from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense
from keras.layers.recurrent import SimpleRNN
from sklearn.feature_extraction.text import HashingVectorizer
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.preprocessing import LabelEncoder
import numpy as np
text = open('eng.train').read().split()
words = []
tags_1 = []
tags_2 = []
for i in range(len(text)):
if i % 4 == 0:
words.append(text[i])
if i % 4 == 1:
tags_1.append(text[i])
if i % 4 == 3:
tags_2.append(text[i])
hashing_vectorizer = HashingVectorizer(decode_error = 'ignore', n_features = 2 **15)
X_v = hashing_vectorizer.fit_transform(words)
label_encoder = LabelEncoder()
y1 = label_encoder.fit_transform(tags_1)
y2 = label_encoder.fit_transform(tags_2)
y1 = np_utils.to_categorical(y1)
y2 = np_utils.to_categorical(y2)
import nltk
trigram_X = list(nltk.trigrams(X_v))
#trigram_X = list(trigram_X)
print(len(trigram_X))
X = numpy.array(trigram_X)
print(X.shape)
y = numpy.reshape(y1, (204567, 1, 46))
trigram_tags = list(nltk.trigrams(y))
#trigram_y = list(trigram_tags)
print (len(trigram_y))
target = numpy.array(trigram_y)
y = numpy.reshape(target, (204565, 3, 46))
X = numpy.reshape(X, (204565, 3, 1))
X_final = numpy.dstack((X, y))
print(X_final.shape)
X_input = X_final[: -1, :, :]
print(X_input.shape)
y_final = label_encoder.fit_transform(tags_1)
y_target = np_utils.to_categorical(y_final[3:])
print(y_target.shape)
from keras.layers import Dense
from keras.models import Sequential
from keras.layers.recurrent import SimpleRNN
Feature hashig is used here. Now the problem requires to give the generated hashed vector with a corresponding one hot encoded vector as the input. But the keras program is throwing the following error:
model = Sequential()
model.add(SimpleRNN(100,input_shape = (X_input.shape[1], X_input.shape[2])))
model.add(Dense(y_target.shape[1], activation = 'softmax'))
model.compile(loss = 'categorical_crossentropy', optimizer = 'adam', metrics = ['accuracy'])
model.fit(X_input, y_target, epochs = 20, batch_size = 200)
ValueError: setting an array element with a sequence.
Please explain the reason for the error and a possible solution
edit 1
I have attached the full error stack as below
ValueError Traceback (most recent call last)
<ipython-input-3-4d9a4c1d9885> in <module>()
62 model.add(Dense(y_target.shape[1], activation = 'softmax'))
63 model.compile(loss = 'categorical_crossentropy', optimizer = 'adam', metrics = ['accuracy'])
---> 64 model.fit(X_input, y_target, epochs = 20, batch_size = 200)
65
/home/aditya/anaconda3/lib/python3.6/site-packages/keras/models.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, **kwargs)
843 class_weight=class_weight,
844 sample_weight=sample_weight,
--> 845 initial_epoch=initial_epoch)
846
847 def evaluate(self, x, y, batch_size=32, verbose=1,
/home/aditya/anaconda3/lib/python3.6/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, **kwargs)
1483 val_f=val_f, val_ins=val_ins, shuffle=shuffle,
1484 callback_metrics=callback_metrics,
-> 1485 initial_epoch=initial_epoch)
1486
1487 def evaluate(self, x, y, batch_size=32, verbose=1, sample_weight=None):
/home/aditya/anaconda3/lib/python3.6/site-packages/keras/engine/training.py in _fit_loop(self, f, ins, out_labels, batch_size, epochs, verbose, callbacks, val_f, val_ins, shuffle, callback_metrics, initial_epoch)
1138 batch_logs['size'] = len(batch_ids)
1139 callbacks.on_batch_begin(batch_index, batch_logs)
-> 1140 outs = f(ins_batch)
1141 if not isinstance(outs, list):
1142 outs = [outs]
/home/aditya/anaconda3/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py in __call__(self, inputs)
2071 session = get_session()
2072 updated = session.run(self.outputs + [self.updates_op],
-> 2073 feed_dict=feed_dict)
2074 return updated[:len(self.outputs)]
2075
/home/aditya/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata)
787 try:
788 result = self._run(None, fetches, feed_dict, options_ptr,
--> 789 run_metadata_ptr)
790 if run_metadata:
791 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
/home/aditya/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
966 feed_handles[subfeed_name] = subfeed_val
967 else:
--> 968 np_val = np.asarray(subfeed_val, dtype=subfeed_dtype)
969
970 if (not is_tensor_handle_feed and
/home/aditya/anaconda3/lib/python3.6/site-packages/numpy/core/numeric.py in asarray(a, dtype, order)
529
530 """
--> 531 return array(a, dtype, copy=False, order=order)
532
533
ValueError: setting an array element with a sequence
Related
I am trying to build a simple Model using the IAM Handwritten dataset from Kaggle and some sample code from a textbook I'm using, but I keep getting an error when I try to fit the model.
