I am trying to make a handwriting classifier by referencing the article: https://github.com/priya-dwivedi/Deep-Learning/blob/master/handwriting_recognition/English_Writer_Identification.ipynb.
while fitting the model I get an error saying that the fir_generator does not expect any such argument!
Also while the error itself is a unexpected argument error the tag shows up as type error, I wonder if something is wrong with my pipeline.
Here is the model. (I am excluding all code after the error as it shouldn't be relevant any ways. You can reffer to the code in the above link if you feel its important)
Tensorflow Version - 1.14 , Keras version - 2.2.4
from __future__ import division
import numpy as np
import os
import glob
from PIL import Image
from random import *
from tensorflow.keras.utils
import to_categorical
from sklearn.preprocessing
import LabelEncoder
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
%matplotlib inline
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Flatten, Lambda, ELU, Activation, BatchNormalization
from tensorflow.keras.layers import Convolution2D, Cropping2D, ZeroPadding2D, MaxPooling2D
from tensorflow.keras.optimizers import SGD, Adam, RMSprop
import tensorflow
import tensorflow.keras
# Create sentence writer mapping
#Dictionary with form and writer mapping
d = {}
with open('forms_for_parsing.txt') as f:
for line in f:
key = line.split(' ')[0]
writer = line.split(' ')[1]
d[key] = writer
tmp = []
target_list = []
path_to_files = os.path.join('datab', '*')
for filename in sorted(glob.glob(path_to_files)):
tmp.append(filename)
image_name = filename.split(os.sep)[1]
file, ext = os.path.splitext(image_name)
parts = file.split('-')
form = parts[0] + '-' + parts[1]
for key in d:
if key == form:
target_list.append(str(d[form]))
img_files = np.asarray(tmp)
img_targets = np.asarray(target_list)
# Visualizing the data
for filename in img_files[:3]:
img=mpimg.imread(filename)
plt.figure(figsize=(10,10))
plt.imshow(img, cmap ='gray')
# Label Encode writer names for one hot encoding later
encoder = LabelEncoder()
encoder.fit(img_targets)
encoded_Y = encoder.transform(img_targets)
print(img_files[:5], img_targets[:5], encoded_Y[:5])
#split into test train and validation in ratio 4:1:1
from sklearn.model_selection import train_test_split
train_files, rem_files, train_targets, rem_targets = train_test_split(
img_files, encoded_Y, train_size=0.66, random_state=52, shuffle= True)
validation_files, test_files, validation_targets, test_targets = train_test_split(
rem_files, rem_targets, train_size=0.5, random_state=22, shuffle=True)
print(train_files.shape, validation_files.shape, test_files.shape)
print(train_targets.shape, validation_targets.shape, test_targets.shape)
# Generator function for generating random crops from each sentence
# # Now create generators for randomly cropping 113x113 patches from these images
batch_size = 16
num_classes = 50
# Start with train generator shared in the class and add image augmentations
def generate_data(samples, target_files, batch_size=batch_size, factor = 0.1 ):
num_samples = len(samples)
from sklearn.utils import shuffle
while 1: # Loop forever so the generator never terminates
for offset in range(0, num_samples, batch_size):
batch_samples = samples[offset:offset+batch_size]
batch_targets = target_files[offset:offset+batch_size]
images = []
targets = []
for i in range(len(batch_samples)):
batch_sample = batch_samples[i]
batch_target = batch_targets[i]
im = Image.open(batch_sample)
cur_width = im.size[0]
cur_height = im.size[1]
# print(cur_width, cur_height)
height_fac = 113 / cur_height
new_width = int(cur_width * height_fac)
size = new_width, 113
imresize = im.resize((size), Image.ANTIALIAS) # Resize so height = 113 while keeping aspect ratio
now_width = imresize.size[0]
now_height = imresize.size[1]
# Generate crops of size 113x113 from this resized image and keep random 10% of crops
avail_x_points = list(range(0, now_width - 113 ))# total x start points are from 0 to width -113
# Pick random x%
pick_num = int(len(avail_x_points)*factor)
# Now pick
random_startx = sample(avail_x_points, pick_num)
for start in random_startx:
imcrop = imresize.crop((start, 0, start+113, 113))
images.append(np.asarray(imcrop))
targets.append(batch_target)
# trim image to only see section with road
X_train = np.array(images)
y_train = np.array(targets)
#reshape X_train for feeding in later
X_train = X_train.reshape(X_train.shape[0], 113, 113, 1) time , and use -1
X_train = X_train.astype('float32')
X_train /= 255
#One hot encode y
y_train = to_categorical(y_train, num_classes)
yield shuffle(X_train, y_train) # literraly shuffel
train_generator = generate_data(train_files, train_targets, batch_size=batch_size, factor = 0.3)
validation_generator = generate_data(validation_files, validation_targets, batch_size=batch_size, factor = 0.3)
test_generator = generate_data(test_files, test_targets, batch_size=batch_size, factor = 0.1)
history_object = model.fit_generator(train_generator, steps_per_epoch= samples_per_epoch1,
validation_data=validation_generator,
nb_val_samples=nb_val_samples, nb_epoch=nb_epoch, verbose=1, callbacks=callbacks_list)
The error log is as follows-
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-34-54937a660f6c> in <module>
1 history_object = model.fit_generator(train_generator, steps_per_epoch= samples_per_epoch1,
2 validation_data=validation_generator,
----> 3 nb_val_samples=nb_val_samples, nb_epoch=nb_epoch, verbose=1, callbacks=callbacks_list)
TypeError: fit_generator() got an unexpected keyword argument 'nb_val_samples'