I'm pretty new to Machine Learning, and I'm trying something experimental on a public wine dataset.
I'm ending up with an error and I can't find a solution.
Here is what I'm trying do with my model:
X = data_all[['country', 'description', 'price', 'province', 'variety']]
y = data_all['points']
# Vectorizing Description column (text analysis)
vectorizerDesc = CountVectorizer()
descriptions = X['description']
vectorizerDesc.fit(descriptions)
vectorizedDesc = vectorizer.transform(X['description'])
X['description'] = vectorizedDesc
# Categorizing other string columns
X = pd.get_dummies(X, columns=['country', 'province', 'variety'])
# Generating train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=101)
# Multinomial Naive Bayes
nb = MultinomialNB()
nb.fit(X_train, y_train)
Here's what X looks like just before calling train_test_split:
<class 'pandas.core.frame.DataFrame'>
Int64Index: 83945 entries, 25 to 150929
Columns: 837 entries, description to variety_Zweigelt
dtypes: float64(1), object(1), uint8(835)
The last line (nb.fit) gives me an error:
ValueError Traceback (most recent call last)
<ipython-input-197-9d40e4624ff6> in <module>()
3 # Multinomial Naive Bayes is a specialised version of Naive Bayes designed more for text documents
4 nb = MultinomialNB()
----> 5 nb.fit(X_train, y_train)
/opt/conda/lib/python3.6/site-packages/sklearn/naive_bayes.py in fit(self, X, y, sample_weight)
577 Returns self.
578 """
--> 579 X, y = check_X_y(X, y, 'csr')
580 _, n_features = X.shape
581
/opt/conda/lib/python3.6/site-packages/sklearn/utils/validation.py in check_X_y(X, y, accept_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, multi_output, ensure_min_samples, ensure_min_features, y_numeric, warn_on_dtype, estimator)
571 X = check_array(X, accept_sparse, dtype, order, copy, force_all_finite,
572 ensure_2d, allow_nd, ensure_min_samples,
--> 573 ensure_min_features, warn_on_dtype, estimator)
574 if multi_output:
575 y = check_array(y, 'csr', force_all_finite=True, ensure_2d=False,
/opt/conda/lib/python3.6/site-packages/sklearn/utils/validation.py in check_array(array, accept_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, warn_on_dtype, estimator)
446 # make sure we actually converted to numeric:
447 if dtype_numeric and array.dtype.kind == "O":
--> 448 array = array.astype(np.float64)
449 if not allow_nd and array.ndim >= 3:
450 raise ValueError("Found array with dim %d. %s expected <= 2."
ValueError: setting an array element with a sequence.
Would you know how I could combine my Vectorized text analysis and other datasets (like countries etc...) in a Multinomial NB algorithm?
Thank you in advance :)
Related
I am trying to detect quillbot paraphrasing by using naive bayes in jupyter notebook. My dataset has 2 columns, first column is filled with a sample text from various sources around 250 words. the second column is type, and that is set to either 1 if it is parahrased or 0 if it is the original text. Ive got this code so far but I am getting some errors. here is a link to my dataset: https://pastebin.com/ts8SLGHq and here is my code:
from pydataset import data
import pandas as pd
from sklearn.naive_bayes import GaussianNB
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
from sklearn.feature_extraction.text import CountVectorizer
# read the CSV file into a DataFrame
df = pd.read_csv('Desktop/Dataset.csv', encoding='utf-8')
# specify the column names
df.columns = ['text', 'type']
# split the dataset into train and test sets
train_df, test_df = train_test_split(df, test_size=0.3, random_state=42)
# convert text data into numerical features
vectorizer = CountVectorizer()
X_train = vectorizer.fit_transform(train_df['text'])
X_test = vectorizer.transform(test_df['text'])
y_train = train_df['type'].values
y_test = test_df['type'].values
# initialize a Gaussian Naive Bayes model
model = GaussianNB()
# train the model on the train set
model.fit(X_train, y_train)