The error says ValueError: Layer sequential_2 expects 1 inputs, but it received 2 input tensors. Inputs received: [<tf.Tensor 'IteratorGetNext:0' shape=(None, None, None, None) dtype=float32>, <tf.Tensor 'IteratorGetNext:1' shape=(None, None) dtype=float32>]
full source code :
from __future__ import division
import numpy as np
import os
import glob
import tensorflow as tf
from random import *
from PIL import Image
from keras.utils import to_categorical
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
import pandas as pd
import matplotlib.image as mpimg
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten, Lambda, ELU, Activation, BatchNormalization
from keras.layers.convolutional import Convolution2D, Cropping2D, ZeroPadding2D, MaxPooling2D
from keras.preprocessing.image import ImageDataGenerator
from keras.optimizers import SGD, Adam, RMSprop
d = {}
from subprocess import check_output
with open('./forms_for_parsing.txt') as f:
for line in f:
key = line.split(' ')[0]
writer = line.split(' ')[1]
d[key] = writer
print(len(d.keys()))
tmp = []
target_list = []
path_to_files = os.path.join('./input/data_subset/data_subset', '*')
for filename in sorted(glob.glob(path_to_files)):
# print(filename)
tmp.append(filename)
image_name = filename.split('/')[-1]
file, ext = os.path.splitext(image_name)
parts = file.split('-')
p = parts[0].split('\\')
form = p[1] + '-' + parts[1]
for key in d:
if key == form:
target_list.append(str(d[form]))
# print(d)
# print(parts[0])
# p = parts[0].split('\\')
# print(p[1])
# print(form)
img_files = np.asarray(tmp)
img_targets = np.asarray(target_list)
print(img_files.shape)
print(img_targets.shape)
for filename in img_files[:20]:
img=mpimg.imread(filename)
plt.figure(figsize=(10,10))
plt.imshow(img, cmap ='gray')
encoder = LabelEncoder()
encoder.fit(img_targets)
encoded_Y = encoder.transform(img_targets)
print(img_files[:5], img_targets[:5], encoded_Y[:5])
train_files, rem_files, train_targets, rem_targets = train_test_split(
img_files, encoded_Y, train_size=0.66, random_state=52, shuffle= True)
validation_files, test_files, validation_targets, test_targets = train_test_split(
rem_files, rem_targets, train_size=0.5, random_state=22, shuffle=True)
print(train_files.shape, validation_files.shape, test_files.shape)
print(train_targets.shape, validation_targets.shape, test_targets.shape)
batch_size = 16 # 8
num_classes = 50
# Start with train generator shared in the class and add image augmentations
def generate_data(samples, target_files, batch_size=batch_size, factor = 0.1 ):
num_samples = len(samples)
from sklearn.utils import shuffle
while 1: # Loop forever so the generator never terminates
for offset in range(0, num_samples, batch_size):
batch_samples = samples[offset:offset+batch_size]
batch_targets = target_files[offset:offset+batch_size]
images = []
targets = []
for i in range(len(batch_samples)):
batch_sample = batch_samples[i]
batch_target = batch_targets[i]
im = Image.open(batch_sample)
cur_width = im.size[0]
cur_height = im.size[1]
# print(cur_width, cur_height)
height_fac = 113 / cur_height
new_width = int(cur_width * height_fac)
size = new_width, 113
imresize = im.resize((size), Image.ANTIALIAS) # Resize so height = 113 while keeping aspect ratio
now_width = imresize.size[0]
now_height = imresize.size[1]
# Generate crops of size 113x113 from this resized image and keep random 10% of crops
avail_x_points = list(range(0, now_width - 113 ))# total x start points are from 0 to width -113
# Pick random x%
pick_num = int(len(avail_x_points)*factor)
# Now pick
random_startx = sample(avail_x_points, pick_num)
for start in random_startx:
imcrop = imresize.crop((start, 0, start+113, 113))
images.append(np.asarray(imcrop))
targets.append(batch_target)
# trim image to only see section with road
X_train = np.array(images)
y_train = np.array(targets)
#reshape X_train for feeding in later
X_train = X_train.reshape(X_train.shape[0], 113, 113, 1)
#convert to float and normalize
X_train = X_train.astype('float32')
X_train /= 255
#One hot encode y
y_train = to_categorical(y_train, num_classes)
yield shuffle(X_train, y_train)
train_generator = generate_data(train_files, train_targets, batch_size=batch_size, factor = 0.3)
validation_generator = generate_data(validation_files, validation_targets, batch_size=batch_size, factor = 0.3)
test_generator = generate_data(test_files, test_targets, batch_size=batch_size, factor = 0.1)
def resize_image(image):
return tf.image.resize(image,[56,56])
# Function to resize image to 64x64
row, col, ch = 113, 113, 1
model = Sequential()
model.add(ZeroPadding2D((1, 1), input_shape=(row, col, ch)))
# Resise data within the neural network
model.add(Lambda(resize_image)) #resize images to allow for easy computation
# CNN model - Building the model suggested in paper
model.add(Convolution2D(filters= 32, kernel_size =(5,5), strides= (2,2), padding='same', name='conv1')) #96
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2,2),strides=(2,2), name='pool1'))
model.add(Convolution2D(filters= 64, kernel_size =(3,3), strides= (1,1), padding='same', name='conv2')) #256
