I'm working on an image classification model for a multiclass problem. I get the model up and running, but when I try to predict/test the model, it appears only to be able to recognise 1 of 4 image types (it's the same class no matter how I change the model). My dataset per class is pretty small, but I do use imagegenerator to increase the amount of data. The model should be able to recognise the images with some added noise on the picture.
My challenges can be boiled down to this:
Small amount of data. I have < 100 images per class.
My model is not supposed to find specific figures, but more overall patterns in the picture (areas with a certain colour and such).
Many of the pictures contain a lot of white and text. Do I need any image preprocessing to help the model.
My model looks like this:
model = Sequential()
model.add(Conv2D(32, (3, 3), padding='same', activation='relu', input_shape=(s1,s2,3), data_format = "channels_first"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(64, (3, 3), padding='same', activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(50, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4, activation='softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='Adam',
metrics=['accuracy'])
And has img size of 250,250, and batch size 16.
Check acc and loss curves
acc curve
loss curve
Do you guys have any advice?
Thanks in advance!
This is classical overfitting. You need to severely restrain your model and/or use transfer learning to combat this behavior. For restraining options you can increase dropout and add l2 regularization. In my experience l2 regularization really makes the problem hard for a NN. For the transfer learning you can use a resnet and just train the last 2-3 layers.
However, nothing beats having more data points though.
Related
I am working on a project to detect the presence of a person in a painting. I have 4000 training images and 1000 test images resized to (256,256,3)
I tried a CNN model with 3 (Conv layers, MaxPool, BatchNormalization) and 2 fully connected layers.
model = Sequential()
model.add(Conv2D(32, kernel_size = (7, 7), activation='relu', input_shape=shape))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(BatchNormalization())
model.add(Conv2D(64, kernel_size=(7,7), activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(BatchNormalization())
model.add(Conv2D(96, kernel_size=(5,5), activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(BatchNormalization())
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dense(32, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(1, activation = 'sigmoid'))
The train accuracy always converges to 1 (with just 20-50 epochs) and the test accuracy always remains constant around 0.67.
I tried the following:
I tried changing the size of the layers and adding more layers.
I tried data augmentation
I tried smaller images 128x128x3.
But I always have the same results.
I don't know if this is due to the few images I have, or if the architecture isn't big enough to learn from complex paintings.
I thought of trying Transfer Learning (But I don't know if this will help because it is my first time trying it). Also, do you have any idea where can I find trained models?
So, I am asking from some suggestions to improve my model.
It might be that you are overfitting on your training data, in that case you can use dropout.
The other thing is If you have not already normalized your data, you can do that. I am not sure whether that would be much help but give it a try with sth like:
X_training = X_training / X_training.max()
I tried using VGG16 (frozen) with 4 fully connected layers and the validation accuracy went up to 0.83. Also, I am using ImageDataGenerator.
I'm trying to make an OCR for Bangla character. I have 168 different classes. For predicting each character my model is
model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
activation='relu',
input_shape=(42,28,1)))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))
It performs well in my testing set. I'm trying to predict a single instance but for each different instance it's showing same class output. I read single image as following
from PIL import Image
#location for single image
location='Bangla-Compound-Character-Recognition/data/2/ka.jpg'
#image size = (42x28) grayscale
image=np.array(Image.open(location)).reshape(42,28,1)
image=np.expand_dims(image,axis=0)
single_image_cls=model.predict_classes(image)
print(single_image_cls)
Predicting a single instance of test set shows proper result and test accuracy is 90%
#predicting a single test instance
probablity=model.predict_classes(x_test[100:101])
When testing on new images, you have to apply the same normalization as the training set, normally dividing image pixels by 255:
single_image_cls=model.predict_classes(image / 255)
I'm pretty new to deep learning, doing hobby projects. Right now i'm doing multiclass image classification with 200 classes. Is there a tutorial or an actual architecture i can take a look on?
So far i tried basic Dense and CNN nets, but i could never reach better accuracy than 5%.
So far my very basic CNN looks like this.
model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
activation='relu',
input_shape=input_shape,
data_format='channels_first'))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(128, (4, 4), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(256, (5, 5), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))
model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))
model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.Adam(),
metrics=['accuracy'])
I looked up for solutions but could never find any project with such large amount of classes(besides VGG-19 or other SOTA CNNs, but i would try write my own, since this is for learning purposes). Is anybody had similar projects or have some tutorial or any advise on such problem?
Thanks in advance.
200 classes is literally few.
Try
from keras.applications.resnet50 import ResNet50
model = ResNet50(weights=None, classes=200)
model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.Adam(),
metrics=['accuracy'])
This model(ResNet50) should be good enough for most task.
