Related
I am trying to create a machine learning model to predict who would survive on the Titanic. Everytime I try to fit my model, I get this error :
Traceback (most recent call last):
File "c:\Users\seand\.vscode\extensions\ms-python.python-2020.6.89148\pythonFiles\ptvsd_launcher.py", line 48, in <module>
main(ptvsdArgs)
File "c:\Users\seand\.vscode\extensions\ms-python.python-2020.6.89148\pythonFiles\lib\python\old_ptvsd\ptvsd\__main__.py", line 432, in main
run()
File "c:\Users\seand\.vscode\extensions\ms-python.python-2020.6.89148\pythonFiles\lib\python\old_ptvsd\ptvsd\__main__.py", line 316, in run_file
runpy.run_path(target, run_name='__main__')
return _run_module_code(code, init_globals, run_name,
File "D:\Python\lib\runpy.py", line 97, in _run_module_code
_run_code(code, mod_globals, init_globals,
File "D:\Python\lib\runpy.py", line 87, in _run_code
exec(code, run_globals)
File "d:\Kaggle\Titanic\titanic4.py", line 100, in <module>
cat_cols2 = pd.DataFrame(OneHot1.fit_transform(new_df[cat_columns]))
File "D:\Python\lib\site-packages\pandas\core\frame.py", line 2806, in __getitem__
indexer = self.loc._get_listlike_indexer(key, axis=1, raise_missing=True)[1]
File "D:\Python\lib\site-packages\pandas\core\indexing.py", line 1552, in _get_listlike_indexer
self._validate_read_indexer(
File "D:\Python\lib\site-packages\pandas\core\indexing.py", line 1640, in _validate_read_indexer
raise KeyError(f"None of [{key}] are in the [{axis_name}]")
KeyError: "None of [Index(['Name', 'Sex', 'Ticket', 'Cabin', 'Embarked'], dtype='object')] are in the [columns]"
PS D:\Kaggle\Titanic> cd 'd:\Kaggle\Titanic'; ${env:PYTHONIOENCODING}='UTF-8'; ${env:PYTHONUNBUFFERED}='1'; & 'D:\Python\python.exe' 'c:\Users\seand\.vscode\extensions\ms-python.python-2020.6.89148\pythonFiles\ptvsd_launcher.py' '--default' '--client' '--host' 'localhost' '--port' '60778' 'd:\Kaggle\Titanic\titanic4.py'
Traceback (most recent call last):
File "c:\Users\seand\.vscode\extensions\ms-python.python-2020.6.89148\pythonFiles\ptvsd_launcher.py", line 48, in <module>
main(ptvsdArgs)
File "c:\Users\seand\.vscode\extensions\ms-python.python-2020.6.89148\pythonFiles\lib\python\old_ptvsd\ptvsd\__main__.py", line 432, in main
run()
File "c:\Users\seand\.vscode\extensions\ms-python.python-2020.6.89148\pythonFiles\lib\python\old_ptvsd\ptvsd\__main__.py", line 316, in run_file
runpy.run_path(target, run_name='__main__')
File "D:\Python\lib\runpy.py", line 265, in run_path
return _run_module_code(code, init_globals, run_name,
File "D:\Python\lib\runpy.py", line 97, in _run_module_code
_run_code(code, mod_globals, init_globals,
File "D:\Python\lib\runpy.py", line 87, in _run_code
exec(code, run_globals)
File "d:\Kaggle\Titanic\titanic4.py", line 143, in <module>
my_pipeline.fit(new_df,y)
File "D:\Python\lib\site-packages\sklearn\pipeline.py", line 330, in fit
Xt = self._fit(X, y, **fit_params_steps)
File "D:\Python\lib\site-packages\sklearn\pipeline.py", line 292, in _fit
X, fitted_transformer = fit_transform_one_cached(
File "D:\Python\lib\site-packages\joblib\memory.py", line 352, in __call__
return self.func(*args, **kwargs)
File "D:\Python\lib\site-packages\sklearn\pipeline.py", line 740, in _fit_transform_one
res = transformer.fit_transform(X, y, **fit_params)
File "D:\Python\lib\site-packages\sklearn\compose\_column_transformer.py", line 531, in fit_transform
result = self._fit_transform(X, y, _fit_transform_one)
File "D:\Python\lib\site-packages\sklearn\compose\_column_transformer.py", line 458, in _fit_transform
return Parallel(n_jobs=self.n_jobs)(
File "D:\Python\lib\site-packages\joblib\parallel.py", line 1032, in __call__
while self.dispatch_one_batch(iterator):
File "D:\Python\lib\site-packages\joblib\parallel.py", line 847, in dispatch_one_batch
self._dispatch(tasks)
File "D:\Python\lib\site-packages\joblib\parallel.py", line 765, in _dispatch
job = self._backend.apply_async(batch, callback=cb)
File "D:\Python\lib\site-packages\joblib\_parallel_backends.py", line 206, in apply_async
result = ImmediateResult(func)
File "D:\Python\lib\site-packages\joblib\_parallel_backends.py", line 570, in __init__
self.results = batch()
File "D:\Python\lib\site-packages\joblib\parallel.py", line 252, in __call__
return [func(*args, **kwargs)
File "D:\Python\lib\site-packages\joblib\parallel.py", line 252, in <listcomp>
return [func(*args, **kwargs)
res = transformer.fit_transform(X, y, **fit_params)
File "D:\Python\lib\site-packages\sklearn\pipeline.py", line 367, in fit_transform
Xt = self._fit(X, y, **fit_params_steps)
File "D:\Python\lib\site-packages\sklearn\pipeline.py", line 292, in _fit
X, fitted_transformer = fit_transform_one_cached(
File "D:\Python\lib\site-packages\joblib\memory.py", line 352, in __call__
return self.func(*args, **kwargs)
File "D:\Python\lib\site-packages\sklearn\pipeline.py", line 740, in _fit_transform_one
res = transformer.fit_transform(X, y, **fit_params)
File "D:\Python\lib\site-packages\sklearn\base.py", line 693, in fit_transform
return self.fit(X, y, **fit_params).transform(X)
File "D:\Python\lib\site-packages\sklearn\impute\_base.py", line 459, in transform
coordinates = np.where(mask.transpose())[::-1]
AttributeError: 'bool' object has no attribute 'transpose'
