Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd Logo
Upload

Welcome to Scribd!

  • 14 views

    Vedant@11

    Uploaded by

    Vedant Andhale

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Vedant@11

    Uploaded by

    Vedant Andhale
    14 views2 pages

    Original Title

    vedant@11

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    14 views2 pages

    Vedant@11

    Uploaded by

    Vedant Andhale

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 2

    11

    April 15, 2024

    [2]: #How to train a neural network with Tensorflow / Pytorch and evaluation of␣
    ↪logistic

    #regression using tensorflow

    import tensorflow as tf
    import numpy as np

    from keras.models import Sequential


    from keras.layers import Dense, Flatten
    from sklearn.model_selection import train_test_split
    from sklearn.preprocessing import StandardScaler
    from sklearn.datasets import load_breast_cancer

    2024-04-15 08:23:30.956156: I external/local_tsl/tsl/cuda/cudart_stub.cc:32]


    Could not find cuda drivers on your machine, GPU will not be used.
    2024-04-15 08:23:31.623215: I external/local_tsl/tsl/cuda/cudart_stub.cc:32]
    Could not find cuda drivers on your machine, GPU will not be used.
    2024-04-15 08:23:32.012440: I tensorflow/core/platform/cpu_feature_guard.cc:210]
    This TensorFlow binary is optimized to use available CPU instructions in
    performance-critical operations.
    To enable the following instructions: AVX2 FMA, in other operations, rebuild
    TensorFlow with the appropriate compiler flags.
    2024-04-15 08:23:34.290430: W
    tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not
    find TensorRT

    [3]: df=load_breast_cancer()
    # two classifications -- malignant / benign

    X_train,X_test,y_train,y_test=train_test_split(df.data,df.target,test_size=0.
    ↪20,random_state=42)

    sc=StandardScaler()
    X_train=sc.fit_transform(X_train)
    X_test=sc.transform(X_test)

    model=Sequential([

    1
    Flatten(input_shape=(X_train.shape[1],)),
    Dense(1,activation='sigmoid')
    ])

    model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])

    model.fit(X_train,y_train,epochs=5)

    test_loss,test_accuracy = model.evaluate(X_test,y_test)

    print("Test Loss: ",test_loss)


    print("accuracy is",test_accuracy)

    /home/codespace/.python/current/lib/python3.10/site-
    packages/keras/src/layers/reshaping/flatten.py:37: UserWarning: Do not pass an
    `input_shape`/`input_dim` argument to a layer. When using Sequential models,
    prefer using an `Input(shape)` object as the first layer in the model instead.
    super().__init__(**kwargs)
    Epoch 1/5
    15/15 �������������������� 1s 1ms/step -
    accuracy: 0.2533 - loss: 1.1562
    Epoch 2/5
    15/15 �������������������� 0s 1ms/step -
    accuracy: 0.2794 - loss: 0.9930
    Epoch 3/5
    15/15 �������������������� 0s 791us/step -
    accuracy: 0.3805 - loss: 0.8562
    Epoch 4/5
    15/15 �������������������� 0s 860us/step -
    accuracy: 0.4316 - loss: 0.7761
    Epoch 5/5
    15/15 �������������������� 0s 805us/step -
    accuracy: 0.5924 - loss: 0.6963
    4/4 �������������������� 0s 2ms/step -
    accuracy: 0.6548 - loss: 0.5986
    Test Loss: 0.6006454825401306
    accuracy is 0.6578947305679321

    You might also like