I have my model saved as a numpy array. I am trying to pickle the model to run predictions on a new dataset. However I keep running into an attribute error.
model = y_pred_binary
filename = 'transfer_prediction_model.pkl'
pickle.dump(model, open(filename, 'wb'))
ickled_model = pickle.load(open(filename, 'rb'))
df = pd.read_csv(f"transfer_students_prediction_dataset.csv")
predictions = pickled_model.predict(df.drop('on_time_graduation', axis = 1))
print(predictions)
AttributeError Traceback (most recent call last)
Input In [24], in <cell line: 3>()
`1 pickled_model = pickle.load(open(filename, 'rb'))
2 df = pd.read_csv(f"transfer_students_prediction_dataset.csv")
----> 3 predictions = pickled_model.predict(df.drop('on_time_graduation', axis = 1))
4 print(predictions)`
AttributeError: 'numpy.ndarray' object has no attribute 'predict'`
I have tried using other methods such as joblib or fitting the model using sklearn but I still run into the same problem.
Related
I wanted to apply Bert on a sequence of sentences in the following manner, but I am getting a NotImplementedError
How to reproduce :
import tensorflow as tf
from transformers import BertTokenizer, TFBertModel
inputs = tf.keras.Input(shape=(50, 64), dtype='int32')
model = TFBertModel.from_pretrained('bert-base-uncased')
outputs = tf.keras.layers.TimeDistributed(model)(inputs)
NotImplementedError Traceback (most recent call last)
<ipython-input-5-631f3cd2e8b2> in <module>
----> 1 outputs = tf.keras.layers.TimeDistributed(model)(inputs)
Whereas the code would work fine for
inputs = tf.keras.Input(shape=(10, 128, 128, 3))
conv_2d_layer = tf.keras.layers.Conv2D(64, (3, 3))
outputs = tf.keras.layers.TimeDistributed(conv_2d_layer)(inputs)
Is there anything I am missing here?
I´m trying to visualize some images belonging to different classes. The classes are class0,class1,class2 and they mean X-ray pictures with healthy, covid and pneumonia lungs respectively. As an example, see picture below of a covid lung:
I´ve created three datasets containing the training, test and validation data. Please, see below the code:
import pandas as pd
from keras_preprocessing.image import ImageDataGenerator
from matplotlib import pyplot as plt
import numpy as np
#Creating three dataframes reading .txt files
trainingfile = pd.read_table('data/training.txt', delim_whitespace=True, names=('class', 'image'))
testingfile = pd.read_table('data/testing.txt', delim_whitespace=True, names=('class', 'image'))
validationfile = pd.read_table('data/validation.txt', delim_whitespace=True, names=('class', 'image'))
#Change 0,1,2 to categorical class class0,class1,class2
trainingfile = trainingfile.replace([0, 1, 2], ['class0', 'class1', 'class2'])
testingfile = testingfile.replace([0, 1, 2], ['class0', 'class1', 'class2'])
validationfile = validationfile.replace([0, 1, 2], ['class0', 'class1', 'class2'])
#Final training, test and validation data
datagen=ImageDataGenerator(rescale=None)
train_generator=datagen.flow_from_dataframe(dataframe=trainingfile, directory="data/", x_col="image", y_col="class", class_mode="categorical", target_size=(256,256), batch_size=32)
test_generator=datagen.flow_from_dataframe(dataframe=testingfile, directory="data/", x_col="image", y_col="class", class_mode="categorical", target_size=(256,256), batch_size=15)
validation_generator=datagen.flow_from_dataframe(dataframe=validationfile, directory="data/", x_col="image", y_col="class", class_mode="categorical", target_size=(256,256), batch_size=21)
Now, the code to visualize one picture:
first_image = train_generator[0]
first_image = np.array(first_image, dtype='float')
pixels = first_image.reshape((28, 28))
plt.imshow(pixels, cmap='gray')
plt.show()
I get the following error:
ValueError Traceback (most recent call last)
<ipython-input-3-b237e88f96dd> in <module>
1 first_image = train_generator[0]
----> 2 first_image = np.array(first_image, dtype='float')
3 pixels = first_image.reshape((28, 28))
4 plt.imshow(pixels, cmap='gray')
5 plt.show()
ValueError: could not broadcast input array from shape (32,256,256,3) into shape (32)
Furthermore, is there any way to visualize an image corresponding to a specific class?