# evaluate the model on the test set
accuracy = model.score(X_test, y_test)
print("Model accuracy on test set: {:.2f}%".format(accuracy * 100))
and here is the error I am getting:
```
TypeError Traceback (most recent call last)
Cell In[184], line 5
2 model = GaussianNB()
4 # train the model on the train set
----> 5 model.fit(X_train, y_train)
File ~\AppData\Local\Programs\Python\Python39\lib\site-packages\sklearn\naive_bayes.py:267, in GaussianNB.fit(self, X, y, sample_weight)
265 self._validate_params()
266 y = self._validate_data(y=y)
--> 267 return self._partial_fit(
268 X, y, np.unique(y), _refit=True, sample_weight=sample_weight
269 )
File ~\AppData\Local\Programs\Python\Python39\lib\site-packages\sklearn\naive_bayes.py:428, in GaussianNB._partial_fit(self, X, y, classes, _refit, sample_weight)
425 self.classes_ = None
427 first_call = _check_partial_fit_first_call(self, classes)
--> 428 X, y = self._validate_data(X, y, reset=first_call)
429 if sample_weight is not None:
430 sample_weight = _check_sample_weight(sample_weight, X)
File ~\AppData\Local\Programs\Python\Python39\lib\site-packages\sklearn\base.py:565, in BaseEstimator._validate_data(self, X, y, reset, validate_separately, **check_params)
563 y = check_array(y, input_name="y", **check_y_params)
564 else:
--> 565 X, y = check_X_y(X, y, **check_params)
566 out = X, y
568 if not no_val_X and check_params.get("ensure_2d", True):
File ~\AppData\Local\Programs\Python\Python39\lib\site-packages\sklearn\utils\validation.py:1106, in check_X_y(X, y, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, multi_output, ensure_min_samples, ensure_min_features, y_numeric, estimator)
1101 estimator_name = _check_estimator_name(estimator)
1102 raise ValueError(
1103 f"{estimator_name} requires y to be passed, but the target y is None"
1104 )
-> 1106 X = check_array(
1107 X,
1108 accept_sparse=accept_sparse,
1109 accept_large_sparse=accept_large_sparse,
1110 dtype=dtype,
1111 order=order,
1112 copy=copy,
1113 force_all_finite=force_all_finite,
1114 ensure_2d=ensure_2d,
1115 allow_nd=allow_nd,
1116 ensure_min_samples=ensure_min_samples,
1117 ensure_min_features=ensure_min_features,
1118 estimator=estimator,
1119 input_name="X",
1120 )
1122 y = _check_y(y, multi_output=multi_output, y_numeric=y_numeric, estimator=estimator)
1124 check_consistent_length(X, y)
File ~\AppData\Local\Programs\Python\Python39\lib\site-packages\sklearn\utils\validation.py:845, in check_array(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, estimator, input_name)
843 if sp.issparse(array):
844 _ensure_no_complex_data(array)
--> 845 array = _ensure_sparse_format(
846 array,
847 accept_sparse=accept_sparse,
848 dtype=dtype,
849 copy=copy,
850 force_all_finite=force_all_finite,
851 accept_large_sparse=accept_large_sparse,
852 estimator_name=estimator_name,
853 input_name=input_name,
854 )
855 else:
856 # If np.array(..) gives ComplexWarning, then we convert the warning
857 # to an error. This is needed because specifying a non complex
858 # dtype to the function converts complex to real dtype,
859 # thereby passing the test made in the lines following the scope
860 # of warnings context manager.
861 with warnings.catch_warnings():
File ~\AppData\Local\Programs\Python\Python39\lib\site-packages\sklearn\utils\validation.py:522, in _ensure_sparse_format(spmatrix, accept_sparse, dtype, copy, force_all_finite, accept_large_sparse, estimator_name, input_name)
519 _check_large_sparse(spmatrix, accept_large_sparse)
521 if accept_sparse is False:
--> 522 raise TypeError(
523 "A sparse matrix was passed, but dense "
524 "data is required. Use X.toarray() to "
525 "convert to a dense numpy array."
526 )
527 elif isinstance(accept_sparse, (list, tuple)):
528 if len(accept_sparse) == 0:
TypeError: A sparse matrix was passed, but dense data is required. Use X.toarray() to convert to a dense numpy array.`
Any help would be greatly appriciated.
