Using Keras Without GPU

Question

I want to train a Neural Network using Keras but when I want to build the model I get the following error

2022-03-14 09:38:10.526372: E tensorflow/stream_executor/cuda/cuda_driver.cc:271] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected
2022-03-14 09:38:10.526465: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (HSKP02): /proc/driver/nvidia/version does not exist
2022-03-14 09:38:10.527391: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.

I tried to solve this error by writing

import os
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ['CUDA_VISIBLE_DEVICES'] = "-1" 

before importing Keras but I still get this error. After this error my code fits the data with the validation set with model.fit() but I get another error

Traceback (most recent call last):
  File "shallownet_ex.py", line 44, in <module>
    H = model.fit(trainX, trainY, validation_data=(testX, testY), batch_size=32, epochs=100, verbose=1)
  File ".../venv/lib/python3.8/site-packages/keras/utils/traceback_utils.py", line 67, in error_handler
    raise e.with_traceback(filtered_tb) from None
  File ".../venv/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py", line 1147, in autograph_handler
    raise e.ag_error_metadata.to_exception(e)
ValueError: in user code:

    File ".../venv/lib/python3.8/site-packages/keras/engine/training.py", line 1021, in train_function  *
        return step_function(self, iterator)
    File ".../venv/lib/python3.8/site-packages/keras/engine/training.py", line 1010, in step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    File ".../venv/lib/python3.8/site-packages/keras/engine/training.py", line 1000, in run_step  **
        outputs = model.train_step(data)
    File ".../venv/lib/python3.8/site-packages/keras/engine/training.py", line 860, in train_step
        loss = self.compute_loss(x, y, y_pred, sample_weight)
    File ".../venv/lib/python3.8/site-packages/keras/engine/training.py", line 918, in compute_loss
        return self.compiled_loss(
    File ".../venv/lib/python3.8/site-packages/keras/engine/compile_utils.py", line 201, in __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    File ".../venv/lib/python3.8/site-packages/keras/losses.py", line 141, in __call__
        losses = call_fn(y_true, y_pred)
    File ".../venv/lib/python3.8/site-packages/keras/losses.py", line 245, in call  **
        return ag_fn(y_true, y_pred, **self._fn_kwargs)
    File ".../venv/lib/python3.8/site-packages/keras/losses.py", line 1789, in categorical_crossentropy
        return backend.categorical_crossentropy(
    File ".../venv/lib/python3.8/site-packages/keras/backend.py", line 5083, in categorical_crossentropy
        target.shape.assert_is_compatible_with(output.shape)

    ValueError: Shapes (None, 4) and (None, 3) are incompatible

The code I'm using looks like this

import os
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ['CUDA_VISIBLE_DEVICES'] = "-1"
from sklearn.preprocessing import LabelBinarizer
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
from preprocesing import ImageToArrayPreprocessor, SimplePreprocesssor
from datasets import SimpleDatasetLoader
from neuralnetworks.conv import ShallowNet
from keras.optimizers import gradient_descent_v2
from imutils import paths
import argparse

ap = argparse.ArgumentParser()
ap.add_argument("-d", "--dataset", required=True, help="path to input dataset")
args = vars(ap.parse_args())

imagePaths = list(paths.list_images(args["dataset"]))

sp = SimplePreprocesssor(32, 32)
iap = ImageToArrayPreprocessor()

sdl = SimpleDatasetLoader(preprocessors=[sp, iap])
(data, labels) = sdl.load(imagePaths, verbose=500)
data = data.astype("float") / 255.0

(trainX, testX, trainY, testY) = train_test_split(data, labels, test_size=0.25, random_state=42)

trainY = LabelBinarizer().fit_transform(trainY)
testY = LabelBinarizer().fit_transform(testY)


opt = gradient_descent_v2.SGD(learning_rate=0.005)
model = ShallowNet.build(width=32, height=32, depth=3, classes=3)

model.compile(loss="categorical_crossentropy", optimizer=opt, metrics=['acc'])

H = model.fit(trainX, trainY, validation_data=(testX, testY), batch_size=32, epochs=100, verbose=1)

The simpleloader is a function that just loads the images and the simplepreprocesor just resizes the images and I think the error is inside the shallownet.py that looks like this

import os
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = "-1"


from keras.models import Sequential
from keras.layers.convolutional import Conv2D
from keras.layers.core import Activation, Flatten, Dense
from keras import backend as K


class ShallowNet():
    @staticmethod
    def build(width, height, depth, classes):
        model = Sequential()
        inputShape = (height, width, depth)
        if K.image_data_format() == "channels_first":
            inputShape = (depth, height, width)

        model.add(Conv2D(32, (3, 3), padding="same", input_shape=inputShape))
        model.add(Activation("relu"))
        model.add(Flatten())
        model.add(Dense(classes))
        model.add(Activation("softmax"))

        return model

What I deduce is that as my computer doesn't have a GPU I can't perform the training and then I can't fit the model. There is a way to perform this training?