The problem being solved is a binary classification using CNN. Here I have images of different size. I am scaled down the images to 20% and normalizing them to the range (0,1) and obviously they still have different sizes. I am using x_train = tf.ragged.constant(normalized_train) to pass them into the CNN but I get an error as mentioned below -
ValueError: The channel dimension of the inputs should be defined. Found None.
Can anyone help?
Also, please suggest if I can use padding around the images to bring everything into same size without distorting the images.
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, Dropout, MaxPooling2D, Flatten, Dense
model = Sequential()
model.add(Conv2D(filters=32, kernel_size=3, activation="relu"))
model.add(Conv2D(filters=64, kernel_size=3, activation="relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(rate=0.2))
model.add(Flatten())
model.add(Dense(128, activation="relu"))
model.add(Dense(1, activation="sigmoid"))
**X_train = tf.ragged.constant(normalized_train)** # allows to pass different size objects
y_train = tf.convert_to_tensor(y_train) # converting list type to tensor
**X_test = tf.ragged.constant(normalized_test)**
y_test = tf.convert_to_tensor(y_test) # converting list type to tensor
model.compile(loss="binary_crossentropy", metrics=\["accuracy"\], optimizer="adam")
model.fit(X_train, y_train, validation_data=(X_test,y_test), epochs = 3)
Detailed error is:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-35-aa60c2e9ae0d> in <module>
1 model.compile(loss="binary_crossentropy", metrics=["accuracy"], optimizer="adam")
2 # model.fit(normalized_train, y_train, validation_data=(normalized_test,y_test), epochs = 3)
----> 3 model.fit(X_train, y_train, validation_data=(X_test,y_test), epochs = 3)
/opt/anaconda3/lib/python3.7/site-packages/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
1182 _r=1):
1183 callbacks.on_train_batch_begin(step)
-> 1184 tmp_logs = self.train_function(iterator)
1185 if data_handler.should_sync:
1186 context.async_wait()
/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
883
884 with OptionalXlaContext(self._jit_compile):
--> 885 result = self._call(*args, **kwds)
886
887 new_tracing_count = self.experimental_get_tracing_count()
/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
931 # This is the first call of __call__, so we have to initialize.
932 initializers = []
--> 933 self._initialize(args, kwds, add_initializers_to=initializers)
934 finally:
935 # At this point we know that the initialization is complete (or less
/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py in _initialize(self, args, kwds, add_initializers_to)
758 self._concrete_stateful_fn = (
759 self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access
--> 760 *args, **kwds))
761
762 def invalid_creator_scope(*unused_args, **unused_kwds):
/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/eager/function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
3064 args, kwargs = None, None
3065 with self._lock:
-> 3066 graph_function, _ = self._maybe_define_function(args, kwargs)
3067 return graph_function
3068
/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/eager/function.py in _maybe_define_function(self, args, kwargs)
3461
3462 self._function_cache.missed.add(call_context_key)
-> 3463 graph_function = self._create_graph_function(args, kwargs)
3464 self._function_cache.primary[cache_key] = graph_function
3465
/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/eager/function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
3306 arg_names=arg_names,
3307 override_flat_arg_shapes=override_flat_arg_shapes,
-> 3308 capture_by_value=self._capture_by_value),
3309 self._function_attributes,
3310 function_spec=self.function_spec,
/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/framework/func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes, acd_record_initial_resource_uses)
1005 _, original_func = tf_decorator.unwrap(python_func)
1006
-> 1007 func_outputs = python_func(*func_args, **func_kwargs)
1008
1009 # invariant: `func_outputs` contains only Tensors, CompositeTensors,
/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py in wrapped_fn(*args, **kwds)
666 # the function a weak reference to itself to avoid a reference cycle.