PS D:\Kaggle\Titanic> cd 'd:\Kaggle\Titanic'; ${env:PYTHONIOENCODING}='UTF-8'; ${env:PYTHONUNBUFFERED}='1'; & 'D:\Python\python.exe' 'c:\Users\seand\.vscode\extensions\ms-python.python-2020.6.89148\pythonFiles\ptvsd_launcher.py' '--default' '--client' '--host' 'localhost' '--port' '60800' 'd:\Kaggle\Titanic\titanic4.py'
Traceback (most recent call last):
File "c:\Users\seand\.vscode\extensions\ms-python.python-2020.6.89148\pythonFiles\ptvsd_launcher.py", line 48, in <module>
main(ptvsdArgs)
File "c:\Users\seand\.vscode\extensions\ms-python.python-2020.6.89148\pythonFiles\lib\python\old_ptvsd\ptvsd\__main__.py", line 432, in main
run()
File "c:\Users\seand\.vscode\extensions\ms-python.python-2020.6.89148\pythonFiles\lib\python\old_ptvsd\ptvsd\__main__.py", line 316, in run_file
runpy.run_path(target, run_name='__main__')
File "D:\Python\lib\runpy.py", line 265, in run_path
return _run_module_code(code, init_globals, run_name,
File "D:\Python\lib\runpy.py", line 97, in _run_module_code
_run_code(code, mod_globals, init_globals,
File "D:\Python\lib\runpy.py", line 87, in _run_code
exec(code, run_globals)
File "d:\Kaggle\Titanic\titanic4.py", line 122, in <module>
my_pipeline.fit(new_df,y)
File "D:\Python\lib\site-packages\sklearn\pipeline.py", line 330, in fit
Xt = self._fit(X, y, **fit_params_steps)
File "D:\Python\lib\site-packages\sklearn\pipeline.py", line 292, in _fit
X, fitted_transformer = fit_transform_one_cached(
File "D:\Python\lib\site-packages\joblib\memory.py", line 352, in __call__
return self.func(*args, **kwargs)
File "D:\Python\lib\site-packages\sklearn\pipeline.py", line 740, in _fit_transform_one
res = transformer.fit_transform(X, y, **fit_params)
File "D:\Python\lib\site-packages\sklearn\compose\_column_transformer.py", line 531, in fit_transform
result = self._fit_transform(X, y, _fit_transform_one)
File "D:\Python\lib\site-packages\sklearn\compose\_column_transformer.py", line 458, in _fit_transform
return Parallel(n_jobs=self.n_jobs)(
File "D:\Python\lib\site-packages\joblib\parallel.py", line 1032, in __call__
while self.dispatch_one_batch(iterator):
File "D:\Python\lib\site-packages\joblib\parallel.py", line 847, in dispatch_one_batch
self._dispatch(tasks)
File "D:\Python\lib\site-packages\joblib\parallel.py", line 765, in _dispatch
job = self._backend.apply_async(batch, callback=cb)
File "D:\Python\lib\site-packages\joblib\_parallel_backends.py", line 206, in apply_async
result = ImmediateResult(func)
File "D:\Python\lib\site-packages\joblib\_parallel_backends.py", line 570, in __init__
self.results = batch()
File "D:\Python\lib\site-packages\joblib\parallel.py", line 252, in __call__
return [func(*args, **kwargs)
File "D:\Python\lib\site-packages\joblib\parallel.py", line 252, in <listcomp>
return [func(*args, **kwargs)
File "D:\Python\lib\site-packages\sklearn\pipeline.py", line 740, in _fit_transform_one
res = transformer.fit_transform(X, y, **fit_params)
File "D:\Python\lib\site-packages\sklearn\pipeline.py", line 367, in fit_transform
Xt = self._fit(X, y, **fit_params_steps)
File "D:\Python\lib\site-packages\sklearn\pipeline.py", line 292, in _fit
X, fitted_transformer = fit_transform_one_cached(
File "D:\Python\lib\site-packages\joblib\memory.py", line 352, in __call__
return self.func(*args, **kwargs)
File "D:\Python\lib\site-packages\sklearn\pipeline.py", line 740, in _fit_transform_one
res = transformer.fit_transform(X, y, **fit_params)
File "D:\Python\lib\site-packages\sklearn\base.py", line 693, in fit_transform
return self.fit(X, y, **fit_params).transform(X)
File "D:\Python\lib\site-packages\sklearn\impute\_base.py", line 459, in transform
coordinates = np.where(mask.transpose())[::-1]
AttributeError: 'bool' object has no attribute 'transpose'
The code I am running is the following :
from xgboost import XGBClassifier
from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.feature_selection import SelectFromModel
from itertools import combinations
import pandas as pd
import numpy as np
#read in data
training_data = pd.read_csv('train.csv')
testing_data = pd.read_csv('test.csv')
#seperate X and Y
X_train_full = training_data.copy()
y = X_train_full.Survived
X_train_full.drop(['Survived'], axis=1, inplace=True)
y_test = testing_data
#get all str columns
cat_columns1 = [cname for cname in X_train_full.columns if
X_train_full[cname].dtype == "object"]
interactions = pd.DataFrame(index= X_train_full)
#create new features
for combination in combinations(cat_columns1,2):
imputer = SimpleImputer(strategy='constant')
new_col_name = '_'.join(combination)
col1 = X_train_full[combination[0]]
col2 = X_train_full[combination[1]]
col1 = np.array(col1).reshape(-1,1)
col2 = np.array(col2).reshape(-1,1)
col1 = imputer.fit_transform(col1)
col2 = imputer.fit_transform(col2)
new_vals = col1 + '_' + col2
OneHot = OneHotEncoder()
interactions[new_col_name] = OneHot.fit_transform(new_vals)
interactions = interactions.reset_index(drop = True)
#create new dataframe with new features included
new_df = X_train_full.join(interactions)
#do the same for the test file
interactions2 = pd.DataFrame(index= y_test)
for combination in combinations(cat_columns1,2):
imputer = SimpleImputer(strategy='constant')
new_col_name = '_'.join(combination)
col1 = y_test[combination[0]]
col2 = y_test[combination[1]]
col1 = np.array(col1).reshape(-1,1)
col2 = np.array(col2).reshape(-1,1)
col1 = imputer.fit_transform(col1)