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2,2),strides=(2,2), name='pool2'))
model.add(Convolution2D(filters= 128, kernel_size =(3,3), strides= (1,1), padding='same', name='conv3')) #256
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2,2),strides=(2,2), name='pool3'))
model.add(Flatten())
model.add(Dropout(0.5))
model.add(Dense(512, name='dense1')) #1024
# model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(256, name='dense2')) #1024
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes,name='output'))
model.add(Activation('softmax')) #softmax since output is within 50 classes
model.compile(loss='categorical_crossentropy', optimizer=Adam(), metrics=['accuracy'])
model.summary()
nb_epoch = 8
samples_per_epoch = 3268
nb_val_samples = 842
# #save every model using Keras checkpoint
from keras.callbacks import ModelCheckpoint
#filepath="check-{epoch:02d}-{val_loss:.4f}.hdf5"
filepath="low_loss.hdf5"
checkpoint = ModelCheckpoint(filepath= filepath, verbose=1, save_best_only=False)
callbacks_list = [checkpoint]
# #Model fit generator
history_object = model.fit_generator(train_generator, steps_per_epoch = (samples_per_epoch/batch_size),
validation_data=validation_generator,
validation_steps=nb_val_samples, epochs=nb_epoch, verbose=1, callbacks=callbacks_list)
and this is error i got :
ValueError Traceback (most recent call last)
<ipython-input-79-99c01bc062d8> in <module>
12
13 # #Model fit generator
---> 14 history_object = model.fit_generator(train_generator, steps_per_epoch = (samples_per_epoch/batch_size),
15 validation_data=validation_generator,
16 validation_steps=nb_val_samples, epochs=nb_epoch, verbose=1, callbacks=callbacks_list)
~\anaconda3\lib\site-packages\tensorflow\python\util\deprecation.py in new_func(*args, **kwargs)
322 'in a future version' if date is None else ('after %s' % date),
323 instructions)
--> 324 return func(*args, **kwargs)
325 return tf_decorator.make_decorator(
326 func, new_func, 'deprecated',
~\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
1813 """
1814 _keras_api_gauge.get_cell('fit_generator').set(True)
-> 1815 return self.fit(
1816 generator,
1817 steps_per_epoch=steps_per_epoch,
~\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py in _method_wrapper(self, *args, **kwargs)
106 def _method_wrapper(self, *args, **kwargs):
107 if not self._in_multi_worker_mode(): # pylint: disable=protected-access
--> 108 return method(self, *args, **kwargs)
109
110 # Running inside `run_distribute_coordinator` already.
~\anaconda3\lib\site-packages\tensorflow\python\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)
1096 batch_size=batch_size):
1097 callbacks.on_train_batch_begin(step)
-> 1098 tmp_logs = train_function(iterator)
1099 if data_handler.should_sync:
1100 context.async_wait()
~\anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds)
778 else:
779 compiler = "nonXla"
--> 780 result = self._call(*args, **kwds)
781
782 new_tracing_count = self._get_tracing_count()
~\anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds)
812 # In this case we have not created variables on the first call. So we can
813 # run the first trace but we should fail if variables are created.
--> 814 results = self._stateful_fn(*args, **kwds)
815 if self._created_variables:
816 raise ValueError("Creating variables on a non-first call to a function"
~\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in __call__(self, *args, **kwargs)
2826 """Calls a graph function specialized to the inputs."""
2827 with self._lock:
-> 2828 graph_function, args, kwargs = self._maybe_define_function(args, kwargs)
2829 return graph_function._filtered_call(args, kwargs) # pylint: disable=protected-access
2830
~\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in _maybe_define_function(self, args, kwargs)
3208 and self.input_signature is None
3209 and call_context_key in self._function_cache.missed):
-> 3210 return self._define_function_with_shape_relaxation(args, kwargs)
3211
3212 self._function_cache.missed.add(call_context_key)
~\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in _define_function_with_shape_relaxation(self, args, kwargs)
3139 expand_composites=True)
3140
-> 3141 graph_function = self._create_graph_function(
3142 args, kwargs, override_flat_arg_shapes=relaxed_arg_shapes)
3143 self._function_cache.arg_relaxed[rank_only_cache_key] = graph_function
~\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
3063 arg_names = base_arg_names + missing_arg_names
3064 graph_function = ConcreteFunction(
-> 3065 func_graph_module.func_graph_from_py_func(
3066 self._name,
3067 self._python_function,
~\anaconda3\lib\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)
984 _, original_func = tf_decorator.unwrap(python_func)
985
--> 986 func_outputs = python_func(*func_args, **func_kwargs)
987
988 # invariant: `func_outputs` contains only Tensors, CompositeTensors,
~\anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in wrapped_fn(*args, **kwds)
598 # __wrapped__ allows AutoGraph to swap in a converted function. We give
599 # the function a weak reference to itself to avoid a reference cycle.