667 with OptionalXlaContext(compile_with_xla):
--> 668 out = weak_wrapped_fn().__wrapped__(*args, **kwds)
669 return out
670
/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
992 except Exception as e: # pylint:disable=broad-except
993 if hasattr(e, "ag_error_metadata"):
--> 994 raise e.ag_error_metadata.to_exception(e)
995 else:
996 raise
ValueError: in user code:
/opt/anaconda3/lib/python3.7/site-packages/keras/engine/training.py:853 train_function *
return step_function(self, iterator)
/opt/anaconda3/lib/python3.7/site-packages/keras/engine/training.py:842 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/distribute/distribute_lib.py:1286 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/distribute/distribute_lib.py:2849 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/distribute/distribute_lib.py:3632 _call_for_each_replica
return fn(*args, **kwargs)
/opt/anaconda3/lib/python3.7/site-packages/keras/engine/training.py:835 run_step **
outputs = model.train_step(data)
/opt/anaconda3/lib/python3.7/site-packages/keras/engine/training.py:787 train_step
y_pred = self(x, training=True)
/opt/anaconda3/lib/python3.7/site-packages/keras/engine/base_layer.py:1037 __call__
outputs = call_fn(inputs, *args, **kwargs)
/opt/anaconda3/lib/python3.7/site-packages/keras/engine/sequential.py:383 call
outputs = layer(inputs, **kwargs)
/opt/anaconda3/lib/python3.7/site-packages/keras/engine/base_layer.py:1030 __call__
self._maybe_build(inputs)
/opt/anaconda3/lib/python3.7/site-packages/keras/engine/base_layer.py:2659 _maybe_build
self.build(input_shapes) # pylint:disable=not-callable
/opt/anaconda3/lib/python3.7/site-packages/keras/layers/convolutional.py:187 build
input_channel = self._get_input_channel(input_shape)
/opt/anaconda3/lib/python3.7/site-packages/keras/layers/convolutional.py:366 _get_input_channel
raise ValueError('The channel dimension of the inputs '
ValueError: The channel dimension of the inputs should be defined. Found `None`.
Related
Here is the model im using
X_test, X_valid, y_test, y_valid = train_test_split(testReview,testLabel, test_size = 0.4,shuffle=True, random_state = 42,stratify=testLabel)
print(len(X_test), len(X_valid))
print((X_valid.shape), X.shape)
def read_glove_vector(glove_vec):
with open(glove_vec, 'r', encoding='UTF-8') as f:
words = set()
word_to_vec_map = {}
for line in f:
w_line = line.split()
curr_word = w_line[0]
word_to_vec_map[curr_word] = np.array(w_line[1:], dtype='float32')
return word_to_vec_map
word_to_vec_map = read_glove_vector('/content/drive/MyDrive/Colab Notebooks/AmazonCustomerReview/glove.6B.100d.txt')
maxLen = 123
vocab_len = len(word_to_index)
embed_vector_len = word_to_vec_map['moon'].shape[0]
emb_matrix = np.zeros((vocab_len, embed_vector_len))
for word, index in word_to_index.items():
embedding_vector = word_to_vec_map.get(word)
if embedding_vector is not None:
emb_matrix[index] = embedding_vector
print('Build model...')
model = Sequential()
model.add(Embedding(vocab_len, embed_vector_len, input_length=maxLen))
model.add(Flatten())
model.add(Dense(32, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
# Load GloVe embeding
model.layers[0].set_weights([emb_matrix])
model.layers[0].trainable = False
print(model.summary())
# Training and evaluation
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])
model.fit(X, y, epochs=2, batch_size=32,
validation_data=(X_valid,y_valid))
print("Result: ", model.metrics_names, model.evaluate(X_test, y_test))
After this the Error i encounter is this
Epoch 1/2
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
<ipython-input-62-4152e138ca8e> in <module>()
----> 1 model.fit(X, y, batch_size=32, epochs=2, verbose=2)
2 # model.fit(X, y, epochs=2, batch_size=32)
3 # # validation_data=(X_valid,y_valid))
1 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
53 ctx.ensure_initialized()
54 tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
---> 55 inputs, attrs, num_outputs)
56 except core._NotOkStatusException as e:
57 if name is not None:
InvalidArgumentError: Graph execution error:
The issue is , i did run the full code 1 hour ago, it was completed perfectly.