col2 = imputer.fit_transform(col2)
new_vals = col1 + '_' + col2
OneHot = OneHotEncoder()
interactions2[new_col_name] = OneHot.fit_transform(new_vals)
interactions2[new_col_name] = new_vals
interactions2 = interactions2.reset_index(drop = True)
y_test = y_test.join(interactions2)
#get names of cat columns (with new features added)
cat_columns = [cname for cname in new_df.columns if
new_df[cname].dtype == "object"]
# Select numerical columns
num_columns = [cname for cname in new_df.columns if
new_df[cname].dtype in ['int64', 'float64']]
#set up pipeline
numerical_transformer = SimpleImputer(strategy = 'constant')
categorical_transformer = Pipeline(steps=[
('imputer', SimpleImputer(strategy='constant')),
('onehot', OneHotEncoder(handle_unknown='ignore'))
])
preprocessor = ColumnTransformer(
transformers=[
('num', numerical_transformer, num_columns),
('cat', categorical_transformer, cat_columns)
])
model = XGBClassifier()
my_pipeline = Pipeline(steps=[('preprocessor', preprocessor),
('model', model)
])
#fit model
my_pipeline.fit(new_df,y)
The csv files I am reading are available from Kaggle at this link :
https://www.kaggle.com/c/titanic/data
I cannot figure out what is causing this problem. Any help would be much appreciated.
This probably happens because your data contains pd.NA values. pd.NA was introduced in pandas 1.0.0, but is still marked as experimental.
SimpleImputer will ultimately run data == np.nan, which would usually return a numpy array. In stead, it is returning a single boolean scalar when data contains pd.NA values.
An example:
import pandas as pd
import numpy as np
test_pd_na = pd.DataFrame({"A": [1, 2, 3, pd.NA]})
test_np_nan = pd.DataFrame({"A": [1, 2, 3, np.nan]})
test_np_nan.to_numpy() == np.nan:
> array([[False],
[False],
[False],
[False]])
test_pd_na.to_numpy() == np.nan
> False
The solution would be to convert all pd.NA values to np.nan before running SimpleImputer. You can use .replace({pd.NA: np.nan})on your data frames for this purpose. The downside is obviously that you loose the benefits pd.NA brings, such as integer columns with missing data, in stead of those columns being converted to float columns.
I'm trying to use a sigmoid to join the output of two models with different embedding matrix. but I keep getting the error at the concatenate line. I have tried other suggestions from similar questions but it keeps giving the same error. I feel I'm missing something but I can't find it. please help explain. Thanks
############################ MODEL 1 ######################################
input_tensor=Input(shape=(35,))
input_layer= Embedding(vocab_size, 300, input_length=35, weights=[embedding_matrix],trainable=True)(input_tensor)
conv_blocks = []
filter_sizes = (2,3,4)
for fx in filter_sizes:
conv_layer= Conv1D(100, kernel_size=fx, activation='relu', data_format='channels_first')(input_layer) #filters=100, kernel_size=3
maxpool_layer = MaxPooling1D(pool_size=4)(conv_layer)
flat_layer= Flatten()(maxpool_layer)
conv_blocks.append(flat_layer)
conc_layer=concatenate(conv_blocks, axis=1)
graph = Model(inputs=input_tensor, outputs=conc_layer)
model = Sequential()
model.add(graph)
model.add(Dropout(0.2))
############################ MODEL 2 ######################################
input_tensor_1=Input(shape=(35,))
input_layer_1= Embedding(vocab_size, 300, input_length=35, weights=[embedding_matrix_1],trainable=True)(input_tensor_1)
conv_blocks_1 = []
filter_sizes_1 = (2,3,4)
for fx in filter_sizes_1:
conv_layer_1= Conv1D(100, kernel_size=fx, activation='relu', data_format='channels_first')(input_layer_1) #filters=100, kernel_size=3
maxpool_layer_1 = MaxPooling1D(pool_size=4)(conv_layer_1)
flat_layer_1= Flatten()(maxpool_layer_1)
conv_blocks_1.append(flat_layer_1)
conc_layer_1=concatenate(conv_blocks_1, axis=1)
graph_1 = Model(inputs=input_tensor_1, outputs=conc_layer_1)
model_1 = Sequential()
model_1.add(graph_1)
model_1.add(Dropout(0.2))
fused = concatenate([graph, graph_1], axis=-1)
prediction = Dense(3, activation='sigmoid')(fused)
model = Model(inputs=[input_tensor,input_tensor_1], outputs=[prediction])
model.compile(loss='sparse_categorical_crossentropy',optimizer='Adagrad', metrics=['accuracy'])
model.summary()
This is the error trace
Traceback (most recent call last):
File "DL_Ensemble.py", line 145, in <module>
fused = concatenate([graph, graph_1], axis= 1 )
File "/usr/pkg/lib/python3.8/site-
packages/tensorflow_core/python/keras/layers/merge.py", line 705, in concatenate
return Concatenate(axis=axis, **kwargs)(inputs)
File "/usr/pkg/lib/python3.8/site-packages/tensorflow_core/python/keras/engine/base_layer.py", line 887, in __call__
self._maybe_build(inputs)
File "/usr/pkg/lib/python3.8/site-packages/tensorflow_core/python/keras/engine/base_layer.py", line 2141, in _maybe_build
self.build(input_shapes)
File "/usr/pkg/lib/python3.8/site-
packages/tensorflow_core/python/keras/utils/tf_utils.py", line 306, in wrapper
output_shape = fn(instance, input_shape)
File "/usr/pkg/lib/python3.8/site-
packages/tensorflow_core/python/keras/layers/merge.py", line 378, in build
raise ValueError('A `Concatenate` layer should be called '
ValueError: A `Concatenate` layer should be called on a list of at least 2 inputs
UPDATE: I have reflected the answers given by #VivekMehta, however, I have this error.