I first tried to convert the data into numerical features but either I did it wrong or there is another issue
Convert sparse matrix to NumPy array
X_train.todense()
I'm trying to train my first CNN. I split the training images into train and validation data by randomly choosing indices and using Subset and DataLoader. The validation and training splits don't have any of the same indices, so that's not the problem. They also cover the entire dataset.
train = datasets.ImageFolder('train_images', transform=transform)
torch.manual_seed(37)
val_split = random.sample(range(len(img_sizes)), int(0.1 * len(img_sizes)))
train_split = [x for x in range(len(img_sizes)) if x not in val_split]
train_data = Subset(train, train_split)
val_data = Subset(train, val_split)
train_loader = DataLoader(train_data, batch_size = 10, shuffle = True)
val_loader = DataLoader(val_data, batch_size = 10, shuffle = False)
However, when I try to enumerate through the train_loader, I get this index out of range error:
---------------------------------------------------------------------------
IndexError Traceback (most recent call last)
~\AppData\Local\Temp\ipykernel_8652\2928585573.py in <module>
13
14 # Run the training batches
---> 15 for b, (X_train, y_train) in enumerate(train_loader):
16
17 # Apply the model
D:\dum\envs\pytorchenv\lib\site-packages\torch\utils\data\dataloader.py in __next__(self)
558 if self.num_workers == 0: # same-process loading
559 indices = next(self.sample_iter) # may raise StopIteration
--> 560 batch = self.collate_fn([self.dataset[i] for i in indices])
561 if self.pin_memory:
562 batch = _utils.pin_memory.pin_memory_batch(batch)
D:\dum\envs\pytorchenv\lib\site-packages\torch\utils\data\dataloader.py in <listcomp>(.0)
558 if self.num_workers == 0: # same-process loading
559 indices = next(self.sample_iter) # may raise StopIteration
--> 560 batch = self.collate_fn([self.dataset[i] for i in indices])
561 if self.pin_memory:
562 batch = _utils.pin_memory.pin_memory_batch(batch)
D:\dum\envs\pytorchenv\lib\site-packages\torch\utils\data\dataset.py in __getitem__(self, idx)
105
106 def __getitem__(self, idx):
--> 107 return self.dataset[self.indices[idx]]
108
109 def __len__(self):
D:\dum\envs\pytorchenv\lib\site-packages\torchvision\datasets\folder.py in __getitem__(self, index)
129 tuple: (sample, target) where target is class_index of the target class.
130 """
--> 131 path, target = self.samples[index]
132 sample = self.loader(path)
133 if self.transform is not None:
IndexError: list index out of range
Anyone know what the problem is?
How do I feed a tf.keras model, that includes a 1D input TF Hub module, with a tf.data.Dataset?
(Ultimately, the aim is to use a single tf.data.Dataset with a multi-input, multi-output keras funtional api model.)
Tried this:
import tensorflow as tf
import tensorflow_hub as hub
embed = "https://tfhub.dev/google/tf2-preview/gnews-swivel-20dim/1"
hub_layer = hub.KerasLayer(embed, output_shape=[20], input_shape=[],
dtype=tf.string, trainable=True, name='hub_layer')
# From tf hub webpage: "The module takes a batch of sentences in a 1-D tensor of strings as input."
input_tensor = tf.keras.Input(shape=(), dtype=tf.string)
hub_tensor = hub_layer(input_tensor)
x = tf.keras.layers.Dense(16, activation='relu')(hub_tensor)#(x)
main_output = tf.keras.layers.Dense(units=4, activation='softmax', name='main_output')(x)
model = tf.keras.models.Model(inputs=[input_tensor], outputs=[main_output])
# This works as expected.
X_tensor = tf.constant(['Hello World', 'The Quick Brown Fox'])
model(X_tensor)
# This fails
X_ds = tf.data.Dataset.from_tensors(X_tensor)
X_ds.element_spec
model(X_ds)
Expectation was that the 1D tensor in the dataset would be automatically extracted and consumed by the model.