After i just tried to fine tune to the Model if i get better result or not, but just unexpected stuck on this , if any mistake have here, it wont run fully the 1st time , but got this error in 3rd time running.
What is the solution to this?
Kindly, I am trying to create an ML model using SVM using a dataset with 23 features and the output should be (0 or 1) which means two classes. My Target to show the visualization before and after the classification.
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
ds= pd.read_csv("dataset_sdn.csv")
ds= ds.fillna(0)
X = ds.iloc[: , [4,5,6,7,8,9,10,11,12,13,14,17,18,19,20,21]] # Input Features
Y = ds.iloc[:, 22] # OutPut
X_Train, X_Test, Y_Train, Y_Test = train_test_split (X, Y, test_size=0.25, random_state=0)
sc_X = StandardScaler()
X_Train = sc_X.fit_transform(X_Train)
X_Test = sc_X.transform(X_Test)
Then i tried to visualization the X and Y
import matplotlib.pyplot as plt
plt.scatter(X,Y)
plt.show()
But i got error
--------------------------------------------------------------------------- ValueError Traceback (most recent call last) Input In [11], in <cell line: 2>()
1 import matplotlib.pyplot as plt
----> 2 plt.scatter(X,Y)
3 plt.show()
File ~\AppData\Roaming\Python\Python310\site-packages\matplotlib\pyplot.py:2817, in scatter(x, y, s, c, marker, cmap, norm, vmin, vmax, alpha, linewidths, edgecolors, plotnonfinite, data, **kwargs) 2812 #_copy_docstring_and_deprecators(Axes.scatter) 2813 def scatter( 2814 x, y, s=None, c=None, marker=None, cmap=None, norm=None, 2815 vmin=None, vmax=None, alpha=None, linewidths=None, *, 2816 edgecolors=None, plotnonfinite=False, data=None,
**kwargs):
-> 2817 __ret = gca().scatter( 2818 x, y, s=s, c=c, marker=marker, cmap=cmap, norm=norm, 2819 vmin=vmin, vmax=vmax, alpha=alpha, linewidths=linewidths, 2820 edgecolors=edgecolors, plotnonfinite=plotnonfinite, 2821
**({"data": data} if data is not None else {}), **kwargs) 2822 sci(__ret) 2823 return __ret
File ~\AppData\Roaming\Python\Python310\site-packages\matplotlib\__init__.py:1414, in _preprocess_data.<locals>.inner(ax, data, *args, **kwargs) 1411 #functools.wraps(func) 1412 def inner(ax, *args, data=None,
**kwargs): 1413 if data is None:
-> 1414 return func(ax, *map(sanitize_sequence, args), **kwargs) 1416 bound = new_sig.bind(ax, *args, **kwargs) 1417 auto_label = (bound.arguments.get(label_namer) 1418 or bound.kwargs.get(label_namer))
File ~\AppData\Roaming\Python\Python310\site-packages\matplotlib\axes\_axes.py:4368, in Axes.scatter(self, x, y, s, c, marker, cmap, norm, vmin, vmax, alpha, linewidths, edgecolors, plotnonfinite, **kwargs) 4366 y = np.ma.ravel(y) 4367 if x.size != y.size:
-> 4368 raise ValueError("x and y must be the same size") 4370 if s is None: 4371 s = (20 if rcParams['_internal.classic_mode'] else 4372 rcParams['lines.markersize'] ** 2.0)
ValueError: x and y must be the same size
Then i start the classification
classifier = SVC (kernel='rbf', C=1, random_state=0,)
classifier.fit(X_Train, Y_Train)
Y_pred = classifier.predict(X_Test)
print (Y_pred)
The I tried to use below code but not work
from mlxtend.plotting import plot_decision_regions
plot_decision_regions(X=X_Test, y=Y_Test, clf=classifier, legend=1)
I get this error
--------------------------------------------------------------------------- ValueError Traceback (most recent call last) Input In [10], in <cell line: 2>()
1 from mlxtend.plotting import plot_decision_regions
----> 2 plot_decision_regions(X=Y_Test, y=X_Test, clf=classifier,legend=2)
File ~\AppData\Local\Programs\Python\Python310\lib\site-packages\mlxtend\plotting\decision_regions.py:148, in plot_decision_regions(X, y, clf, feature_index, filler_feature_values, filler_feature_ranges, ax, X_highlight, zoom_factor, legend, hide_spines, markers, colors, scatter_kwargs, contourf_kwargs, contour_kwargs, scatter_highlight_kwargs)
44 def plot_decision_regions(
45 X,
46 y, (...)