File "DL_Ensemble.py", line 165, in <module>
model.fit([train_sequences,train_sequences], train_y, epochs=10,
verbose=False, batch_size=32, class_weight={0: 6.0, 1: 1.0, 2: 2.0})
File "/usr/pkg/lib/python3.8/site-
packages/tensorflow_core/python/keras/engine/training.py", line 709, in fit
return func.fit(
File "/usr/pkg/lib/python3.8/site-
packages/tensorflow_core/python/keras/engine/training_v2.py", line 313, in fit
training_result = run_one_epoch(
File "/usr/pkg/lib/python3.8/site-
packages/tensorflow_core/python/keras/engine/training_v2.py", line 123, in run_one_epoch
batch_outs = execution_function(iterator)
File "/usr/pkg/lib/python3.8/site-
packages/tensorflow_core/python/keras/engine/training_v2_utils.py",
line
86, in execution_function
distributed_function(input_fn))
File "/usr/pkg/lib/python3.8/site-
packages/tensorflow_core/python/eager/def_function.py", line 457, in __call__
result = self._call(*args, **kwds)
File "/usr/pkg/lib/python3.8/site-
packages/tensorflow_core/python/eager/def_function.py", line 520, in _call
return self._stateless_fn(*args, **kwds)
File "/usr/pkg/lib/python3.8/site-
packages/tensorflow_core/python/eager/function.py", line 1823, in __call__
return graph_function._filtered_call(args, kwargs) # pylint:
disable=protected-access
File "/usr/pkg/lib/python3.8/site-
packages/tensorflow_core/python/eager/function.py", line 1137, in _filtered_call
return self._call_flat(
File "/usr/pkg/lib/python3.8/site-
packages/tensorflow_core/python/eager/function.py", line 1223, in _call_flat
flat_outputs = forward_function.call(
File "/usr/pkg/lib/python3.8/site-
packages/tensorflow_core/python/eager/function.py", line 506, in call
outputs = execute.execute(
File "/usr/pkg/lib/python3.8/site-
packages/tensorflow_core/python/eager/execute.py", line 67, in quick_execute
six.raise_from(core._status_to_exception(e.code, message), None)
File "<string>", line 3, in raise_from
tensorflow.python.framework.errors_impl.InvalidArgumentError:
Conv2DCustomBackpropInputOp only supports NHWC.
[[node Conv2DBackpropInput (defined at /usr/pkg/lib/python3.8/site-
packages/tensorflow_core/python/framework/ops.py:1751) ]] [Op:__inference_distributed_function_2250]
Function call stack:
distributed_function
I also wanted to add that when the code is run on a GPU as opposed to a CPU, the error occurs on the same line as before but the message changes to :
File "DL_Ensemble.py", line 166, in <module>
model.fit([train_sequences,train_sequences], train_y, epochs=10, verbose=False, batch_size=32, class_weight={0: 6.0, 1: 1.0, 2: 2.0})
File "/home/kosimadukwe/.local/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py", line 880, in fit
validation_steps=validation_steps)
File "/home/kosimadukwe/.local/lib/python3.7/site-packages/tensorflow/python/keras/engine/training_arrays.py", line 329, in model_iteration
batch_outs = f(ins_batch)
File "/home/kosimadukwe/.local/lib/python3.7/site-packages/tensorflow/python/keras/backend.py", line 3073, in __call__
self._make_callable(feed_arrays, feed_symbols, symbol_vals, session)
File "/home/kosimadukwe/.local/lib/python3.7/site-packages/tensorflow/python/keras/backend.py", line 3019, in _make_callable
callable_fn = session._make_callable_from_options(callable_opts)
File "/home/kosimadukwe/.local/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1471, in _make_callable_from_options
return BaseSession._Callable(self, callable_options)
File "/home/kosimadukwe/.local/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1425, in __init__
session._session, options_ptr, status)
File "/home/kosimadukwe/.local/lib/python3.7/site-packages/tensorflow/python/framework/errors_impl.py", line 528, in __exit__
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Conv2DCustomBackpropInputOp only supports NHWC.
[[{{node training/Adagrad/gradients/conv1d_5/conv1d/Conv2D_grad/Conv2DBackpropInput}}]]
Exception ignored in: <function BaseSession._Callable.__del__ at 0x7fe4dd06a730>
Traceback (most recent call last):
File "/home/kosimadukwe/.local/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1455, in __del__
self._session._session, self._handle, status)
File "/home/kosimadukwe/.local/lib/python3.7/site-packages/tensorflow/python/framework/errors_impl.py", line 528, in __exit__
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: No such callable handle: 94697914208640
So from you stack trace, code is throwing error at:
fused = concatenate([graph, graph_1], axis= 1 )
print(type(graph))
# output: <class 'tensorflow.python.keras.engine.training.Model'>
This error is coming because concatenate expects list of tensors to be concatenated. While you are passing graph and graph_1 which is not tensor but a Model instance.
So from your code I assume that you want to concatenate output of these two models. In that case you'll have to change above line to:
fused = concatenate([graph.outputs[0], graph_1.outputs[0]], axis=-1)
Here, graph.outputs gives list of outputs by given by Model. Since each model is giving us one output, we will take 0th index from each output.
Change this part and you'll get model summary as you are expecting.