If instead of first_image= first_image[0], I do first_image= first_image[0][0]. Then the error that pops up is:
ValueError Traceback (most recent call last)
<ipython-input-4-0664c7dc8c6b> in <module>
1 first_image = train_generator[0][0]
2 first_image = np.array(first_image, dtype='float')
----> 3 pixels = first_image.reshape((28, 28))
4 plt.imshow(pixels, cmap='gray')
5 plt.show()
ValueError: cannot reshape array of size 6291456 into shape (28,28)
I've written a simple tensorflow code & constantly getting TypeError error, I am trying to write a code for simple log regression. Error is in this line : logits = tf.matmul( img,w) + b ,
Following is the error:
Traceback (most recent call last): File "test.py", line 22, in <module> logits = tf.matmul(img,w) + b File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/math_ops.py",
line 2122, in matmul a, b, transpose_a=transpose_a, transpose_b=transpose_b, name=name) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_math_ops.py",
line 4279, in mat_mul name=name) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py",
line 546, in _apply_op_helper inferred_from[input_arg.type_attr]))
TypeError: Input 'b' of 'MatMul' Op has type float32 that does not match type float64 of argument 'a'
Help me to resolve this issue. Here is the code:
import tensorflow as tf
import numpy as np
#making dummy dataset and converting that in tensor object
x = (np.random.sample((100,2)), np.random.sample((100,1)))
train_data = tf.data.Dataset.from_tensor_slices(x)
y = (np.random.sample((10,2)), np.random.sample((10,1)))
test_data = tf.data.Dataset.from_tensor_slices(y)
#making iteration to access the dataset
train_iterator = train_data.make_initializable_iterator()
img, label = train_iterator.get_next()
#define weights & biases
w = tf.get_variable("weight", initializer=tf.constant((0.0)))
b = tf.get_variable("bias", initializer=tf.constant((0.0)))
tf.cast(img, tf.float64)
tf.cast(w, tf.float64)
tf.cast(b, tf.float64)
#model
logits = tf.matmul(img,w) + b
#loss
entropy = tf.nn.softmax_cross_entropy_with_logits(labels=label, logits=logits)
loss = tf.reduce_mean(entropy)
#optimizer
optimizer = tf.train.AdamOptimizer(learning_rate=0.01).minimize(loss)
#create the session
with tf.Session() as sess:
sess.run(train_iterator.initializer)
for i in range(100):
sess.run([optimizer,loss])
print(optimizer,loss)
You did not save the tf.cast() result back to the variables. Try below to fix it.
img = tf.cast(img, tf.float64)
w = tf.cast(w, tf.float64)
b = tf.cast(b, tf.float64)
I am trying to create an image classifier that utilizes the pre-trained ResNet V2 model provided in the slim documentation.
Here is the code so far:
import tensorflow as tf
slim = tf.contrib.slim
from PIL import Image
from inception_resnet_v2 import *
import numpy as np
checkpoint_file = 'inception_resnet_v2_2016_08_30.ckpt'
sample_images = ['carrot.jpg']
input_tensor = tf.placeholder(tf.float32, shape=(None,299,299,3), name='input_image')
scaled_input_tensor = tf.scalar_mul((1.0/255), input_tensor)
scaled_input_tensor = tf.subtract(scaled_input_tensor, 0.5)
scaled_input_tensor = tf.multiply(scaled_input_tensor, 2.0)
variables_to_restore = slim.get_model_variables()
print(variables_to_restore)
init_fn = slim.assign_from_checkpoint_fn(
checkpoint_file,
slim.get_model_variables('InceptionResnetV2'))
sess = tf.Session()
init_fn(sess)
arg_scope = inception_resnet_v2_arg_scope()
with slim.arg_scope(arg_scope):
logits, end_points = inception_resnet_v2(scaled_input_tensor, is_training=False)
for image in sample_images:
im = Image.open(image).resize((299,299))
im = np.array(im)
im = im.reshape(-1,299,299,3)
predict_values, logit_values = sess.run([end_points['Predictions'], logits], feed_dict={input_tensor: im})
print (np.max(predict_values), np.max(logit_values))
print (np.argmax(predict_values), np.argmax(logit_values))
The problem is I keep getting this error:
Traceback (most recent call last):
File "./classify.py", line 21, in <module>
slim.get_model_variables('InceptionResnetV2'))
File "/home/ubuntu/tensorflow/local/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/variables.py", line 584, in assign_from_checkpoint_fn
saver = tf_saver.Saver(var_list, reshape=reshape_variables)
File "/home/ubuntu/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1040, in __init__
self.build()
File "/home/ubuntu/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1061, in build
raise ValueError("No variables to save")
ValueError: No variables to save
So it seems TF/Slim is unable to find any variables and this is made clear when I call:
variables_to_restore = slim.get_model_variables()
print(variables_to_restore)
As it outputs an empty array.
