Getting error when training the CNN model

Question

I am getting errors when training my CNN model which is for checking what a person is telling in sign language. I am working with keras, tensorflow. This is my code:

import tensorflow as tf  ;importing libraries
from tensorflow.keras import datasets,layers,models
import numpy as np
import matplotlib.pyplot as plt
from tensorflow.keras.preprocessing.image import ImageDataGenerator
; Data preprocessing
train_datagen = ImageDataGenerator(rescale = 1./255,
                                  shear_range = 0.2,
                                  zoom_range = 0.2,
                                  horizontal_flip = True)
training_set = train_datagen.flow_from_directory('split__data/Train',
                                                target_size = (64, 64),
                                                batch_size = 32,
                                                class_mode = 'categorical')
test_datagen = ImageDataGenerator(rescale = 1./255)
test_set = test_datagen.flow_from_directory('split__data/Test',
                                           target_size = (64, 64),
                                           batch_size = 32,
                                           class_mode = 'categorical')

; Building the model
cnn = tf.keras.models.Sequential()
cnn.add(tf.keras.layers.Conv2D(filters = 16,kernel_size = 3,activation = 'relu',input_shape = [64,64,3]))
cnn.add(tf.keras.layers.MaxPool2D(pool_size=2,strides=2))

cnn.add(tf.keras.layers.Conv2D(filters = 32,kernel_size = 3,activation = 'relu',input_shape = [64,64,3]))
cnn.add(tf.keras.layers.MaxPool2D(pool_size=2,strides=2))

cnn.add(tf.keras.layers.Conv2D(filters = 64,kernel_size = 3,activation = 'relu',input_shape = [64,64,3]))
cnn.add(tf.keras.layers.MaxPool2D(pool_size=2,strides=2))
cnn.add(tf.keras.layers.Flatten())
cnn.add(tf.keras.layers.Dense(units=500,activation='relu'))
cnn.add(tf.keras.layers.Dense(units=1,activation='softmax'))

; compiling and training
cnn.compile(optimizer = 'adam' , loss= 'categorical_crossentropy',metrics = ['accuracy'])
;the next line is giving me error
cnn.fit(x = training_set,validation_data = test_set,batch_size = 32,epochs = 10)

This is the error. I am not able to get from where these errors are being generated. I have tried changing batch size, image height and width but nothing happens. I am getting same error.

---------------------------------------------------------------------------
InvalidArgumentError                      Traceback (most recent call last)
<ipython-input-15-b67ba9813850> in <module>
----> 1 cnn.fit(x = training_set,validation_data = test_set,batch_size = 32,epochs = 10)

C:\ProgramData\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)
   1181                 _r=1):
   1182               callbacks.on_train_batch_begin(step)
-> 1183               tmp_logs = self.train_function(iterator)
   1184               if data_handler.should_sync:
   1185                 context.async_wait()

C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds)
    887 
    888       with OptionalXlaContext(self._jit_compile):
--> 889         result = self._call(*args, **kwds)
    890 
    891       new_tracing_count = self.experimental_get_tracing_count()

C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds)
    948         # Lifting succeeded, so variables are initialized and we can run the
    949         # stateless function.
--> 950         return self._stateless_fn(*args, **kwds)
    951     else:
    952       _, _, _, filtered_flat_args = \

C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\eager\function.py in __call__(self, *args, **kwargs)
   3021       (graph_function,
   3022        filtered_flat_args) = self._maybe_define_function(args, kwargs)
-> 3023     return graph_function._call_flat(
   3024         filtered_flat_args, captured_inputs=graph_function.captured_inputs)  # pylint: disable=protected-access
   3025 

C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\eager\function.py in _call_flat(self, args, captured_inputs, cancellation_manager)
   1958         and executing_eagerly):
   1959       # No tape is watching; skip to running the function.
-> 1960       return self._build_call_outputs(self._inference_function.call(
   1961           ctx, args, cancellation_manager=cancellation_manager))
   1962     forward_backward = self._select_forward_and_backward_functions(

C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\eager\function.py in call(self, ctx, args, cancellation_manager)
    589       with _InterpolateFunctionError(self):
    590         if cancellation_manager is None:
--> 591           outputs = execute.execute(
    592               str(self.signature.name),
    593               num_outputs=self._num_outputs,

C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\eager\execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
     57   try:
     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:

InvalidArgumentError:  In[0] mismatch In[1] shape: 35 vs. 1: [32,35] [500,1] 0 0
     [[node gradient_tape/sequential/dense_1/MatMul (defined at <ipython-input-15-b67ba9813850>:1) ]] [Op:__inference_train_function_847]

Function call stack:
train_function

can someone help?

How do you expect every single convolutional layer in the model to have input shape [64, 64,3]? — xdurch0
– xdurch0, Commented Nov 11, 2021 at 20:11

Gerry P · Accepted Answer · 2021-11-12 03:24:17Z

1

How many classes are in the dataset? You have the code

cnn.add(tf.keras.layers.Dense(units=1,activation='softmax'))

This would indicate you are doing binary classification which I expect is not what you want. Try this after your generator code

classes=list(training_set.class_indices.keys())
class_count=len (classes)  # this integer is the number of nodes you need in your models final layer

change the last layer in your model to

cnn.add(tf.keras.layers.Dense(units=class_count,activation='softmax'))

answered Nov 12, 2021 at 3:24

Gerry P

8,1923 gold badges17 silver badges23 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

Deepak Kumar Over a year ago

Thank you @Gerry P. Actually I am a beginner and I was trying to convert Binary model to categorical model by rearranging code. Can you tell me how to get a prediction for single image. Actually when I try to do it, it is giving correct output for only one character. Also if you could suggest a good resource for CNN model building, it would be great.

Gerry P Over a year ago

see my second answer

Gerry P · Accepted Answer · 2021-11-12 19:53:59Z

to predict a single image- first read in the image. If you trained your model on RGB images then

import matplotlib.pyplot as plt
import cv2
classes=list(train_gen.class_indices.keys())
img_path = r' full path to the image'
img=plt.imread(img_path)
img=cv2.resize(img, (64.64))
img=img/255
img=np.expand_dims(img, axis=0)
prediction=model.predict( img, verbose=1)
index=argmax(prediction)
predicted_class = classes(index)

I don't bother building my own CNN, instead I use transfer learning with the EfficientNetB3 model. Note EfficientNet expects pixels in the range 0 to 255 so do not scale the pixels. Code below works well for most applications

base_model=tf.keras.applications.EfficientNetB3(include_top=False, weights="imagenet",input_shape=img_shape, pooling='max') 
x=base_model.output
x=keras.layers.BatchNormalization(axis=-1, momentum=0.99, epsilon=0.001 )(x)
x = Dense(256, kernel_regularizer = regularizers.l2(l = 0.016),activity_regularizer=regularizers.l1(0.006),
                bias_regularizer=regularizers.l1(0.006) ,activation='relu')(x)
x=Dropout(rate=.45, seed=123)(x)        
output=Dense(class_count, activation='softmax')(x)
model=Model(inputs=base_model.input, outputs=output)
model.compile(Adamax(learning_rate=.001), loss='categorical_crossentropy', metrics=['accuracy'])

Collectives™ on Stack Overflow

Getting error when training the CNN model

2 Answers 2

2 Comments

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

2 Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Related