0

My keras version is 2.2.4 and tf is 1.15.3.

Code to create the model:

import numpy as np
import pandas as pd
%matplotlib inline
import matplotlib as mpl
import matplotlib.pyplot as plt

import tensorflow as tf
from tensorflow import keras

keras.__version__

tf.__version__

fashion_mnist = keras.datasets.fashion_mnist
(X_train_full, y_train_full), (X_test, y_test) = fashion_mnist.load_data()

plt.imshow(X_train_full[10])

class_names = ["T-shirt/top", "Trouser", "Pullover", "Dress", "Coat",
               "Sandal", "Shirt", "Sneaker", "Bag", "Ankle boot"]

class_names[y_train_full[10]]

X_train_full[10]

X_train_n = X_train_full / 255.
X_test_n = X_test / 255.

X_valid, X_train = X_train_n[:5000], X_train_n[5000:]
y_valid, y_train = y_train_full[:5000], y_train_full[5000:]
X_test = X_test_n

X_valid[0]

np.random.seed(42)
tf.random.set_random_seed(42)

model = keras.models.Sequential()
model.add(keras.layers.Flatten(input_shape=[28, 28]))
model.add(keras.layers.Dense(300, activation="relu"))
model.add(keras.layers.Dense(100, activation="relu"))
model.add(keras.layers.Dense(10, activation="softmax"))

model.summary()

Output summary:

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
flatten (Flatten)            (None, 784)               0         
_________________________________________________________________
dense (Dense)                (None, 300)               235500    
_________________________________________________________________
dense_1 (Dense)              (None, 100)               30100     
_________________________________________________________________
dense_2 (Dense)              (None, 10)                1010      
=================================================================
Total params: 266,610
Trainable params: 266,610
Non-trainable params: 0
_________________________________________________________________

Code that is generating the error:

pip install pydot
pip install graphviz

import pydot
from keras.utils.vis_utils import plot_model

plot_model(model, to_file= 'model.png' , show_shapes=True)

Error:

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
~\AppData\Local\Temp\ipykernel_14952\4050438567.py in <module>
----> 1 plot_model(model, to_file= 'model.png' , show_shapes=True)

NameError: name 'model' is not defined


    weights, biases = model.layers[1].get_weights()

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
~\AppData\Local\Temp\ipykernel_14952\2052231455.py in <module>
----> 1 model.layers[1].get_weights()

NameError: name 'model' is not defined

I expected to proceed and get the weights and biases of the model. The cell however shows the error that: name 'model' is not defined like this:

enter image description here

ClaudiaR
  • 3,108
  • 2
  • 13
  • 27
FELIX MUTUMA
  • 1
  • 1
  • Welcome to Stack Overflow. Please include your code and errors as text and not as an image. – ewokx Sep 09 '22 at 07:46
  • 1
    Can barely see the code; but what I can see is ```plot_model(model,....)```. Where did you define model? – ewokx Sep 09 '22 at 07:59
  • model = keras.models.Sequential() model.add(keras.layers.Flatten(input_shape=[28, 28])) model.add(keras.layers.Dense(300, activation="relu")) model.add(keras.layers.Dense(100, activation="relu")) model.add(keras.layers.Dense(10, activation="softmax")) – FELIX MUTUMA Sep 09 '22 at 19:05
  • Please provide enough code so others can better understand or reproduce the problem. – Community Sep 09 '22 at 20:20
  • Are you sure you executed the code related to the creation of `model`, right before executing the cell to plot it? – ClaudiaR Sep 10 '22 at 11:00

0 Answers0