65 scatter_highlight_kwargs=None,
66 ):
67 """Plot decision regions of a classifier.
68
69 Please note that this functions assumes that class labels are (...)
145
146 """
--> 148 check_Xy(X, y, y_int=True) # Validate X and y arrays
149 dim = X.shape[1]
151 if ax is None:
File ~\AppData\Local\Programs\Python\Python310\lib\site-packages\mlxtend\utils\checking.py:16, in check_Xy(X, y, y_int)
12 def check_Xy(X, y, y_int=True):
13
14 # check types
15 if not isinstance(X, np.ndarray):
---> 16 raise ValueError("X must be a NumPy array. Found %s" % type(X))
17 if not isinstance(y, np.ndarray):
18 raise ValueError("y must be a NumPy array. Found %s" % type(y))
ValueError: X must be a NumPy array. Found <class 'pandas.core.series.Series'>
So, please your advice to how show the visualization. Thanks in advance
See here:
X = ds.iloc[: , [4,5,6,7,8,9,10,11,12,13,14,17,18,19,20,21]] # Input Features
Y = ds.iloc[:, 22] # OutPut
and then here
plt.scatter(X,Y)
Your X vector is multi-dimensional vector having a size of 16 and hence the scatterplot is not working. You can only plot 2 variables in a 2D scatterplot.
So you have plot for each feature vs Y, e.g.,
plt.scatter(X.iloc[:,0], Y)
So, I have been working on my first ML project and as part of that I have been trying out various models from sci-kit learn and I wrote this piece of code for a random forest model:
#Random Forest
reg = RandomForestRegressor(random_state=0, criterion = 'mse')
#Apply grid search for best parameters
params = {'randomforestregressor__n_estimators' : range(100, 500, 200),
'randomforestregressor__min_samples_split' : range(2, 10, 3)}
pipe = make_pipeline(reg)
grid = GridSearchCV(pipe, param_grid = params, scoring='mean_squared_error', n_jobs=-1, iid=False, cv=5)
reg = grid.fit(X_train, y_train)
print('Best MSE: ', grid.best_score_)
print('Best Parameters: ', grid.best_estimator_)
y_train_pred = reg.predict(X_train)
y_test_pred = reg.predict(X_test)
tr_err = mean_squared_error(y_train_pred, y_train)
ts_err = mean_squared_error(y_test_pred, y_test)
print(tr_err, ts_err)
results_train['random_forest'] = tr_err
results_test['random_forest'] = ts_err
But, when I run this code, I get the following error:
KeyError Traceback (most recent call last)
~\anaconda3\lib\site-packages\sklearn\metrics\_scorer.py in get_scorer(scoring)
359 else:
--> 360 scorer = SCORERS[scoring]
361 except KeyError:
KeyError: 'mean_squared_error'
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
<ipython-input-149-394cd9e0c273> in <module>
5 pipe = make_pipeline(reg)
6 grid = GridSearchCV(pipe, param_grid = params, scoring='mean_squared_error', n_jobs=-1, iid=False, cv=5)
----> 7 reg = grid.fit(X_train, y_train)
8 print('Best MSE: ', grid.best_score_)
9 print('Best Parameters: ', grid.best_estimator_)
~\anaconda3\lib\site-packages\sklearn\utils\validation.py in inner_f(*args, **kwargs)
71 FutureWarning)
72 kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 73 return f(**kwargs)
74 return inner_f
75
~\anaconda3\lib\site-packages\sklearn\model_selection\_search.py in fit(self, X, y, groups, **fit_params)
652 cv = check_cv(self.cv, y, classifier=is_classifier(estimator))
653
--> 654 scorers, self.multimetric_ = _check_multimetric_scoring(
655 self.estimator, scoring=self.scoring)
656
~\anaconda3\lib\site-packages\sklearn\metrics\_scorer.py in _check_multimetric_scoring(estimator, scoring)
473 if callable(scoring) or scoring is None or isinstance(scoring,
474 str):
--> 475 scorers = {"score": check_scoring(estimator, scoring=scoring)}
476 return scorers, False
477 else:
~\anaconda3\lib\site-packages\sklearn\utils\validation.py in inner_f(*args, **kwargs)
71 FutureWarning)
72 kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 73 return f(**kwargs)