How can I go about using the pre-trained model?
This happens because you haven't constructed the model in your graph yet to have any variables starting with the name "InceptionResnetV2" to be captured and restored by the saver.
I believe you should put the model construction before using slim.get_variables_to_restore().
For instance:
with slim.arg_scope(arg_scope):
logits, end_points = inception_resnet_v2(scaled_input_tensor, is_training=False)
variables_to_restore = slim.get_model_variables()
This way, the Tensor variables will be constructed and you should see variables_to_restore is no longer empty.
You need to manually add the model variables.
Try this
with slim.arg_scope(arg_scope):
logits, end_points = inception_resnet_v2(scaled_input_tensor, is_training=False)
# Add model variables
for var in tf.global_variables(scope='inception_resnet_v2'):
slim.add_model_variable(var)
I am trying to implement a recurrent state tensor using tf.scan. The code I have at the moment is this:
import tensorflow as tf
import math
import numpy as np
INPUTS = 10
HIDDEN_1 = 20
BATCH_SIZE = 3
def iterate_state(prev_state_tuple, input):
with tf.name_scope('h1'):
weights = tf.get_variable('W', shape=[INPUTS, HIDDEN_1], initializer=tf.truncated_normal_initializer(stddev=1.0 / math.sqrt(float(INPUTS))))
biases = tf.get_variable('bias', shape=[HIDDEN_1], initializer=tf.constant_initializer(0.0))
matmuladd = tf.matmul(inputs, weights) + biases
unpacked_state, unpacked_out = tf.split(0,2,prev_state_tuple)
prev_state = unpacked_state
state = 0.9* prev_state + 0.1*matmuladd
output = tf.nn.relu(state)
return tf.concat(0,[state, output])
def data_iter():
while True:
idxs = np.random.rand(BATCH_SIZE, INPUTS)
yield idxs
with tf.Graph().as_default():
inputs = tf.placeholder(tf.float32, shape=(BATCH_SIZE, INPUTS))
with tf.variable_scope('states'):
initial_state = tf.zeros([HIDDEN_1],
name='initial_state')
initial_out = tf.zeros([HIDDEN_1],
name='initial_out')
concat_tensor = tf.concat(0,[initial_state, initial_out])
states, output = tf.scan(iterate_state, inputs,
initializer=concat_tensor, name='states')
sess = tf.Session()
# Run the Op to initialize the variables.
sess.run(tf.initialize_all_variables())
iter_ = data_iter()
for i in xrange(0, 2):
print ("iteration: ",i)
input_data = iter_.next()
out,st = sess.run([output,states], feed_dict={ inputs: input_data})
However, I get this error when running this:
Traceback (most recent call last):
File "cycles_in_graphs_with_scan.py", line 37, in <module>
initializer=concat_tensor, name='states')
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 442, in __iter__
raise TypeError("'Tensor' object is not iterable.")
TypeError: 'Tensor' object is not iterable.
(tensorflow)charlesq#Leviathan ~/projects/stuff $ python cycles_in_graphs_with_scan.py
Traceback (most recent call last):
File "cycles_in_graphs_with_scan.py", line 37, in <module>
initializer=concat_tensor, name='states')
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 442, in __iter__
raise TypeError("'Tensor' object is not iterable.")
TypeError: 'Tensor' object is not iterable.
I've already tried with pack/unpack and concat/split but I get this same error.
Any ideas how to solve this problem?
You're getting an error because tf.scan() returns a single tf.Tensor, so the line:
states, output = tf.scan(...)
...cannot destructure (unpack) the tensor returned from tf.scan() into two values (states and outputs). Effectively, the code is trying to treat the result of tf.scan() as a list of length 2, and assign the first element to states and the second element to output, but—unlike a Python list or tuple—tf.Tensor does not support this.
Instead you need to extract the values from the result of tf.scan() manually. For example, using tf.split():
scan_result = tf.scan(...)
# Assumes values are packed together along `split_dim`.
states, output = tf.split(split_dim, 2, scan_result)
Alternatively, you could use tf.slice() or tf.unpack() to extract the relevant states and output values.