“损失：0.0000e+00 - acc: 1.0000 - val_loss: 0.0000e+00 - val_acc: 1.0000”是什么意思？

Question

I am trying to classify skin diseases into 4 classes. I tried transfer learning using VGG16. No matter what changes I make, its not classifying. Accuracy is 1 and loss is 0. But I think its not overfitting also, as by confusion matrix I got to know that its classifying everything as single class.

import json
import math
import os
import cv2
from PIL import Image
import numpy as np
from keras import layers
from keras.callbacks import Callback, ModelCheckpoint, ReduceLROnPlateau, TensorBoard
from keras.models import Model
from keras.applications.vgg16 import VGG16, preprocess_input
from keras.preprocessing.image import ImageDataGenerator
from keras.utils.np_utils import to_categorical
from keras.models import Sequential
from keras.optimizers import Adam
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.metrics import cohen_kappa_score, accuracy_score
import scipy
import tensorflow as tf
from keras import backend as K
import gc
from functools import partial
from tqdm import tqdm
from sklearn import metrics
from collections import Counter
import json
import itertools
from keras.optimizers import Adam
from keras.applications.vgg16 import VGG16, preprocess_input
from keras.preprocessing.image import ImageDataGenerator
from keras.callbacks import ModelCheckpoint, EarlyStopping
from keras.layers import Dense, Dropout, Flatten

#loading data and data preparation

def Dataset_loader(DIR, RESIZE, sigmaX=10):
    IMG = []
    read = lambda imname: np.asarray(Image.open(imname).convert("RGB"))
    for IMAGE_NAME in tqdm(os.listdir(DIR)):
        PATH = os.path.join(DIR,IMAGE_NAME)
        _, ftype = os.path.splitext(PATH)
        if ftype == ".jpg":
            img = read(PATH)

            img = cv2.resize(img, (RESIZE,RESIZE))

            IMG.append(np.array(img))
    return IMG

eczema_train = np.array(Dataset_loader('/content/medical-image-analysis/train/Eczema Photos', 224))
melanoma_train = np.array(Dataset_loader('/content/medical-image-analysis/train/Melanoma Skin Cancer Nevi and Moles',224))
psoriasis_train = np.array(Dataset_loader('/content/medical-image-analysis/train/Psoriasis pictures Lichen Planus and related diseases',224))

#labelling 
eczema_train_label = np.zeros(len(eczema_train))
melonoma_train_label = np.zeros(len(melanoma_train))
psoriasis_train_label = np.zeros(len(psoriasis_train))

X_train = np.concatenate((eczema_train, melanoma_train, psoriasis_train), axis=0,)
Y_train = np.concatenate((eczema_train_label, melonoma_train_label, psoriasis_train_label), axis=0,)

#train and evaluation split
X_train = (X_train-np.mean(X_train))/np.std(X_train)
X_train, X_test, Y_train, Y_test = train_test_split(
    X_train, Y_train, 
    test_size=0.3, 
    random_state=1
)
X_test, X_val, Y_test, Y_val = train_test_split(
    X_test, Y_test, 
    test_size=0.3, 
    random_state=1
)

s = np.arange(X_train.shape[0])
np.random.shuffle(s)
X_train = X_train[s]
Y_train = Y_train[s]

pre_trained_model = VGG16(input_shape=(224, 224, 3), include_top=False, weights="imagenet")

for layer in pre_trained_model.layers:
    print(layer.name)
    layer.trainable = False
    
print(len(pre_trained_model.layers))

last_layer = pre_trained_model.get_layer('block5_pool')
print('last layer output shape:', last_layer.output_shape)
last_output = last_layer.output

# Flatten the output layer to 1 dimension
x = layers.GlobalMaxPooling2D()(last_output)
# Add a fully connected layer with 512 hidden units and ReLU activation
x = layers.Dense(128, activation='softmax')(x)
# Add a dropout rate of 0.5
x = layers.Dropout(0.5)(x)
# Add a final sigmoid layer for classification
x = layers.Dense(4, activation='softmax')(x)

# Configure and compile the model

model = Model(pre_trained_model.input, x)
optimizer = Adam(lr=0.0001, beta_1=0.9, beta_2=0.9999, epsilon=None, decay=0.0, amsgrad=True)
model.compile(loss='categorical_crossentropy',
              optimizer=optimizer,
              metrics=['accuracy'])

train_datagen = ImageDataGenerator(rotation_range=60,
                    shear_range=0.2,
                    zoom_range=0.2,
                    width_shift_range=0.2,
                    height_shift_range=0.2,
                    horizontal_flip=True,
                    fill_mode='nearest')

train_datagen.fit(X_train)

val_datagen = ImageDataGenerator()
val_datagen.fit(X_val)

batch_size = 64
epochs = 3
history = model.fit(train_datagen.flow(X_train,Y_train, batch_size=batch_size),
                              epochs = epochs, validation_data = val_datagen.flow(X_val, Y_val),
                              verbose = 1, steps_per_epoch=(X_train.shape[0] // batch_size), 
                              validation_steps=(X_val.shape[0] // batch_size))

This is the code, can you please help to find out where we went wrong. Thanks in advance:)

Answer 1

 #labelling eczema_train_label = np.zeros(len(eczema_train)) melonoma_train_label = np.zeros(len(melanoma_train)) psoriasis_train_label = np.zeros(len(psoriasis_train))

All of these numpy arrays are filled with zeroes. No matter whether an image represents eczema, melanoma, or psoriasis, you define its ground-truth label as 0 and hence your model "learns" to unconditionally output 0. Make the labels for at least two of the classes nonzero.

Further, you are using a CategoricalCrossentropy, which is only suitable for one-hot label encodings or binary classification. Use a sparse categorical (or sparse softmax) crossentropy instead. (Note that there may be other issues in the code, but this one stands out as a common error which may be seen).