CODEWITHSUNDEEP
pythontensorflowmachine-learningkeras
Tomek Pulkiewicz
Tomek Pulkiewicz

Reputation: 79

My image classification model written in tensorflow don't learn

im trying to build image classification model that will predict if you are wearing a mask.This is a first time i make my own model and when im training it the accuracy jump arround 50% and if i predict it always says "no mask" i tryied changing number of epoches, batch size, number of training data changing model code and nothing works. This is my code:

import os
import cv2
import random
import numpy as np
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Flatten,Dropout
from tensorflow.keras.optimizers import SGD

def preproccesImage(img):
     img = cv2.resize(img,dsize=(150,150 ), interpolation = cv2.INTER_CUBIC)
     return img

def getData():
     training = []

     for image in os.listdir("src/data/with_mask"):
          img = cv2.imread(f"src/data/with_mask/{image}",cv2.IMREAD_GRAYSCALE)
          proccesed = preproccesImage(img)
          training.append([proccesed.tolist(),1])

     for image in os.listdir("src/data/without_mask"):
          img = cv2.imread(f"src/data/without_mask/{image}",cv2.IMREAD_GRAYSCALE)
          proccesed = preproccesImage(img)
          training.append([proccesed.tolist(),0])

     random.shuffle(training)
     train_x = np.array([x[0] for x in training],dtype=np.float32)
     train_y = np.array([x[1] for x in training],dtype=np.float32)
     print(train_x)
     print(train_y)
     return (train_x ,train_y)

train_x , train_y = getData()

model = Sequential()

model.add(Dense(32,input_shape=(len(train_x[0]),150),activation="relu"))
model.add(Flatten())
model.add(Dense(128,activation="relu"))
model.add(Dropout(0.2))
model.add(Dense(128,activation="relu"))
model.add(Flatten())
model.add(Dense(1,activation="softmax"))


model.compile(loss="categorical_crossentropy",
              optimizer="adam", metrics=["accuracy"])



hist = model.fit(
    train_x,train_y,
    epochs=200, batch_size=2, verbose=1)
model.save("model.h5", hist)

img = cv2.imread("src/me.png",cv2.IMREAD_GRAYSCALE)
resized = cv2.resize(img,dsize=(150,150 ), interpolation = cv2.INTER_CUBIC)


def predict():
     res = model.predict([resized.tolist()])[0]
     resoult = [[i, r] for i, r in enumerate(res)]
     predicted = []
     for r in resoult:
        predicted.append({"intent": 1 if r[0] == 1 else 0, "probability": r[1]})
     if predicted[0]["intent"] == 1:
          print("mask on")
     else:
          print('no mask')
     
predict()

I will be pleased if someone can help

Upvotes: 0

Views: 101

Answers (1)

desertnaut
desertnaut

Reputation: 60319

This is not the correct combination for binary classification; you should change your loss to binary_crossentropy and the activation of your last layer to sigmoid, i.e.:

model.add(Dense(1,activation="sigmoid"))  # last layer

model.compile(loss="binary_crossentropy",
              optimizer="adam", metrics=["accuracy"])

More generally, you could really benefit from some convolutional layers in the early stages of your model; notice also that placing Flatten layers after Dense ones does not make any sense.

Upvotes: 1

Related Questions