--> 600 return weak_wrapped_fn().__wrapped__(*args, **kwds)
601 weak_wrapped_fn = weakref.ref(wrapped_fn)
602
~\anaconda3\lib\site-packages\tensorflow\python\framework\func_graph.py in wrapper(*args, **kwargs)
971 except Exception as e: # pylint:disable=broad-except
972 if hasattr(e, "ag_error_metadata"):
--> 973 raise e.ag_error_metadata.to_exception(e)
974 else:
975 raise
ValueError: in user code:
C:\Users\subha\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:806 train_function *
return step_function(self, iterator)
C:\Users\subha\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:796 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
C:\Users\subha\anaconda3\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1211 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
C:\Users\subha\anaconda3\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2585 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
C:\Users\subha\anaconda3\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2945 _call_for_each_replica
return fn(*args, **kwargs)
C:\Users\subha\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:789 run_step **
outputs = model.train_step(data)
C:\Users\subha\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:747 train_step
y_pred = self(x, training=True)
C:\Users\subha\anaconda3\lib\site-packages\tensorflow\python\keras\engine\base_layer.py:975 __call__
input_spec.assert_input_compatibility(self.input_spec, inputs,
C:\Users\subha\anaconda3\lib\site-packages\tensorflow\python\keras\engine\input_spec.py:155 assert_input_compatibility
raise ValueError('Layer ' + layer_name + ' expects ' +
ValueError: Layer sequential_2 expects 1 inputs, but it received 2 input tensors. Inputs received: [<tf.Tensor 'IteratorGetNext:0' shape=(None, None, None, None) dtype=float32>, <tf.Tensor 'IteratorGetNext:1' shape=(None, None) dtype=float32>]
i couldn't understand the error message so kindly somebody help me out!
thank u
I am trying to do semantic segmentation using Unet from segmentation model for multi channel (>3) image.
The code works if the batch_size =1. But if I change the batch_size to other values (e.g. 2) then error occurs (InvalidArgumentError: Incompatible shapes):
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
<ipython-input-19-15dc3666afa8> in <module>
22 validation_steps = 1,
23 callbacks=build_callbacks(),
---> 24 verbose = 1)
25
~/.virtualenvs/sm/lib/python3.6/site-packages/keras/legacy/interfaces.py in wrapper(*args, **kwargs)
89 warnings.warn('Update your `' + object_name +
90 '` call to the Keras 2 API: ' + signature, stacklevel=2)
---> 91 return func(*args, **kwargs)
92 wrapper._original_function = func
93 return wrapper
~/.virtualenvs/sm/lib/python3.6/site-packages/keras/engine/training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
1424 use_multiprocessing=use_multiprocessing,
1425 shuffle=shuffle,
-> 1426 initial_epoch=initial_epoch)
1427
1428 #interfaces.legacy_generator_methods_support
~/.virtualenvs/sm/lib/python3.6/site-packages/keras/engine/training_generator.py in fit_generator(model, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
189 outs = model.train_on_batch(x, y,
190 sample_weight=sample_weight,
--> 191 class_weight=class_weight)
192
193 if not isinstance(outs, list):
~/.virtualenvs/sm/lib/python3.6/site-packages/keras/engine/training.py in train_on_batch(self, x, y, sample_weight, class_weight)
1218 ins = x + y + sample_weights
1219 self._make_train_function()
-> 1220 outputs = self.train_function(ins)
1221 if len(outputs) == 1:
1222 return outputs[0]
~/.virtualenvs/sm/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py in __call__(self, inputs)
2659 return self._legacy_call(inputs)
2660
-> 2661 return self._call(inputs)
2662 else:
2663 if py_any(is_tensor(x) for x in inputs):
~/.virtualenvs/sm/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py in _call(self, inputs)
2629 symbol_vals,
2630 session)
-> 2631 fetched = self._callable_fn(*array_vals)
2632 return fetched[:len(self.outputs)]
2633
~/.virtualenvs/sm/lib/python3.6/site-packages/tensorflow_core/python/client/session.py in __call__(self, *args, **kwargs)
1470 ret = tf_session.TF_SessionRunCallable(self._session._session,
1471 self._handle, args,
-> 1472 run_metadata_ptr)
1473 if run_metadata:
1474 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
InvalidArgumentError: Incompatible shapes: [2,256,256,1] vs. [2,256,256]
[[{{node loss_1/model_4_loss/mul}}]]
I tried to play around by following different posts in the forum but could not solve it. Here, is a portion of code which runs for batch_size=1.
batch_size = 1 # CHANGING ‘batch_size ‘ value other than 1 gives error
train_image_files = glob(patch_img + "/**/*.tif")
# simple_image_generator() is used to work with multi channel (>3) images (the function is
at the end)
train_image_generator = simple_image_generator(train_image_files,
batch_size=batch_size,
rotation_range=45,
horizontal_flip=True,
vertical_flip=True)
train_mask_files = glob(patch_ann + "/**/*.tif")
train_mask_generator = simple_image_generator(train_mask_files,
batch_size=batch_size)
test_image_files = glob(test_img + "/**/*.tif")
test_image_generator = simple_image_generator(test_image_files,
batch_size=batch_size,
rotation_range=45,
horizontal_flip=True,
vertical_flip=True)
test_mask_files = glob(test_ann + "/**/*.tif")
test_mask_generator = simple_image_generator(test_mask_files,
batch_size=batch_size)
train_generator = (pair for pair in zip(train_image_generator, train_mask_generator))
test_generator = (pair for pair in zip(test_image_generator, test_mask_generator))
.