74 return inner_f
75
~\anaconda3\lib\site-packages\sklearn\metrics\_scorer.py in check_scoring(estimator, scoring, allow_none)
403 "'fit' method, %r was passed" % estimator)
404 if isinstance(scoring, str):
--> 405 return get_scorer(scoring)
406 elif callable(scoring):
407 # Heuristic to ensure user has not passed a metric
~\anaconda3\lib\site-packages\sklearn\metrics\_scorer.py in get_scorer(scoring)
360 scorer = SCORERS[scoring]
361 except KeyError:
--> 362 raise ValueError('%r is not a valid scoring value. '
363 'Use sorted(sklearn.metrics.SCORERS.keys()) '
364 'to get valid options.' % scoring)
ValueError: 'mean_squared_error' is not a valid scoring value. Use sorted(sklearn.metrics.SCORERS.keys()) to get valid options.
So, I tried running it by removing the scoring='mean_squared_error' from GridSearchCV(pipe, param_grid = params, scoring='mean_squared_error', n_jobs=-1, iid=False, cv=5). When I do that, the code runs perfectly and gives a decent enough training and testing error.
Regardless of that, I can't figure out why with scoring='mean_squared_error' parameter in GridSearchCV function throws me that error. What am I doing wrong?
According to the documentation:
All scorer objects follow the convention that higher return values are better than lower return values. Thus metrics which measure the distance between the model and the data, like metrics.mean_squared_error, are available as neg_mean_squared_error which return the negated value of the metric.
This means that you have to pass scoring='neg_mean_squared_error' in order to evaluate the grid search results with Mean Squared Error.
I am not able to resolve this error. This code is taken from https://becominghuman.ai/extract-a-feature-vector-for-any-image-with-pytorch-9717561d1d4c
import torch
import torch.nn as nn
import torchvision.models as models
import torchvision.transforms as transforms
from torch.autograd import Variable
from PIL import Image
pic_one = '/content/drive/My Drive/Video_Recommender/zframe1.jpg'
pic_two = '/content/drive/My Drive/Video_Recommender/zframe2.jpg'
model = models.resnet18(pretrained=True)
layer = model._modules.get('avgpool')
scaler = transforms.Scale((224, 224))
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
to_tensor = transforms.ToTensor()
def get_vector(image_name):
# 1. Load the image with Pillow library
img = Image.open(image_name)
# 2. Create a PyTorch Variable with the transformed image
t_img = Variable(normalize(to_tensor(scaler(img))).unsqueeze(0))
# 3. Create a vector of zeros that will hold our feature vector
# The 'avgpool' layer has an output size of 512
my_embedding = torch.zeros(512)
# 4. Define a function that will copy the output of a layer
def copy_data(m, i, o):
my_embedding.copy_(o.data)
# 5. Attach that function to our selected layer
h = layer.register_forward_hook(copy_data)
# 6. Run the model on our transformed image
model(t_img)
# 7. Detach our copy function from the layer
h.remove()
# 8. Return the feature vector
return my_embedding
pic_one_vector = get_vector(pic_one)
pic_two_vector = get_vector(pic_two)
Error:-
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-41-ca2d66de2d9c> in <module>()
----> 1 pic_one_vector = get_vector(pic_one)
2 pic_two_vector = get_vector(pic_two)
5 frames
<ipython-input-40-a45affe9d8f7> in get_vector(image_name)
13 h = layer.register_forward_hook(copy_data)
14 # 6. Run the model on our transformed image
---> 15 model(t_img)
16 # 7. Detach our copy function from the layer
17 h.remove()
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
548 result = self._slow_forward(*input, **kwargs)
549 else:
--> 550 result = self.forward(*input, **kwargs)
551 for hook in self._forward_hooks.values():