I compiled tensorflow from source with MKL in order to accelerate my DNN learning progress. And I have a ResNet model which is copy from tensorflow/models. The dataset is CIFAR-10. When I run the model with channels last format, everything goes ok. But in order to use MKL which is said only accelerate only for channels first format, I add some code to transpose the data into NCHW format, and run it. Then I get:
Caused by op 'stage/residual_v1/conv2d/Conv2D', defined at:
File "main.py", line 182, in <module>
main(args)
File "main.py", line 83, in main
tf.estimator.train_and_evaluate(estimator, train_spec, eval_spec)
File "/home/holmescn/.pyenv/versions/anaconda35.2.0/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/estimator/training.py", line 447, in train_and_evaluate
return executor.run()
File "/home/holmescn/.pyenv/versions/anaconda3-5.2.0/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/estimator/training.py", line 531, in run
return self.run_local()
File "/home/holmescn/.pyenv/versions/anaconda3-5.2.0/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/estimator/training.py", line 669, in run_local
hooks=train_hooks)
File "/home/holmescn/.pyenv/versions/anaconda3-5.2.0/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 366, in train
loss = self._train_model(input_fn, hooks, saving_listeners)
File "/home/holmescn/.pyenv/versions/anaconda3-5.2.0/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 1119, in _train_model
return self._train_model_default(input_fn, hooks, saving_listeners)
File "/home/holmescn/.pyenv/versions/anaconda3-5.2.0/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 1132, in _train_model_default
features, labels, model_fn_lib.ModeKeys.TRAIN, self.config)
File "/home/holmescn/.pyenv/versions/anaconda3-5.2.0/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 1107, in _call_model_fn
model_fn_results = self._model_fn(features=features, **kwargs)
File "/home/holmescn/Work/deep-learning-practice/tensorflow/estimator/utils.py", line 18, in _model_fn
logits = build_model(input_layer, mode == tf.estimator.ModeKeys.TRAIN, params=params, args=args)
File "/home/holmescn/Work/deep-learning-practice/tensorflow/estimator/estimators/resnet.py", line 175, in build_model
return resnet.build_model(input_layer, args.num_layers)
File "/home/holmescn/Work/deep-learning-practice/tensorflow/estimator/estimators/resnet.py", line 56, in build_model
x = res_func(x, 3, filters[i], filters[i + 1], strides[i])
File "/home/holmescn/Work/deep-learning-practice/tensorflow/estimator/estimators/resnet.py", line 79, in _residual_v1
x = self._conv(x, kernel_size, out_filter, stride)
File "/home/holmescn/Work/deep-learning-practice/tensorflow/estimator/estimators/base.py", line 59, in _conv
name=name)
File "/home/holmescn/.pyenv/versions/anaconda3-5.2.0/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/layers/convolutional.py", line 427, in conv2d
return layer.apply(inputs)
File "/home/holmescn/.pyenv/versions/anaconda3-5.2.0/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/keras/engine/base_layer.py", line 759, in apply
return self.__call__(inputs, *args, **kwargs)
File "/home/holmescn/.pyenv/versions/anaconda3-5.2.0/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/layers/base.py", line 329, in __call__
outputs = super(Layer, self).__call__(inputs, *args, **kwargs)
File "/home/holmescn/.pyenv/versions/anaconda3-5.2.0/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/keras/engine/base_layer.py", line 688, in __call__
outputs = self.call(inputs, *args, **kwargs)
File "/home/holmescn/.pyenv/versions/anaconda3-5.2.0/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/keras/layers/convolutional.py", line 184, in call
outputs = self._convolution_op(inputs, self.kernel)
File "/home/holmescn/.pyenv/versions/anaconda3-5.2.0/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 868, in __call__
return self.conv_op(inp, filter)
File "/home/holmescn/.pyenv/versions/anaconda3-5.2.0/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 520, in __call__
return self.call(inp, filter)
File "/home/holmescn/.pyenv/versions/anaconda3-5.2.0/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 204, in __call__
name=self.name)
File "/home/holmescn/.pyenv/versions/anaconda3-5.2.0/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 956, in conv2d
data_format=data_format, dilations=dilations, name=name)
File "/home/holmescn/.pyenv/versions/anaconda3-5.2.0/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/home/holmescn/.pyenv/versions/anaconda3-5.2.0/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3414, in create_op
op_def=op_def)
File "/home/holmescn/.pyenv/versions/anaconda3-5.2.0/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1740, in __init__
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
InvalidArgumentError (see above for traceback): input and filter must have the same depth: 32 vs 16
[[Node: stage/residual_v1/conv2d/Conv2D = _MklConv2D[T=DT_FLOAT, _kernel="MklOp", data_format="NCHW", dilations=[1, 1, 1, 1], padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](Relu, conv2d/kernel/read, Relu:1, DMT/_6)]]
the last trackback said input and filter must have the same depth, which IMO means the depth dim for both input tensor and filter should be same? But how could I do that if I want to generate more feature maps? What should I do?
No need to transpose the data for changing the dataformat.
You can pass the data format as channels first or channels last as argument
For example,
python cifar10_main.py --data-dir=${PWD}/cifar-10-data --data-format=channels_first --job-dir=/tmp/cifar10
I am getting the error:
“tensorflow.python.framework.errors_impl.InvalidArgumentError: Dense float feature must be a matrix.” when training with estimator tensorflow.contrib.boosted_trees.estimator_batch.estimator.GradientBoostedDecisionTreeClassifier. I am using Tensorflow version 1.4.0. The same code works correctly if I change estimator to tf.contrib.learn.DNNClassifier. In the code, dictionary of features are passed in “Train_input_fn” in tf.contrib.learn.Experiment.
Anyone faced similar error before?