.
num_channels = 8 # no. of channel
base_model = sm.Unet(backbone_name='resnet34', encoder_weights='imagenet')
inp = Input(shape=( None, None, num_channels))
layer_1 = Conv2D( 3, (1, 1))(inp) # map N channels data to 3 channels
out = base_model(layer_1)
model = Model(inp, out, name=base_model.name)
model.summary()
model.compile(
optimizer = keras.optimizers.Adam(lr=learning_rate),
loss = sm.losses.bce_jaccard_loss,
metrics = ['accuracy',sm.metrics.iou_score]
)
model_history = model.fit_generator(train_generator,
epochs = 1,
steps_per_epoch = 1,
validation_data = test_generator,
validation_steps = 1,
callbacks = build_callbacks(),
verbose = 1)
Additional Information:
I am not using the default imageGenerator provided by keras. I am using ‘simple_image_generator’ (slightly modified)
def simple_image_generator(files, batch_size=32,
rotation_range=0, horizontal_flip=False,
vertical_flip=False):
while True:
# select batch_size number of samples without replacement
batch_files = sample(files, batch_size)
# array for images
batch_X = []
# loop over images of the current batch
for idx, input_path in enumerate(batch_files):
image = np.array(imread(input_path), dtype=float)
# process image
if horizontal_flip:
# randomly flip image up/down
if choice([True, False]):
image = np.flipud(image)
if vertical_flip:
# randomly flip image left/right
if choice([True, False]):
image = np.fliplr(image)
# rotate image by random angle between
# -rotation_range <= angle < rotation_range
if rotation_range is not 0:
angle = np.random.uniform(low=-abs(rotation_range),
high=abs(rotation_range))
image = rotate(image, angle, mode='reflect',
order=1, preserve_range=True)
# put all together
batch_X += [image]
# convert lists to np.array
X = np.array(batch_X)
yield(X)
This error was solved by redefining a new image generator instead of simple_image_generator(). The simple_image_generator() worked well with the shape of the images (8 Bands) but did not cope well with the shape of the mask (1 band ).
During the execution, image_generator had 4 dimensions with [2,256,256,1] ( i.e. batch_size, (image size), bands) BUT mask_generator had 3 dimensions only vs. [2,256,256] (i.e. batch_size,(image size))
So reshaping the mask of [2,256,256] to [2,256,256, 1] solved the issue.
Hello I got this error which I could not solve any thoughts. I am trying to build a model using my own dataset. So I choose transfer learning (VGG16) but it still isn't working. Thank you in advance.
Im using Python 3.8X
The latest version of Tensorflow 2.2X
Im trying to build a classifier that can dd
import tensorflow as tf
from tensorflow.keras.layers import Input, Lambda, Dense, Flatten
from tensorflow.keras.models import Model
from tensorflow.keras.applications.vgg16 import VGG16
from tensorflow.keras.applications.vgg16 import preprocess_input
from tensorflow.keras.preprocessing import image
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.models import Sequential
import numpy as np
from glob import glob
import matplotlib.pyplot as plt
IMAGE_SIZE = [224, 224]
train_path = 'dataset/Train'
val_path = 'dataset/validation'
vgg = VGG16(input_shape=IMAGE_SIZE + [3], weights='imagenet', include_top=False)
for layer in vgg.layers:
layer.trainable = False
folders = glob('datasets/Train/*')
x = Flatten()(vgg.output)
x = Dense(1000, activation='relu')(x)
prediction = Dense(len(folders), activation='softmax')(x)
# create a model object
model = Model(inputs=vgg.input, outputs=prediction)
model.summary()
model.compile(
loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy']
)
train_datagen = ImageDataGenerator(rescale = 1./255,
shear_range = 0.2,
zoom_range = 0.2,
horizontal_flip = True)
test_datagen = ImageDataGenerator(rescale = 1./255)
training_set = train_datagen.flow_from_directory('dataset/train',
target_size = (224, 224),
batch_size = 32,
class_mode = 'categorical')
test_set = test_datagen.flow_from_directory('dataset/validation',
target_size = (224, 224),
batch_size = 32,
class_mode = 'categorical')
r = model.fit(
training_set,
validation_data=test_set,
epochs=5,
steps_per_epoch=len(training_set),
validation_steps=len(test_set)
)
Below is the error
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
<ipython-input-46-a479a62b157d> in <module>
2 steps_per_epoch = 1,
3 epochs = 10,
----> 4 validation_data = test_set
5 )
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py in _method_wrapper(self, *args, **kwargs)
106 def _method_wrapper(self, *args, **kwargs):
107 if not self._in_multi_worker_mode(): # pylint: disable=protected-access
--> 108 return method(self, *args, **kwargs)
109
110 # Running inside `run_distribute_coordinator` already.
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/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)
1100 _r=1):
1101 callbacks.on_train_batch_begin(step)
-> 1102 tmp_logs = self.train_function(iterator)
1103 if data_handler.should_sync:
1104 context.async_wait()
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
794 else:
795 compiler = "nonXla"
--> 796 result = self._call(*args, **kwds)
797
798 new_tracing_count = self._get_tracing_count()
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
821 # In this case we have created variables on the first call, so we run the
822 # defunned version which is guaranteed to never create variables.