552 hook_result = hook(self, input, result)
/usr/local/lib/python3.6/dist-packages/torchvision/models/resnet.py in forward(self, x)
218
219 def forward(self, x):
--> 220 return self._forward_impl(x)
221
222
/usr/local/lib/python3.6/dist-packages/torchvision/models/resnet.py in _forward_impl(self, x)
211 x = self.layer4(x)
212
--> 213 x = self.avgpool(x)
214 x = torch.flatten(x, 1)
215 x = self.fc(x)
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
550 result = self.forward(*input, **kwargs)
551 for hook in self._forward_hooks.values():
--> 552 hook_result = hook(self, input, result)
553 if hook_result is not None:
554 result = hook_result
<ipython-input-40-a45affe9d8f7> in copy_data(m, i, o)
9 # 4. Define a function that will copy the output of a layer
10 def copy_data(m, i, o):
---> 11 my_embedding.copy_(o.data)
12 # 5. Attach that function to our selected layer
13 h = layer.register_forward_hook(copy_data)
RuntimeError: output with shape [512] doesn't match the broadcast shape [1, 512, 1, 512]
What I am actually trying to do is trying to extract feature vector from images that I want to further use for building a recommendation system. Do inform me if there is any other alternative available.
Thanks in advance!!!
You need to reshape the output data after avgpool:
def copy_data(m, i, o):
my_embedding.copy_(o.data.reshape(o.data.size(1)))
Alternatively, you may replace the hook function with the following, just so you don't have to deal with adjusting the output shape:
# step 3 and 4
my_embedding = None
def my_hook(module_, input_, output_):
nonlocal my_output
my_embedding = output_
then simply call the following
# step 5
h = layer.register_forward_hook(my_hook)
I have built a RNN with BasicRNN now I want to use the LSTMCell but the passage does not seem trivial. What should I change?
First i define all the placeholders and variables:
X_placeholder = tf.placeholder(tf.float32, [batch_size, truncated_backprop_length, embedding_size])
Y_placeholder = tf.placeholder(tf.int32, [batch_size, truncated_backprop_length])
init_state = tf.placeholder(tf.float32, [batch_size, state_size])
W = tf.Variable(np.random.rand(state_size, num_classes),dtype=tf.float32)
b = tf.Variable(np.zeros((batch_size, num_classes)), dtype=tf.float32)
W2 = tf.Variable(np.random.rand(state_size, num_classes),dtype=tf.float32)
b2 = tf.Variable(np.zeros((batch_size, num_classes)), dtype=tf.float32)
Then I unstack the labels:
labels_series = tf.transpose(batchY_placeholder)
labels_series = tf.unstack(batchY_placeholder, axis=1)
inputs_series = X_placeholder
Then i define my RNN:
cell = tf.contrib.rnn.BasicLSTMCell(state_size, state_is_tuple = False)
states_series, current_state = tf.nn.dynamic_rnn(cell, inputs_series, initial_state = init_state)
The error that I get is:
InvalidArgumentError Traceback (most recent call last)
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/framework/common_shapes.py in _call_cpp_shape_fn_impl(op, input_tensors_needed, input_tensors_as_shapes_needed, debug_python_shape_fn, require_shape_fn)
669 node_def_str, input_shapes, input_tensors, input_tensors_as_shapes,
--> 670 status)
671 except errors.InvalidArgumentError as err:
/home/deepnlp2017/anaconda3/lib/python3.5/contextlib.py in __exit__(self, type, value, traceback)
65 try:
---> 66 next(self.gen)
67 except StopIteration:
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py in raise_exception_on_not_ok_status()
468 compat.as_text(pywrap_tensorflow.TF_Message(status)),
--> 469 pywrap_tensorflow.TF_GetCode(status))
470 finally:
InvalidArgumentError: Dimensions must be equal, but are 50 and 100 for 'rnn/while/basic_lstm_cell/mul' (op: 'Mul') with input shapes: [32,50], [32,100].