#'tensorflow==1.4.0'
import tensorflow as tf
import argparse
import sys
import os
from tensorflow.contrib.boosted_trees.estimator_batch.estimator import GradientBoostedDecisionTreeClassifier
from tensorflow.contrib.boosted_trees.proto import learner_pb2
from tensorflow_transform.tf_metadata import metadata_io
from tensorflow_transform.saved import input_fn_maker
from tensorflow.contrib.learn.python.learn import learn_runner
RAW_METADATA_DIR="raw_metadata"
CONTRACTED_METADATA_DIR="contracted_metadata"
TRANSFORMED_METADATA_DIR="transformed_metadata"
TRANSFORMED_TRAIN_DATA_FILE_PREFIX="train"
TRANSFORMED_EVAL_DATA_FILE_PREFIX="eval"
DATA_FILE_SUFFIX=".tfrecord.gz"
TRANSFORM_FN_DIR="transform_fn"
TARGET_FEATURE_COLUMN='target_field'
FEATURE_NUMERICAL_COLUMN_NAMES = [
'feature1',
'feature2',
'feature3',
'feature4',
'feature5'
]
FEATURE_INTEGER_COLUMN_NAMES = [ # comment out fields that are not features
'feature6',
'feature7',
'feature8',
'feature9',
'feature10'
]
def _parse_arguments(argv):
"""Parses command line arguments."""
parser = argparse.ArgumentParser(
description="Runs training on data.")
parser.add_argument(
"--model_dir", required=True, type=str,
help="The directory where model outputs will be written")
parser.add_argument(
"--input_dir", required=True, type=str,
help=("GCS or local directory containing tensorflow-transform outputs."))
parser.add_argument(
"--batch_size", default=30, required=False, type=int,
help=("Batch size to use during training."))
parser.add_argument(
"--num_epochs", default=100, required=False, type=int,
help=("Number of epochs through the training set"))
args, _ = parser.parse_known_args(args=argv[1:])
return args
def get_eval_metrics():
return {
"accuracy":
tf.contrib.learn.MetricSpec(
metric_fn=tf.contrib.metrics.streaming_accuracy,
prediction_key=tf.contrib.learn.PredictionKey.CLASSES),
"precision":
tf.contrib.learn.MetricSpec(
metric_fn=tf.contrib.metrics.streaming_precision,
prediction_key=tf.contrib.learn.PredictionKey.CLASSES),
"recall":
tf.contrib.learn.MetricSpec(
metric_fn=tf.contrib.metrics.streaming_recall,
prediction_key=tf.contrib.learn.PredictionKey.CLASSES)
}
def read_and_decode_single_record(input_dir, num_epochs,
mode=tf.contrib.learn.ModeKeys.TRAIN):
if mode == tf.contrib.learn.ModeKeys.TRAIN:
num_epochs = num_epochs
file_prefix = TRANSFORMED_TRAIN_DATA_FILE_PREFIX
else:
num_epochs = 1
file_prefix = TRANSFORMED_EVAL_DATA_FILE_PREFIX
transformed_metadata = metadata_io.read_metadata(os.path.join(input_dir,
TRANSFORMED_METADATA_DIR))
input_file_names = tf.train.match_filenames_once(os.path.join(input_dir,
'{}*{}'.format(file_prefix, DATA_FILE_SUFFIX)))
filename_queue = tf.train.string_input_producer(input_file_names,
num_epochs=num_epochs, shuffle=True)
reader = tf.TFRecordReader(options=tf.python_io.TFRecordOptions(
tf.python_io.TFRecordCompressionType.GZIP))
_, serialized_example = reader.read(filename_queue)
features = tf.parse_single_example(
serialized = serialized_example,
features=transformed_metadata.schema.as_feature_spec()
)
return features
def read_dataset(input_dir, num_epochs, batch_size, mode=tf.contrib.learn.ModeKeys.TRAIN):
def _input_fn():
min_after_dequeue = 10000
features = read_and_decode_single_record(input_dir, num_epochs, mode)
features = tf.train.shuffle_batch(
tensors=features,
batch_size=batch_size,
min_after_dequeue=min_after_dequeue,
capacity=(min_after_dequeue + 3) * batch_size)
target = features.pop(TARGET_FEATURE_COLUMN)
return features, target
return _input_fn
def specify_feature_columns():
feature_columns = [
tf.contrib.layers.real_valued_column(column_name = column_name)
for column_name in FEATURE_NUMERICAL_COLUMN_NAMES]
feature_columns.extend([
tf.contrib.layers.real_valued_column(column_name = column_name)
for column_name in FEATURE_INTEGER_COLUMN_NAMES])
return feature_columns
def build_estimator(model_dir, config, params):
print "Using gradient boosted decision trees estimator \n"
learner_config = learner_pb2.LearnerConfig()
learner_config.learning_rate_tuner.fixed.learning_rate = 0.1
learner_config.regularization.l1 = 0.0
learner_config.regularization.l2 = 4.0 / params.batch_size
learner_config.constraints.max_tree_depth = 4
learner_config.growing_mode = learner_pb2.LearnerConfig.WHOLE_TREE
return GradientBoostedDecisionTreeClassifier(
learner_config=learner_config,
examples_per_layer=params.batch_size,
num_trees=100,
center_bias=False,
feature_columns=specify_feature_columns()
# feature_engineering_fn=feature_engineering_fn
)
def get_experiment_fn(args):
config = tf.contrib.learn.RunConfig(save_checkpoints_steps=1000)
def experiment_fn(output_dir):
return tf.contrib.learn.Experiment(
estimator = build_estimator(model_dir = output_dir,
config = config,
params = args),
train_input_fn = read_dataset(args.input_dir,
args.num_epochs, args.batch_size,
mode=tf.contrib.learn.ModeKeys.TRAIN),
eval_input_fn = read_dataset(args.input_dir,
args.num_epochs, args.batch_size,
mode=tf.contrib.learn.ModeKeys.EVAL),
eval_metrics = get_eval_metrics())
return experiment_fn
def run(args):
learn_runner.run(get_experiment_fn(args), args.model_dir)
if __name__ == '__main__':
args = _parse_arguments(sys.argv)
run(args)
The full error trace:
WARNING:tensorflow:Using temporary folder as model directory: /var/folders/mg/sd4_qlyj4_lbh5ggfn6frvcr00fk8_/T/tmpPFhins
WARNING:tensorflow:From /Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/monitors.py:267: __init__ (from tensorflow.contrib.learn.python.learn.monitors) is deprecated and will be removed after 2016-12-05.