--> 823 return self._stateless_fn(*args, **kwds) # pylint: disable=not-callable
824 elif self._stateful_fn is not None:
825 # Release the lock early so that multiple threads can perform the call
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/eager/function.py in __call__(self, *args, **kwargs)
2920 with self._lock:
2921 graph_function, args, kwargs = self._maybe_define_function(args, kwargs)
-> 2922 return graph_function._filtered_call(args, kwargs) # pylint: disable=protected-access
2923
2924 #property
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/eager/function.py in _filtered_call(self, args, kwargs, cancellation_manager)
1856 resource_variable_ops.BaseResourceVariable))],
1857 captured_inputs=self.captured_inputs,
-> 1858 cancellation_manager=cancellation_manager)
1859
1860 def _call_flat(self, args, captured_inputs, cancellation_manager=None):
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/eager/function.py in _call_flat(self, args, captured_inputs, cancellation_manager)
1932 # No tape is watching; skip to running the function.
1933 return self._build_call_outputs(self._inference_function.call(
-> 1934 ctx, args, cancellation_manager=cancellation_manager))
1935 forward_backward = self._select_forward_and_backward_functions(
1936 args,
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/eager/function.py in call(self, ctx, args, cancellation_manager)
555 inputs=args,
556 attrs=attrs,
--> 557 ctx=ctx)
558 else:
559 outputs = execute.execute_with_cancellation(
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
58 ctx.ensure_initialized()
59 tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
---> 60 inputs, attrs, num_outputs)
61 except core._NotOkStatusException as e:
62 if name is not None:
InvalidArgumentError: Reduction axis -1 is empty in shape [32,0]
[[node ArgMax_1 (defined at <ipython-input-45-71c422cbdbf7>:4) ]] [Op:__inference_train_function_3410]
Function call stack:
train_function
[ ]:
I am trying to modify code provided to me to import a image file and build a training and test set using keras.
I am receiving the following error:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-154-b4983c6bd066> in <module>()
1 # Fit the model
----> 2 history = model.fit(X_train, y_train, batch_size = 256, epochs = 15, verbose=2, validation_data=(X_test,y_test))
~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\keras\engine\training.py in _method_wrapper(self, *args, **kwargs)
106 def _method_wrapper(self, *args, **kwargs):
107 if not self._in_multi_worker_mode(): # pylint: disable=protected-access
--> 108 return method(self, *args, **kwargs)
109
110 # Running inside `run_distribute_coordinator` already.
~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\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)
1096 batch_size=batch_size):
1097 callbacks.on_train_batch_begin(step)
-> 1098 tmp_logs = train_function(iterator)
1099 if data_handler.should_sync:
1100 context.async_wait()
~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds)
778 else:
779 compiler = "nonXla"
--> 780 result = self._call(*args, **kwds)
781
782 new_tracing_count = self._get_tracing_count()
~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds)
821 # This is the first call of __call__, so we have to initialize.
822 initializers = []
--> 823 self._initialize(args, kwds, add_initializers_to=initializers)
824 finally:
825 # At this point we know that the initialization is complete (or less
~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\eager\def_function.py in _initialize(self, args, kwds, add_initializers_to)
695 self._concrete_stateful_fn = (
696 self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access
--> 697 *args, **kwds))
698
699 def invalid_creator_scope(*unused_args, **unused_kwds):
~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\eager\function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
2853 args, kwargs = None, None
2854 with self._lock:
-> 2855 graph_function, _, _ = self._maybe_define_function(args, kwargs)
2856 return graph_function
2857
~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\eager\function.py in _maybe_define_function(self, args, kwargs)
3211
3212 self._function_cache.missed.add(call_context_key)
-> 3213 graph_function = self._create_graph_function(args, kwargs)
3214 self._function_cache.primary[cache_key] = graph_function
3215 return graph_function, args, kwargs
~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
3073 arg_names=arg_names,
3074 override_flat_arg_shapes=override_flat_arg_shapes,
-> 3075 capture_by_value=self._capture_by_value),
3076 self._function_attributes,
3077 function_spec=self.function_spec,
~\AppData\Roaming\Python\Python37\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)
984 _, original_func = tf_decorator.unwrap(python_func)
985
--> 986 func_outputs = python_func(*func_args, **func_kwargs)
987
988 # invariant: `func_outputs` contains only Tensors, CompositeTensors,
~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\eager\def_function.py in wrapped_fn(*args, **kwds)
598 # __wrapped__ allows AutoGraph to swap in a converted function. We give
599 # the function a weak reference to itself to avoid a reference cycle.