Every models in keras.applications are trained to have 1000 classes, if your task is some real-world image you can use the trained weights by
from keras.applications.resnet50 import ResNet50
from keras.layers import Dense
from keras.models import Model
model = ResNet50(weights='imagenet')
x = model.get_layer('avg_pool').output
x = Dense(200, activation='softmax')(x)
model = Model(model.input, x)
I'm new to machine learning and Keras. I made an Neural Network with Keras for regression looking like this:
model = Sequential()
model.add(Dense(57, input_dim=44, kernel_initializer='normal',
activation='relu'))
model.add(Dense(45, activation='relu'))
model.add(Dense(35, activation='relu'))
model.add(Dense(20, activation='relu'))
model.add(Dense(18, activation='relu'))
model.add(Dense(15, activation='relu'))
model.add(Dense(10, activation='relu'))
model.add(Dense(5, activation='relu'))
model.add(Dense(5, activation='relu'))
model.add(Dense(1, activation='linear'))
My data after preprocessing has 44 dimensions, so could you please give me an example how could i make an CNN.
Originally it looks like this: https://scontent.fskp1-1.fna.fbcdn.net/v/t1.0-9/40159383_10204721730878434_598395145989128192_n.jpg?_nc_cat=0&_nc_eui2=AeEYA4Nb3gomElC9qt0kF6Ou86P7jidco_LeHxEkmCB0-oVA9YKVe9VAh41SF25YomKTqKdkS96E18-sTCBidxJdbml4OV7FvFuAOWxI4mRafQ&oh=e81f4f56ebdf15e9c6eefbb078b8a982&oe=5BFD4157
Convolution neural network is not the best choice in this case. BTW you can do this thing easily with Conv1d:
model = keras.Sequential()
model.add(keras.layers.Embedding(44, 100))
model.add(keras.layers.Conv1D(50, kernel_size=1, strides=1))
model.add(keras.layers.GlobalAveragePooling1D())
# model.add(keras.layers.Dense(10, activation=tf.nn.relu))
model.add(keras.layers.Dense(1, activation=tf.nn.sigmoid))
To answer your question upfront I don't think you can use CNNs for your problem. Generally when people say they are using CNNs they usually mean the 2D convolution. It is operated on 2D spatial data (images). In NLP there exists 1D Convolution which people use to find local patterns in sequentual data. I don't think 1D convolution is relevant in your case. If you are from ML background you can think of regression using feed forward neural networks as polynomial regression. Intuitively you let the network decide which polynomial degree should we use to fit the data properly
You can add 2Dconvnet-layers like this:
model.add(Conv2D(32, (3, 3), input_shape=(3, 150, 150)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
where
model.add(Conv2D(<feature maps>, (<kernel size>), input_shape=(<imput-tensor-shape)))
But be careful, 2Dconfnet-layers are mathematically different than dense-layers, so you can't stack them easily. To stack 2Dconvnet-layers with dense layers, you'll have to flatten them (you'll normally do this at the end to get your "fully-connected layer"):
model.add(Flatten()) # this converts our 3D feature maps to 1D feature vectors
model.add(Dense(64))
model.add(Activation('relu'))
You'll find a lot of good tutorials on creating conv-nets with keras. This one for example focuses on image recognition. The examples above are taken from this article.
To find out, what a convolutional network does, I'd recommend you this article.
Edit:
But I share the opinion, that it might not be useful to use 2DConvnet layers for your example. Your data structure seems kind of "flat" and 2Dconvnets only make sense, when you have some multidimensional tensors as inputs.
I need to build a Bull's eye rash recognition system.
I chose to work with Tensorflow+Keras for this. I've batch downloaded about 300 images of bull's eye rash, and same amount of other skin diseases&clean skin images. Here is my model:
model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))
In the process (30 epochs) it does give 90%+ accuracy, however, the system shows only about 65% accuracy on the test set.
Then I tried to crop all the rash images so that they fill the entire image. The result was disappointing, again, I don't know why, but it showed about 55% accuracy on the test set.
Can you give me some suggestions on what to do? Is the model wrong or inefficient? Do I have to use some other ML techniques for this?
Examples of images from my dataset: here, here and here
Examples of cropped pictures I used for the second attempt: here, here and here
Well, hard to start with this information.
1) have you tried pre-processing your images?
2) have you tried to load in a pre trained VGG16 network (looks close to yours), then you only need to train the dense layers.
base_model = VGG16(weights='imagenet', include_top=False, input_shape=target_shape)
model_top = Sequential()
model_top.add(Flatten(name='flatten', input_shape=base_model.output_shape[1:]))
model_top.add(Dense(4096, activation='relu', name='fc1'))
model_top.add(Dense(4096, activation='relu', name='fc2'))
model_top.add(Dropout(0.5))
model_top.add(Dense(nr_classes, activation='softmax', name='predictions'))
model_full = Model(inputs=base_model.input, outputs=model_top(base_model.output))
# set the first 25 layers (up to the last convolution block)
# to non-trainable (weights will not be updated)
for layer in model_full.layers[:-5]:
layer.trainable = False
model_full.compile(loss='categorical_crossentropy',
optimizer=optimizers.Adam(lr=1e-7))
model_full.summary()
3) Create a validation set to see if you overfit the network (validation accuracy decreases, but training accuracy increases).