Instructions for updating:
Monitors are deprecated. Please use tf.train.SessionRunHook.
WARNING:tensorflow:Casting <dtype: 'int64'> labels to bool.
WARNING:tensorflow:Casting <dtype: 'int64'> labels to bool.
WARNING:tensorflow:Error encountered when serializing resources.
Type is unsupported, or the types of the items don't match field type in CollectionDef.
'_Resource' object has no attribute 'name'
2017-11-16 13:38:39.919664: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
WARNING:tensorflow:Error encountered when serializing resources.
Type is unsupported, or the types of the items don't match field type in CollectionDef.
'_Resource' object has no attribute 'name'
2017-11-16 13:38:48.810825: W tensorflow/core/framework/op_kernel.cc:1192] Invalid argument: Dense float feature must be a matrix.
2017-11-16 13:38:48.810825: W tensorflow/core/framework/op_kernel.cc:1192] Invalid argument: Dense float feature must be a matrix.
Traceback (most recent call last):
File "./trainer/task.py", line 162, in <module>
run(args)
File "./trainer/task.py", line 157, in run
learn_runner.run(get_experiment_fn(args), args.model_dir)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/learn_runner.py", line 218, in run
return _execute_schedule(experiment, schedule)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/learn_runner.py", line 46, in _execute_schedule
return task()
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/experiment.py", line 625, in train_and_evaluate
self.train(delay_secs=0)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/experiment.py", line 367, in train
hooks=self._train_monitors + extra_hooks)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/experiment.py", line 812, in _call_train
monitors=hooks)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/python/util/deprecation.py", line 316, in new_func
return func(*args, **kwargs)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 480, in fit
loss = self._train_model(input_fn=input_fn, hooks=hooks)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 1040, in _train_model
_, loss = mon_sess.run([model_fn_ops.train_op, model_fn_ops.loss])
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 521, in run
run_metadata=run_metadata)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 892, in run
run_metadata=run_metadata)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 967, in run
raise six.reraise(*original_exc_info)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 952, in run
return self._sess.run(*args, **kwargs)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 1024, in run
run_metadata=run_metadata)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 827, in run
return self._sess.run(*args, **kwargs)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 889, in run
run_metadata_ptr)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1120, in _run
feed_dict_tensor, options, run_metadata)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1317, in _do_run
options, run_metadata)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1336, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Dense float feature must be a matrix.
[[Node: gbdt_1/GradientTreesPartitionExamples = GradientTreesPartitionExamples[num_dense_float_features=10, num_sparse_float_features=0, num_sparse_int_features=0, use_locking=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](ensemble_model, shuffle_batch:16, shuffle_batch:18, shuffle_batch:20, shuffle_batch:21, shuffle_batch:22, shuffle_batch:23, shuffle_batch:24, shuffle_batch:25, shuffle_batch:26, shuffle_batch:27, ^gbdt_1/TreeEnsembleStats)]]
Caused by op u'gbdt_1/GradientTreesPartitionExamples', defined at:
File "./trainer/task.py", line 162, in <module>
run(args)
File "./trainer/task.py", line 157, in run
learn_runner.run(get_experiment_fn(args), args.model_dir)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/learn_runner.py", line 218, in run
return _execute_schedule(experiment, schedule)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/learn_runner.py", line 46, in _execute_schedule
return task()
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/experiment.py", line 625, in train_and_evaluate
self.train(delay_secs=0)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/experiment.py", line 367, in train
hooks=self._train_monitors + extra_hooks)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/experiment.py", line 812, in _call_train
monitors=hooks)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/python/util/deprecation.py", line 316, in new_func
return func(*args, **kwargs)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 480, in fit
loss = self._train_model(input_fn=input_fn, hooks=hooks)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 986, in _train_model
model_fn_ops = self._get_train_ops(features, labels)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 1202, in _get_train_ops
return self._call_model_fn(features, labels, model_fn_lib.ModeKeys.TRAIN)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 1166, in _call_model_fn
model_fn_results = self._model_fn(features, labels, **kwargs)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/contrib/boosted_trees/estimator_batch/model.py", line 98, in model_builder
predictions_dict = gbdt_model.predict(mode)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/contrib/boosted_trees/python/training/functions/gbdt_batch.py", line 463, in predict
ensemble_stamp, mode)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/contrib/boosted_trees/python/training/functions/gbdt_batch.py", line 392, in _predict_and_return_dict
use_locking=True)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/contrib/boosted_trees/python/ops/gen_prediction_ops.py", line 117, in gradient_trees_partition_examples
use_locking=use_locking, name=name)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2956, in create_op
op_def=op_def)
File "/Users/amolsharma/anaconda/envs/oldpython/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1470, in __init__
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
InvalidArgumentError (see above for traceback): Dense float feature must be a matrix.
[[Node: gbdt_1/GradientTreesPartitionExamples = GradientTreesPartitionExamples[num_dense_float_features=10, num_sparse_float_features=0, num_sparse_int_features=0, use_locking=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](ensemble_model, shuffle_batch:16, shuffle_batch:18, shuffle_batch:20, shuffle_batch:21, shuffle_batch:22, shuffle_batch:23, shuffle_batch:24, shuffle_batch:25, shuffle_batch:26, shuffle_batch:27, ^gbdt_1/TreeEnsembleStats)]]
I am guessing that the parsing spec created by tf.transform is different from what we normally get.
Can you share the output of transformed_metadata.schema.as_feature_spec()?