Error message:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
in
21 X_ds = tf.data.Dataset.from_tensors(X_tensor)
22 X_ds.element_spec
---> 23 model(X_ds)
24
25
~/projects/email_analysis/email_venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/base_layer.py in __call__(self, *args, **kwargs)
966 with base_layer_utils.autocast_context_manager(
967 self._compute_dtype):
--> 968 outputs = self.call(cast_inputs, *args, **kwargs)
969 self._handle_activity_regularization(inputs, outputs)
970 self._set_mask_metadata(inputs, outputs, input_masks)
~/projects/email_analysis/email_venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/network.py in call(self, inputs, training, mask)
717 return self._run_internal_graph(
718 inputs, training=training, mask=mask,
--> 719 convert_kwargs_to_constants=base_layer_utils.call_context().saving)
720
721 def compute_output_shape(self, input_shape):
~/projects/email_analysis/email_venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/network.py in _run_internal_graph(self, inputs, training, mask, convert_kwargs_to_constants)
835 tensor_dict = {}
836 for x, y in zip(self.inputs, inputs):
--> 837 y = self._conform_to_reference_input(y, ref_input=x)
838 x_id = str(id(x))
839 tensor_dict[x_id] = [y] * self._tensor_usage_count[x_id]
~/projects/email_analysis/email_venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/network.py in _conform_to_reference_input(self, tensor, ref_input)
959 # Dtype handling.
960 if isinstance(ref_input, (ops.Tensor, composite_tensor.CompositeTensor)):
--> 961 tensor = math_ops.cast(tensor, dtype=ref_input.dtype)
962
963 return tensor
~/projects/email_analysis/email_venv/lib/python3.6/site-packages/tensorflow/python/util/dispatch.py in wrapper(*args, **kwargs)
178 """Call target, and fall back on dispatchers if there is a TypeError."""
179 try:
--> 180 return target(*args, **kwargs)
181 except (TypeError, ValueError):
182 # Note: convert_to_eager_tensor currently raises a ValueError, not a
~/projects/email_analysis/email_venv/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py in cast(x, dtype, name)
785 # allows some conversions that cast() can't do, e.g. casting numbers to
786 # strings.
--> 787 x = ops.convert_to_tensor(x, name="x")
788 if x.dtype.base_dtype != base_type:
789 x = gen_math_ops.cast(x, base_type, name=name)
~/projects/email_analysis/email_venv/lib/python3.6/site-packages/tensorflow/python/framework/ops.py in convert_to_tensor(value, dtype, name, as_ref, preferred_dtype, dtype_hint, ctx, accepted_result_types)
1339
1340 if ret is None:
-> 1341 ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
1342
1343 if ret is NotImplemented:
~/projects/email_analysis/email_venv/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py in _constant_tensor_conversion_function(v, dtype, name, as_ref)
319 as_ref=False):
320 _ = as_ref
--> 321 return constant(v, dtype=dtype, name=name)
322
323
~/projects/email_analysis/email_venv/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py in constant(value, dtype, shape, name)
260 """
261 return _constant_impl(value, dtype, shape, name, verify_shape=False,
--> 262 allow_broadcast=True)
263
264
~/projects/email_analysis/email_venv/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py in _constant_impl(value, dtype, shape, name, verify_shape, allow_broadcast)
268 ctx = context.context()
269 if ctx.executing_eagerly():
--> 270 t = convert_to_eager_tensor(value, ctx, dtype)
271 if shape is None:
272 return t
~/projects/email_analysis/email_venv/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py in convert_to_eager_tensor(value, ctx, dtype)
94 dtype = dtypes.as_dtype(dtype).as_datatype_enum
95 ctx.ensure_initialized()
---> 96 return ops.EagerTensor(value, ctx.device_name, dtype)
97
98
ValueError: Attempt to convert a value () with an unsupported type () to a Tensor.