--> 600 return weak_wrapped_fn().__wrapped__(*args, **kwds)
601 weak_wrapped_fn = weakref.ref(wrapped_fn)
602
~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\framework\func_graph.py in wrapper(*args, **kwargs)
971 except Exception as e: # pylint:disable=broad-except
972 if hasattr(e, "ag_error_metadata"):
--> 973 raise e.ag_error_metadata.to_exception(e)
974 else:
975 raise
ValueError: in user code:
C:\Users\synar\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\keras\engine\training.py:806 train_function *
return step_function(self, iterator)
C:\Users\synar\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\keras\engine\training.py:796 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
C:\Users\synar\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\distribute\distribute_lib.py:1211 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
C:\Users\synar\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\distribute\distribute_lib.py:2585 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
C:\Users\synar\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\distribute\distribute_lib.py:2945 _call_for_each_replica
return fn(*args, **kwargs)
C:\Users\synar\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\keras\engine\training.py:789 run_step **
outputs = model.train_step(data)
C:\Users\synar\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\keras\engine\training.py:747 train_step
y_pred = self(x, training=True)
C:\Users\synar\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\keras\engine\base_layer.py:976 __call__
self.name)
C:\Users\synar\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\keras\engine\input_spec.py:216 assert_input_compatibility
' but received input with shape ' + str(shape))
ValueError: Input 0 of layer sequential_41 is incompatible with the layer: expected axis -1 of input shape to have value 784 but received input with shape [None, 1]
My code I have implemented so is:
%matplotlib inline
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn import preprocessing
from sklearn import model_selection
from scipy.io import loadmat
data = loadmat('notMNIST_small.mat')
X_temp = data['images']/255
#for i in range(X_temp.shape[2]):
X = np.empty(shape=[X_temp.shape[2]] + [784], dtype='float32')
for i in range(X_temp.shape[2]):
X[i,:] = X_temp[:,:,i].flatten()
y = pd.get_dummies(data['labels']).to_numpy()
print(X_temp.shape)
print(X.shape)
print(y.shape)
X[1,:]
X = np.array(data['labels']).reshape(-1, 1)
y = np.array(data['labels'])
X_train, X_test, y_train, y_test =train_test_split(
X, y, test_size=0.2, random_state=9)
stdscaler = preprocessing.StandardScaler().fit(X_train)
X_train_scaled = stdscaler.transform(X_train)
X_test_scaled = stdscaler.transform(X_test)
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.regularizers import l2, l1
from tensorflow.keras.optimizers import SGD
# Stochastic Logistic Regression
model = Sequential()
# Model
model.add(Dense(units=10, input_shape = [784,], activation = 'relu', kernel_regularizer=l2(0)))
model.add(Dense(units = 40, activation = 'relu'))
model.add(Dense(units = 10, activation = 'sigmoid'))
# Compile model
sgd = SGD(lr=0.1)
model.compile(loss='categorical_crossentropy', optimizer=sgd)
I get the error when implementing the following cell:
# Fit the model
history = model.fit(X_train, y_train, batch_size = 256, epochs = 15, verbose=2, validation_data=(X_test,y_test))
Any help in resolving this would be great I am new to machine learning so excuse my ignorance.
Add extra dimension to your X_train as
x_train = x_train.reshape(-1, 28*28)
model = Sequential()
# Model
model.add(Dense(units=10, input_dim = 784, activation = 'relu', kernel_regularizer=l2(0)))
model.add(Dense(units = 40, activation = 'relu'))
model.add(Dense(units = 10, activation = 'sigmoid'))
# Compile model
sgd = SGD(lr=0.1)
model.compile(loss='categorical_crossentropy', optimizer=sgd)
Intro and setup
So I have been for some time now trying to make a simple Convolution Neural Network. I followed a simple tutorial, which can be found Here's a link!
It is a simple cat vs dog test (2 categories)
I have set my jupyter/tensorflow/keras up in
C:\Users\labadmin
What i have understood is that i just have to put the path from labadmin in order to implement my data for testing and training.
Since i am not sure what is causing the error i have pasted the whole code and error, i think it is about the system not getting the data.
The folder with the Data set-up as following:
labadmin has a folder called data withing that there are two folders
training
test
Both cat images and dog images are shuffled in both folders. There are 10000+ pictures in each folder, so there should be enough,
This is my code:
from keras.models import Sequential
from keras.layers import Convolution2D
from keras.layers import MaxPooling2D
from keras.layers import Flatten
from keras.layers import Dense
classifier = Sequential()
classifier.add(Convolution2D(32, 3, 3, input_shape = (64, 64, 3), activation = 'relu'))
classifier.add(MaxPooling2D(pool_size = (2,2)))
classifier.add(Flatten())
classifier.add(Dense(output_dim = 128, activation = 'relu'))
classifier.add(Dense(output_dim = 1, activation = 'sigmoid'))
classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics=['accuracy'])
import pandas as pd
from keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(
rescale=1./255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
test_datagen = ImageDataGenerator(rescale=1./255)
training_set = train_datagen.flow_from_directory(
'data\\training',
target_size=(64, 64),
batch_size=32,
class_mode='categorical',
shuffle=False)
test_set = test_datagen.flow_from_directory(
'data\\test',
target_size=(64, 64),
batch_size=32,
class_mode='categorical',
shuffle=False)
from IPython.display import display
from PIL import Image
classifier.fit_generator(
training_set,
steps_per_epoch=8000,
epochs=10,
validation_data = test_set,
validation_steps = 800)
import numpy as np
from keras_preprocessing import image
test_image = image.load_img('data\\random.jpg', target_size=(64, 64))
test_image = image.img_to_array(test_image)
test_image = np.expand_dims(test_image, axis = 0)
result = classifier.predict(test_image)
training_set.class_indices
if result[0][0]>= 0.5:
prediction = 'dog'
else:
prediction = 'cat'
print(prediction)
I get the following error:
C:\Users\labadmin\Miniconda3\envs\tensorflow\lib\site-packages\ipykernel_launcher.py:26: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(32, (3, 3), input_shape=(64, 64, 3..., activation="relu")`
C:\Users\labadmin\Miniconda3\envs\tensorflow\lib\site-packages\ipykernel_launcher.py:35: UserWarning: Update your `Dense` call to the Keras 2 API: `Dense(activation="relu", units=128)`
C:\Users\labadmin\Miniconda3\envs\tensorflow\lib\site-packages\ipykernel_launcher.py:36: UserWarning: Update your `Dense` call to the Keras 2 API: `Dense(activation="sigmoid", units=1)`
Found 0 images belonging to 0 classes.