As a work-around try adding this line to your input_fn after features = tf.train.shuffle_batch(...):
features = {feature_name: tf.reshape(feature_value, [-1, 1]) for
feature_name, feature_value in features.items()}
I want to create a bidirectional RNN Encoder in
embedding_attention_seq2seq
in
seq2seq_model.py :
here is the code blew
def embedding_attention_seq2seq(encoder_inputs, decoder_inputs, cell,
num_encoder_symbols, num_decoder_symbols,
num_heads=1, output_projection=None,
feed_previous=False, dtype=dtypes.float32,
scope=None, initial_state_attention=False):
with variable_scope.variable_scope(scope or"embedding_attention_seq2seq"):
# Encoder.
encoder_cell = rnn_cell.EmbeddingWrapper(cell, num_encoder_symbols)
encoder_outputs, encoder_state = rnn.rnn(
encoder_cell, encoder_inputs, dtype=dtype)
# First calculate a concatenation of encoder outputs to put attention on.
top_states = [array_ops.reshape(e, [-1, 1, cell.output_size])
for e in encoder_outputs]
attention_states = array_ops.concat(1, top_states)
....
Here the code I changed.Borrowed from https://github.com/ematvey/tensorflow-seq2seq-tutorials/blob/master/2-seq2seq-advanced.ipynb
# Encoder.
encoder_cell = copy.deepcopy(cell)
encoder_cell = core_rnn_cell.EmbeddingWrapper(
encoder_cell,
embedding_classes=num_encoder_symbols,
embedding_size=embedding_size)
(encoder_outputs,
encoder_fw_final_state,
encoder_bw_final_state)=rnn.bidirectional_rnn(
cell_fw=encoder_cell,
cell_bw=encoder_cell,
encoder_inputs,
dtype=dtype)
encoder_final_state_c = tf.concat(
(encoder_fw_final_state.c, encoder_bw_final_state.c), 1)
encoder_final_state_h = tf.concat(
(encoder_fw_final_state.h, encoder_bw_final_state.h), 1)
encoder_state = LSTMStateTuple(
c=encoder_final_state_c,
h=encoder_final_state_h)
list of errors:
Traceback (most recent call last):
File "translate.py", line 301, in <module>
tf.app.run()
File "/home/tensorflow/anaconda3/envs/tf/lib/python3.4/site-packages/tensorflow/python/platform/app.py", line 43, in run
sys.exit(main(sys.argv[:1] + flags_passthrough))
File "translate.py", line 297, in main
train()
File "translate.py", line 156, in train
model = create_model(sess, False)
File "translate.py", line 134, in create_model
dtype=dtype)
File "/home/tensorflow/Downloads/NMT-jp-ch-master/seq2seq_model.py", line 185, in __init__
softmax_loss_function=softmax_loss_function)
File "/home/tensorflow/Downloads/NMT-jp-ch-master/seq2seq.py", line 628, in model_with_buckets
decoder_inputs[:bucket[1]])
File "/home/tensorflow/Downloads/NMT-jp-ch-master/seq2seq_model.py", line 184, in <lambda>
lambda x, y: seq2seq_f(x, y, False),
File "/home/tensorflow/Downloads/NMT-jp-ch-master/seq2seq_model.py", line 148, in seq2seq_f
dtype=dtype)
File "/home/tensorflow/Downloads/NMT-jp-ch-master/seq2seq.py", line 432, in embedding_attention_seq2seq
inputs=encoder_inputs
File "/home/tensorflow/anaconda3/envs/tf/lib/python3.4/site-packages/tensorflow/python/ops/rnn.py", line 652, in bidirectional_dynamic_rnn
time_major=time_major, scope=fw_scope)
File "/home/tensorflow/anaconda3/envs/tf/lib/python3.4/site-packages/tensorflow/python/ops/rnn.py", line 789, in dynamic_rnn
for input_ in flat_input)
File "/home/tensorflow/anaconda3/envs/tf/lib/python3.4/site-packages/tensorflow/python/ops/rnn.py", line 789, in <genexpr>
for input_ in flat_input)
File "/home/tensorflow/anaconda3/envs/tf/lib/python3.4/site-packages/tensorflow/python/ops/array_ops.py", line 1280, in transpose
ret = gen_array_ops.transpose(a, perm, name=name)
File "/home/tensorflow/anaconda3/envs/tf/lib/python3.4/site-packages/tensorflow/python/ops/gen_array_ops.py", line 3656, in transpose
result = _op_def_lib.apply_op("Transpose", x=x, perm=perm, name=name)
File "/home/tensorflow/anaconda3/envs/tf/lib/python3.4/site-packages/tensorflow/python/framework/op_def_library.py", line 759, in apply_op
op_def=op_def)
File "/home/tensorflow/anaconda3/envs/tf/lib/python3.4/site-packages/tensorflow/python/framework/ops.py", line 2242, in create_op
set_shapes_for_outputs(ret)
File "/home/tensorflow/anaconda3/envs/tf/lib/python3.4/site-packages/tensorflow/python/framework/ops.py", line 1617, in set_shapes_for_outputs
shapes = shape_func(op)
File "/home/tensorflow/anaconda3/envs/tf/lib/python3.4/site-packages/tensorflow/python/framework/ops.py", line 1568, in call_with_requiring
return call_cpp_shape_fn(op, require_shape_fn=True)
File "/home/tensorflow/anaconda3/envs/tf/lib/python3.4/site-packages/tensorflow/python/framework/common_shapes.py", line 610, in call_cpp_shape_fn
debug_python_shape_fn, require_shape_fn)
File "/home/tensorflow/anaconda3/envs/tf/lib/python3.4/site-packages/tensorflow/python/framework/common_shapes.py", line 675, in _call_cpp_shape_fn_impl
raise ValueError(err.message)
ValueError: Dimension must be 1 but is 3 for 'model_with_buckets/embedding_attention_seq2seq/BiRNN/FW/transpose' (op: 'Transpose') with input shapes: [?], [3].
I use py3.4 and tf-v0.12
How to create the proper bidirectional RNN Encoder with the https://github.com/tensorflow/tensorflow/blob/master/tensorflow/contrib/rnn/python/ops/rnn.py in seq2seq model ?
Thank you in advance.
The problem solved by
top_states = [array_ops.reshape(e, [-1, 1, cell.output_size*2])
Yes，reshape should *2 .