The point of a dataset is to provide a sequence of tensors, like here:
all_data = tf.constant([['Hello', 'World'], ['Brown Fox', 'lazy dog']])
ds = tf.data.Dataset.from_tensor_slices(all_data)
for tensor in ds:
print(tensor)
which outputs
tf.Tensor([b'Hello' b'World'], shape=(2,), dtype=string)
tf.Tensor([b'Brown Fox' b'lazy dog'], shape=(2,), dtype=string)
Instead of just printing tensor, you can compute with it:
for tensor in ds:
print(hub_layer(tensor))
which outputs 2 tensors of shape (2,20) each.
For more, see https://www.tensorflow.org/guide/data.
I am trying to configure a model that I previously trained to classify images in a such a way that it accepts images as base64-strings (instead of a NumPy array), converts them to a NumPy array and then performs the prediction. How do I add a layer on top of my regular input layer that accepts strings and outputs a NumPy array?
So I've already pre-trained a model that predicts images based on the ResNet architecture. Having looked at this and this answer, I am trying to create a Lambda layer that converts strings to RGB jpeg images. I have done this as shown in the sample code below:
image = tf.placeholder(shape=[], dtype=tf.string)
input_tensor = keras.layers.Input(shape = (1,), tensor = image, dtype=tf.string)
x = keras.layers.Lambda(lambda image: tf.image.decode_jpeg(image))(input_tensor)
output_tensor = model(x)
new_model = Model(input_tensor, output_tensor)
Where model() is the Keras keras.models.Model model that I have pre-trained.
I am expecting new_model() to be the new Keras model that has 1 extra layer on top of my previous model, which accepts base64-string and outputs a NumPy array into the next layer.
However, the third line of my code raises the following error:
TypeError: Input 'contents' of 'DecodeJpeg' Op has type float32 that does not match expected type of string.
My understanding of this is that the 'image' in the Lambda layer that uses the decode_jpeg() is a float32 instead of a string, which seems odd to me as I have set the dtype of both the placeholder as well as the Input layer to tf.string.
I have searched all over stackoverflow for this but can't find a solution for this error. It appears this question also has not been able to find a solution for this specific issue.
EDIT 1: corrected typo and added full error message
The full error message is show below:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
~/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py in _apply_op_helper(self, op_type_name, name, **keywords)
509 as_ref=input_arg.is_ref,
--> 510 preferred_dtype=default_dtype)
511 except TypeError as err:
~/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/ops.py in internal_convert_to_tensor(value, dtype, name, as_ref, preferred_dtype, ctx)
1103 if ret is None:
-> 1104 ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
1105
~/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/ops.py in _TensorTensorConversionFunction(t, dtype, name, as_ref)
946 "Tensor conversion requested dtype %s for Tensor with dtype %s: %r" %
--> 947 (dtype.name, t.dtype.name, str(t)))
948 return t
ValueError: Tensor conversion requested dtype string for Tensor with dtype float32: 'Tensor("lambda_28/Placeholder:0", shape=(?, 1), dtype=float32)'
During handling of the above exception, another exception occurred:
TypeError Traceback (most recent call last)
<ipython-input-47-5793b0703860> in <module>
1 image = tf.placeholder(shape=[], dtype=tf.string)
2 input_tensor = Input(shape = (1,), tensor = image, dtype=tf.string)
----> 3 x = Lambda(lambda image: tf.image.decode_jpeg(image))(input_tensor)
4 output_tensor = model(x)
5
~/anaconda3/envs/tensorflow/lib/python3.6/site-packages/keras/engine/base_layer.py in __call__(self, inputs, **kwargs)
472 if all([s is not None
473 for s in to_list(input_shape)]):
--> 474 output_shape = self.compute_output_shape(input_shape)
475 else:
476 if isinstance(input_shape, list):
~/anaconda3/envs/tensorflow/lib/python3.6/site-packages/keras/layers/core.py in compute_output_shape(self, input_shape)
650 else:
651 x = K.placeholder(shape=input_shape)
--> 652 x = self.call(x)
653 if isinstance(x, list):
654 return [K.int_shape(x_elem) for x_elem in x]
~/anaconda3/envs/tensorflow/lib/python3.6/site-packages/keras/layers/core.py in call(self, inputs, mask)
685 if has_arg(self.function, 'mask'):
686 arguments['mask'] = mask
--> 687 return self.function(inputs, **arguments)
688
689 def compute_mask(self, inputs, mask=None):
<ipython-input-47-5793b0703860> in <lambda>(image)
1 image = tf.placeholder(shape=[], dtype=tf.string)
2 input_tensor = Input(shape = (1,), tensor = image, dtype=tf.string)
----> 3 x = Lambda(lambda image: tf.image.decode_jpeg(image))(input_tensor)
4 output_tensor = model(x)
5
~/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/ops/gen_image_ops.py in decode_jpeg(contents, channels, ratio, fancy_upscaling, try_recover_truncated, acceptable_fraction, dct_method, name)
946 try_recover_truncated=try_recover_truncated,
947 acceptable_fraction=acceptable_fraction, dct_method=dct_method,
--> 948 name=name)
949 _result = _op.outputs[:]
950 _inputs_flat = _op.inputs
~/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py in _apply_op_helper(self, op_type_name, name, **keywords)
531 if input_arg.type != types_pb2.DT_INVALID:
532 raise TypeError("%s expected type of %s." %
--> 533 (prefix, dtypes.as_dtype(input_arg.type).name))
534 else:
535 # Update the maps with the default, if needed.
