As an exercise I am trying to train a classification model using Tensorflow v1 without using keras nor sklearn nor any other library that would greatly ease my life.. lol.
I keep getting this error though and I can't figure out what's wrong about my code :
# imports
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O
import os,shutil, cv2, itertools
import tensorflow.compat.v1 as tf
tf.disable_v2_behavior() # use Tensorflow v1
For simplicity I resized every image to 64 x 64.
Since there are 3 channels, size of input vector X wiz n is 64 x 64 x 3 (=12288).
To reduce computation time I only use 3000 images from the training data.
TRAIN_DATA_DIR_PREFIX = '/kaggle/input/cat-and-dog/training_set/training_set/'
TRAIN_DATA_DOG_DIR = TRAIN_DATA_DIR_PREFIX 'dogs/'
TRAIN_DATA_CAT_DIR = TRAIN_DATA_DIR_PREFIX 'cats/'
N_x = 64 * 64 * 3
TRAIN_DOG = [(TRAIN_DATA_DOG_DIR i, 1) for i in os.listdir(TRAIN_DATA_DOG_DIR) if i.endswith(".jpg")]
TRAIN_DOG = TRAIN_DOG[:1500]
TRAIN_CAT = [(TRAIN_DATA_CAT_DIR i, 0) for i in os.listdir(TRAIN_DATA_CAT_DIR) if i.endswith(".jpg")]
TRAIN_CAT = TRAIN_CAT[:1500]
TRAIN_DATA = TRAIN_DOG TRAIN_CAT
print('TRAIN_DATA :', len(TRAIN_DATA))
def read_image(file_path):
image = cv2.imread(file_path, cv2.IMREAD_COLOR)
return cv2.resize(image, (64, 64),interpolation=cv2.INTER_CUBIC)
def prepare(data):
X = np.ndarray((N_x,len(TRAIN_DATA)), dtype=np.uint8)
print ("X shape is {}".format(X.shape))
Y = np.zeros((1,len(TRAIN_DATA)))
print ("Y shape is {}".format(Y.shape))
for i,(image_path, y) in enumerate(data):
Y[0,i] = y
image = read_image(image_path)
X[:,i] = np.squeeze(image.reshape((N_x,1)))
return X,Y
X,Y = prepare(TRAIN_DATA)
Y = tf.transpose(Y)
X = tf.transpose(X)
print ("after transpose X shape is {}".format(X.shape))
print ("after transpose Y shape is {}".format(Y.shape))
Output:
TRAIN_DATA : 3000
X shape is (12288, 3000)
Y shape is (1, 3000)
after transpose X shape is (3000, 12288)
after transpose Y shape is (3000, 1)
Then I define my tf_train function:
def tf_train(X, Y, batch_size=20):
# Dataset (inputs and labels)
D=12880
x = tf.placeholder(tf.float32, [batch_size, D])
y_ = tf.placeholder(tf.float32, [batch_size, 1])
# random variable
W = tf.Variable(tf.random_normal([D, 1],stddev=0.1))
z=tf.matmul(x,W)
# Define loss and optimizer
cross_entropy = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=z, labels=y_))
train_step = tf.train.GradientDescentOptimizer(1e-2).minimize(cross_entropy)
sess = tf.InteractiveSession()
tf.initialize_all_variables().run() #initializes W and z
# Train
for epoch in range (3000):
idx = np.random.choice(len(TRAIN_DATA), batch_size, replace=False)
#idx = np.random.permutation(np.arange(X.shape[1])) [:batch_size]
_, l = sess.run([train_step, cross_entropy], feed_dict={x: X[idx], y_: Y[0,idx]})
if epoch%100 == 0:
print('loss: ' str(l))
And then when I start training my model :
tf_train(X,Y)
I get this following output:
/opt/conda/lib/python3.7/site-packages/tensorflow/python/client/session.py:1766: UserWarning: An interactive session is already active. This can cause out-of-memory errors in some cases. You must explicitly call `InteractiveSession.close()` to release resources held by the other session(s).
