py", line 117, in _handle_events handler_func(fileobj, events) File "/usr/local/lib/python3.6/dist-packages/tornado/stack_context.py", line 276, in null_wrapper return fn(*args, **kwargs) File "/usr/local/lib/python3.6/dist-packages/zmq/eventloop/zmqstream.py", line 450, in _handle_events self._handle_recv() File "/usr/local/lib/python3.6/dist-packages/zmq/eventloop/zmqstream.py", line 480, in _handle_recv self._run_callback(callback, msg) File "/usr/local/lib/python3.6/dist-packages/zmq/eventloop/zmqstream.py", line 432, in _run_callback callback(*args, **kwargs) File "/usr/local/lib/python3.6/dist-packages/tornado/stack_context.py", line 276, in null_wrapper return fn(*args, **kwargs) File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelbase.py", line 283, in dispatcher return self.dispatch_shell(stream, msg) File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelbase.py", line 233, in dispatch_shell handler(stream, idents, msg) File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelbase.py", line 399, in execute_request user_expressions, allow_stdin) File "/usr/local/lib/python3.6/dist-packages/ipykernel/ipkernel.py", line 208, in do_execute res = shell.run_cell(code, store_history=store_history, silent=silent) File "/usr/local/lib/python3.6/dist-packages/ipykernel/zmqshell.py", line 537, in run_cell return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs) File "/usr/local/lib/python3.6/dist-packages/IPython/core/interactiveshell.py", line 2662, in run_cell raw_cell, store_history, silent, shell_futures) File "/usr/local/lib/python3.6/dist-packages/IPython/core/interactiveshell.py", line 2785, in _run_cell interactivity=interactivity, compiler=compiler, result=result) File "/usr/local/lib/python3.6/dist-packages/IPython/core/interactiveshell.py", line 2903, in run_ast_nodes if self.run_code(code, result): File "/usr/local/lib/python3.6/dist-packages/IPython/core/interactiveshell.py", line 2963, in run_code exec(code_obj, self.user_global_ns, self.user_ns) File "", line 1, in full_c2 = m_dgp2.predict_all_layers_full_cov(X_test,2) File "/usr/local/lib/python3.6/dist-packages/gpflow/decors.py", line 164, in autoflow_wrapper _build_method(method, obj, store) File "/usr/local/lib/python3.6/dist-packages/gpflow/decors.py", line 207, in _build_method store['result'] = method(obj, *store['arguments']) File "/usr/local/lib/python3.6/dist-packages/doubly_stochastic_dgp/dgp.py", line 108, in predict_all_layers_full_cov return self.propagate(Xnew, full_cov=True, S=num_samples) File "/usr/local/lib/python3.6/dist-packages/gpflow/decors.py", line 67, in tensor_mode_wrapper result = method(obj, *args, **kwargs) File "/usr/local/lib/python3.6/dist-packages/doubly_stochastic_dgp/dgp.py", line 64, in propagate F, Fmean, Fvar = layer.sample_from_conditional(F, z=z, full_cov=full_cov) File "/usr/local/lib/python3.6/dist-packages/doubly_stochastic_dgp/layers.py", line 109, in sample_from_conditional samples = reparameterize(mean, var, z, full_cov=full_cov) File "/usr/local/lib/python3.6/dist-packages/doubly_stochastic_dgp/utils.py", line 47, in reparameterize f = mean + tf.matmul(chol, z_SDN1)[:, :, :, 0] # SDN(1) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/math_ops.py", line 2084, in matmul a, b, adj_x=adjoint_a, adj_y=adjoint_b, name=name) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/gen_math_ops.py", line 1236, in batch_mat_mul "BatchMatMul", x=x, y=y, adj_x=adj_x, adj_y=adj_y, name=name) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper op_def=op_def) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py", line 3392, in create_op op_def=op_def) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py", line 1718, in __init__ self._traceback = self._graph._extract_stack() # pylint: disable=protected-access InvalidArgumentError (see above for traceback): In[0].dim(1) and In[1].dim(1) must be the same: [30,1,30,30] vs [30,80,30,1] [[Node: autoflow/DGP/predict_all_layers_full_cov_10/MatMul = BatchMatMul[T=DT_DOUBLE, adj_x=false, adj_y=false, _device="/job:localhost/replica:0/task:0/device:CPU:0"](autoflow/DGP/predict_all_layers_full_cov_10/Cholesky, autoflow/DGP/predict_all_layers_full_cov_10/strided_slice_4)]] Thanks for your help, Sarem
hughsalimbeni commented 6 years ago

Could you show the details of how you construct the model? For some reason the 80 dimensions in the mean are not being matched in the covariance. Are you using the DGP class, or constructing the layers directly and using DGP_Base? The full code to reproduce the error (with dummy data) would be great.