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
<ipython-input-19-2ac617f4dde4> in <module>()
4 #cell = tf.contrib.rnn.BasicRNNCell(state_size)
5 cell = tf.contrib.rnn.BasicLSTMCell(state_size, state_is_tuple = False)
----> 6 states_series, current_state = tf.nn.dynamic_rnn(cell, inputs_series, initial_state = init_state)
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/rnn.py in dynamic_rnn(cell, inputs, sequence_length, initial_state, dtype, parallel_iterations, swap_memory, time_major, scope)
543 swap_memory=swap_memory,
544 sequence_length=sequence_length,
--> 545 dtype=dtype)
546
547 # Outputs of _dynamic_rnn_loop are always shaped [time, batch, depth].
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/rnn.py in _dynamic_rnn_loop(cell, inputs, initial_state, parallel_iterations, swap_memory, sequence_length, dtype)
710 loop_vars=(time, output_ta, state),
711 parallel_iterations=parallel_iterations,
--> 712 swap_memory=swap_memory)
713
714 # Unpack final output if not using output tuples.
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/control_flow_ops.py in while_loop(cond, body, loop_vars, shape_invariants, parallel_iterations, back_prop, swap_memory, name)
2624 context = WhileContext(parallel_iterations, back_prop, swap_memory, name)
2625 ops.add_to_collection(ops.GraphKeys.WHILE_CONTEXT, context)
-> 2626 result = context.BuildLoop(cond, body, loop_vars, shape_invariants)
2627 return result
2628
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/control_flow_ops.py in BuildLoop(self, pred, body, loop_vars, shape_invariants)
2457 self.Enter()
2458 original_body_result, exit_vars = self._BuildLoop(
-> 2459 pred, body, original_loop_vars, loop_vars, shape_invariants)
2460 finally:
2461 self.Exit()
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/control_flow_ops.py in _BuildLoop(self, pred, body, original_loop_vars, loop_vars, shape_invariants)
2407 structure=original_loop_vars,
2408 flat_sequence=vars_for_body_with_tensor_arrays)
-> 2409 body_result = body(*packed_vars_for_body)
2410 if not nest.is_sequence(body_result):
2411 body_result = [body_result]
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/rnn.py in _time_step(time, output_ta_t, state)
695 skip_conditionals=True)
696 else:
--> 697 (output, new_state) = call_cell()
698
699 # Pack state if using state tuples
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/rnn.py in <lambda>()
681
682 input_t = nest.pack_sequence_as(structure=inputs, flat_sequence=input_t)
--> 683 call_cell = lambda: cell(input_t, state)
684
685 if sequence_length is not None:
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/contrib/rnn/python/ops/core_rnn_cell_impl.py in __call__(self, inputs, state, scope)
182 i, j, f, o = array_ops.split(value=concat, num_or_size_splits=4, axis=1)
183
--> 184 new_c = (c * sigmoid(f + self._forget_bias) + sigmoid(i) *
185 self._activation(j))
186 new_h = self._activation(new_c) * sigmoid(o)
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/math_ops.py in binary_op_wrapper(x, y)
882 if not isinstance(y, sparse_tensor.SparseTensor):
883 y = ops.convert_to_tensor(y, dtype=x.dtype.base_dtype, name="y")
--> 884 return func(x, y, name=name)
885
886 def binary_op_wrapper_sparse(sp_x, y):
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/math_ops.py in _mul_dispatch(x, y, name)
1103 is_tensor_y = isinstance(y, ops.Tensor)
1104 if is_tensor_y:
-> 1105 return gen_math_ops._mul(x, y, name=name)
1106 else:
1107 assert isinstance(y, sparse_tensor.SparseTensor) # Case: Dense * Sparse.