warnings.warn('An interactive session is already active. This can '
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
/tmp/ipykernel_33/1897119706.py in <module>
----> 1 tf_train(X,Y)
/tmp/ipykernel_33/3528951873.py in tf_train(X, Y, batch_size)
29 idx = np.random.choice(len(TRAIN_DATA), batch_size, replace=False)
30 #idx = np.random.permutation(np.arange(X.shape[1])) [:batch_size]
---> 31 _, l = sess.run([train_step, cross_entropy], feed_dict={x: X[idx], y_: Y[0,idx]})
32 if epoch%100 == 0:
33 print('loss: ' str(l))
/opt/conda/lib/python3.7/site-packages/tensorflow/python/util/dispatch.py in wrapper(*args, **kwargs)
204 """Call target, and fall back on dispatchers if there is a TypeError."""
205 try:
--> 206 return target(*args, **kwargs)
207 except (TypeError, ValueError):
208 # Note: convert_to_eager_tensor currently raises a ValueError, not a
/opt/conda/lib/python3.7/site-packages/tensorflow/python/ops/array_ops.py in _slice_helper(tensor, slice_spec, var)
1012 new_axis_mask |= (1 << index)
1013 else:
-> 1014 _check_index(s)
1015 begin.append(s)
1016 end.append(s 1)
/opt/conda/lib/python3.7/site-packages/tensorflow/python/ops/array_ops.py in _check_index(idx)
886 # TODO(slebedev): IndexError seems more appropriate here, but it
887 # will break `_slice_helper` contract.
--> 888 raise TypeError(_SLICE_TYPE_ERROR ", got {!r}".format(idx))
889
890
TypeError: Only integers, slices (`:`), ellipsis (`...`), tf.newaxis (`None`) and scalar tf.int32/tf.int64 tensors are valid indices, got array([2282, 1114, 1884, 2812, 887, 381, 1723, 2031, 820, 2989, 314,
1800, 372, 2219, 1937, 2313, 2264, 2154, 2168, 283])
Apparently the error is caused by
_, l = sess.run([train_step, cross_entropy], feed_dict={x: X[idx], y_: Y[0,idx]})
Any idea what's wrong with it ?
CodePudding user response：
You are trying to slice your inputs based on idx, which is a list and therefore it will not work. Try something like this:
%tensorflow_version 1.x
import tensorflow as tf
import numpy as np
def tf_train(X, Y, batch_size=20):
# Dataset (inputs and labels)
D=12880
x = tf.placeholder(tf.float32, [batch_size, D])
y_ = tf.placeholder(tf.float32, [batch_size, 1])
# random variable
W = tf.Variable(tf.random_normal([D, 1],stddev=0.1))
z=tf.matmul(x,W)
# Define loss and optimizer
cross_entropy = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=z, labels=y_))
train_step = tf.train.GradientDescentOptimizer(1e-2).minimize(cross_entropy)
sess = tf.InteractiveSession()
tf.initialize_all_variables().run() #initializes W and z
# Train
for epoch in range (3000):
idx = np.random.choice(3000, batch_size, replace=False)
xx = np.array([X[i, :] for i in idx])
yy = np.array([Y[i, :] for i in idx])
_, l = sess.run([train_step, cross_entropy], feed_dict={x: xx, y_: yy})
if epoch%100 == 0:
print('loss: ' str(l))
X = np.random.random((3000, 12880))
Y = np.random.random((3000, 1))
tf_train(X, Y)
loss: 2.0646608
loss: 3.5250945
loss: 4.343132
loss: 4.4199777
loss: 2.8261409
loss: 3.0091796
loss: 2.010383
loss: 2.4877071
loss: 3.520267
loss: 4.089248
loss: 8.244058
loss: 1.5667378