Running Spyder code on GPU instead of CPU on Ubuntu

Question

I am working on Spyder to create deep learning model on a machine have a GPU I have found that am working on a CPU and my code run for a long time.First I downloaded tensorflow-GPU but I don't how to start working on GPU.

I used { with tf.device("cpu"): } but when I write nvidia-smi on terminal I found no running processes.

I also used { import os os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = "" import os os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = "" import os os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = "" } but it doesn't work.

How to make my Spyder code run on GPU instead of cpu on Ubuntu?

Any help would be appreciated.

code:

def createModel():
   with tf.device("cpu"):
        input_shape=(1, 22, 5, 3844)
        model = Sequential()
        model.add(Conv3D(16, (22, 5, 5), strides=(1, 2, 2), padding='same',activation='relu',data_format= "channels_first", input_shape=input_shape))

        model.add(keras.layers.MaxPooling3D(pool_size=(1, 2, 2),data_format= "channels_first",  padding='same'))

        model.add(BatchNormalization())
        model.add(Conv3D(32, (1, 3, 3), strides=(1, 1,1), padding='same',data_format= "channels_first",  activation='relu'))#incertezza se togliere padding

        model.add(keras.layers.MaxPooling3D(pool_size=(1,2, 2),data_format= "channels_first", ))
        model.add(BatchNormalization())
        model.add(Conv3D(64, (1,3, 3), strides=(1, 1,1), padding='same',data_format= "channels_first",  activation='relu'))#incertezza se togliere padding
        model.add(keras.layers.MaxPooling3D(pool_size=(1,2, 2),data_format= "channels_first",padding='same' ))
        model.add(BatchNormalization())
        model.add(Dense(64, input_dim=64,kernel_regularizer=regularizers.l2(0.0001), activity_regularizer=regularizers.l1(0.0001)))
        model.add(Flatten())
        model.add(Dropout(0.5))
        model.add(Dense(256, activation='sigmoid'))
        model.add(Dropout(0.5))
        model.add(Dense(2, activation='softmax'))
        opt_adam = keras.optimizers.Adam(lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=0.0)
        model.compile(loss='categorical_crossentropy', optimizer=opt_adam, metrics=['accuracy'])
    return model

Answer 1

According to github discussion there are 2 ways to solve that problem:

1. Uninstall tensorflow and install downgrade version of tensorflow

   pip uninstall tensorflow pip uninstall tensorflow-gpu pip install tensorflow==1.8.0 pip install tensorflow-gpu==1.8.0

2. If you have more than 1 GPU

    export CUDA_VISIBLE_DEVICES='0'