Found 0 images belonging to 0 classes.
Epoch 1/10
---------------------------------------------------------------------------
ZeroDivisionError Traceback (most recent call last)
<ipython-input-5-393aaba195e9> in <module>
82 epochs=10,
83 validation_data = test_set,
---> 84 validation_steps = 800)
85
86 # Our image we now send through to test
~\Miniconda3\envs\tensorflow\lib\site-packages\keras\legacy\interfaces.py in wrapper(*args, **kwargs)
89 warnings.warn('Update your `' + object_name + '` call to the ' +
90 'Keras 2 API: ' + signature, stacklevel=2)
---> 91 return func(*args, **kwargs)
92 wrapper._original_function = func
93 return wrapper
~\Miniconda3\envs\tensorflow\lib\site-packages\keras\engine\training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
1416 use_multiprocessing=use_multiprocessing,
1417 shuffle=shuffle,
-> 1418 initial_epoch=initial_epoch)
1419
1420 #interfaces.legacy_generator_methods_support
~\Miniconda3\envs\tensorflow\lib\site-packages\keras\engine\training_generator.py in fit_generator(model, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
179 batch_index = 0
180 while steps_done < steps_per_epoch:
--> 181 generator_output = next(output_generator)
182
183 if not hasattr(generator_output, '__len__'):
~\Miniconda3\envs\tensorflow\lib\site-packages\keras\utils\data_utils.py in get(self)
707 "`use_multiprocessing=False, workers > 1`."
708 "For more information see issue #1638.")
--> 709 six.reraise(*sys.exc_info())
~\Miniconda3\envs\tensorflow\lib\site-packages\six.py in reraise(tp, value, tb)
691 if value.__traceback__ is not tb:
692 raise value.with_traceback(tb)
--> 693 raise value
694 finally:
695 value = None
~\Miniconda3\envs\tensorflow\lib\site-packages\keras\utils\data_utils.py in get(self)
683 try:
684 while self.is_running():
--> 685 inputs = self.queue.get(block=True).get()
686 self.queue.task_done()
687 if inputs is not None:
~\Miniconda3\envs\tensorflow\lib\multiprocessing\pool.py in get(self, timeout)
642 return self._value
643 else:
--> 644 raise self._value
645
646 def _set(self, i, obj):
~\Miniconda3\envs\tensorflow\lib\multiprocessing\pool.py in worker(inqueue, outqueue, initializer, initargs, maxtasks, wrap_exception)
117 job, i, func, args, kwds = task
118 try:
--> 119 result = (True, func(*args, **kwds))
120 except Exception as e:
121 if wrap_exception and func is not _helper_reraises_exception:
~\Miniconda3\envs\tensorflow\lib\site-packages\keras\utils\data_utils.py in next_sample(uid)
624 The next value of generator `uid`.
625 """
--> 626 return six.next(_SHARED_SEQUENCES[uid])
627
628
~\Miniconda3\envs\tensorflow\lib\site-packages\keras_preprocessing\image\iterator.py in __next__(self, *args, **kwargs)
98
99 def __next__(self, *args, **kwargs):
--> 100 return self.next(*args, **kwargs)
101
102 def next(self):
~\Miniconda3\envs\tensorflow\lib\site-packages\keras_preprocessing\image\iterator.py in next(self)
107 """
108 with self.lock:
--> 109 index_array = next(self.index_generator)
110 # The transformation of images is not under thread lock
111 # so it can be done in parallel
~\Miniconda3\envs\tensorflow\lib\site-packages\keras_preprocessing\image\iterator.py in _flow_index(self)
83 self._set_index_array()
84
---> 85 current_index = (self.batch_index * self.batch_size) % self.n
86 if self.n > current_index + self.batch_size:
87 self.batch_index += 1
ZeroDivisionError: integer division or modulo by zero
Thank you for your time.
Did you populate your data\\training and data\\test directories? From the output:
Found 0 images belonging to 0 classes.
Found 0 images belonging to 0 classes.
Epoch 1/10
it appears that your data augmentation generator did not find any images and the resulting dataset is empty; consequently, when Keras tries to run the fit_generator, you get the division by 0 error as it tries to iterate through your null image set.