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/gen_math_ops.py in _mul(x, y, name)
1623 A `Tensor`. Has the same type as `x`.
1624 """
-> 1625 result = _op_def_lib.apply_op("Mul", x=x, y=y, name=name)
1626 return result
1627
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py in apply_op(self, op_type_name, name, **keywords)
761 op = g.create_op(op_type_name, inputs, output_types, name=scope,
762 input_types=input_types, attrs=attr_protos,
--> 763 op_def=op_def)
764 if output_structure:
765 outputs = op.outputs
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/framework/ops.py in create_op(self, op_type, inputs, dtypes, input_types, name, attrs, op_def, compute_shapes, compute_device)
2395 original_op=self._default_original_op, op_def=op_def)
2396 if compute_shapes:
-> 2397 set_shapes_for_outputs(ret)
2398 self._add_op(ret)
2399 self._record_op_seen_by_control_dependencies(ret)
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/framework/ops.py in set_shapes_for_outputs(op)
1755 shape_func = _call_cpp_shape_fn_and_require_op
1756
-> 1757 shapes = shape_func(op)
1758 if shapes is None:
1759 raise RuntimeError(
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/framework/ops.py in call_with_requiring(op)
1705
1706 def call_with_requiring(op):
-> 1707 return call_cpp_shape_fn(op, require_shape_fn=True)
1708
1709 _call_cpp_shape_fn_and_require_op = call_with_requiring
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/framework/common_shapes.py in call_cpp_shape_fn(op, input_tensors_needed, input_tensors_as_shapes_needed, debug_python_shape_fn, require_shape_fn)
608 res = _call_cpp_shape_fn_impl(op, input_tensors_needed,
609 input_tensors_as_shapes_needed,
--> 610 debug_python_shape_fn, require_shape_fn)
611 if not isinstance(res, dict):
612 # Handles the case where _call_cpp_shape_fn_impl calls unknown_shape(op).
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/framework/common_shapes.py in _call_cpp_shape_fn_impl(op, input_tensors_needed, input_tensors_as_shapes_needed, debug_python_shape_fn, require_shape_fn)
673 missing_shape_fn = True
674 else:
--> 675 raise ValueError(err.message)
676
677 if missing_shape_fn:
ValueError: Dimensions must be equal, but are 50 and 100 for 'rnn/while/basic_lstm_cell/mul' (op: 'Mul') with input shapes: [32,50], [32,100].
You should consider giving the error trace. Otherwise it is hard (or impossible) to help.
I reproduced the situation and found that the issue was coming from state unpacking, i.e. line c, h = state.
Try to set state_is_tuple to false i.e.
cell = tf.contrib.rnn.BasicLSTMCell(state_size, state_is_tuple=False)
I'm not sure why this is happening. Are you loading a previous model? What is your tensorflow version?
More information on TensorFlow RNN Cells:
I would suggest you to take a look at: WildML post, section "RNN CELLS, WRAPPERS AND MULTI-LAYER RNNS".
It states that:
BasicRNNCell – A vanilla RNN cell.
GRUCell – A Gated Recurrent Unit cell.
BasicLSTMCell – An LSTM cell based on Recurrent Neural Network Regularization. No peephole connection or cell clipping.
LSTMCell – A more complex LSTM cell that allows for optional peephole connections and cell clipping.
MultiRNNCell – A wrapper to combine multiple cells into a multi-layer cell.
DropoutWrapper – A wrapper to add dropout to input and/or output connections of a cell.
Given this, I would suggest you to switch from BasicRNNCell to BasicLSTMCell. Where Basic here means "use it unless you know what you are doing". If you want to try LSTMs without going into details, thats the way to go. It may be straightforward, just replace with it and voilà!
If not, share some of your code + error.
Hope it helps
The problem seems to be with the init_state variable.
Basic RNN cells only have one state variable while LSTM has a visible and a hidden state. Specify the options state_is_tuple=False will concat the two state variables into one, therefore double the size of what you have specified in the init_state declaration.
To avoid this, one can use the built-in zero_state method for an LSTMCell to initialize the state in the correct way without worrying about size differences.
So it would simply be:
init_state = cell.zero_state(batch_size, dtype)
Of course will will have to be placed after the line where the cell is built.