TypeError: Input 'contents' of 'DecodeJpeg' Op has type float32 that does not match expected type of string.
def acc(output, label):
correct_preds = output.argmax(axis=1) == label.astype('float32')
return correct_preds.mean().asscalar()
for epoch in range(10):
train_loss, train_acc, valid_acc = 0., 0., 0.
tic = time()
for data, label in train_data:
data = data.copyto(mx.cpu(0))
label = label.copyto(mx.cpu(0))
with autograd.record():
output = net(data)
loss = softmax_cross_entropy(output, label)
loss.backward()
trainer.step(batch_size)
train_loss += loss.mean().asscalar()
train_acc += acc(output, label)
When running this part I get the error and my dataset is in pascol voc format
ValueError
Traceback (most recent call last)
<ipython-input-7-9926ba7deb21> in <module>()
12 label = label.copyto(mx.cpu(0))
13 with autograd.record():
---> 14 output = net(data)
15 loss = softmax_cross_entropy(output, label)
16
/home/manasi/.local/lib/python2.7/site-packages/mxnet/gluon/block.pyc in __call__(self, *args)
539 hook(self, args)
540
--> 541 out = self.forward(*args)
542
543 for hook in self._forward_hooks.values():
/home/manasi/.local/lib/python2.7/site-packages/mxnet/gluon/nn/basic_layers.pyc in forward(self, x)
51 def forward(self, x):
52 for block in self._children.values():
---> 53 x = block(x)
54 return x
55
/home/manasi/.local/lib/python2.7/site-packages/mxnet/gluon/block.pyc in __call__(self, *args)
539 hook(self, args)
540
--> 541 out = self.forward(*args)
542
543 for hook in self._forward_hooks.values():
/home/manasi/.local/lib/python2.7/site-packages/mxnet/gluon/block.pyc in forward(self, x, *args)
911 params = {i: j.data(ctx) for i, j in self._reg_params.items()}
912 except DeferredInitializationError:
--> 913 self._deferred_infer_shape(x, *args)
914 for _, i in self.params.items():
915 i._finish_deferred_init()
/home/manasi/.local/lib/python2.7/site-packages/mxnet/gluon/block.pyc in _deferred_infer_shape(self, *args)
792 error_msg = "Deferred initialization failed
because shape"\
793 " cannot be inferred. {}".format(e)
--> 794 raise ValueError(error_msg)
795
796 def _call_cached_op(self, *args):
ValueError: Deferred initialization failed because shape cannot be inferred. Error in operator conv2_fwd: [10:56:15] src/operator/nn/convolution.cc:196: Check failed: dilated_ksize_x <= AddPad(dshape[3], param_.pad[1]) (5 vs. 3) kernel size exceed input
kernel size exceed input error is usually seen when your input image is too small for the network. You either need to resize your input image, or change the network architecture to remove layers that reduce the spatial dimensions of the feature maps (e.g. pooling layers, or convolution with stride).