therealnaveenkamal

auc_vals = []
for i in range(len(labels)):
    try:
        gt = np.array(testgenerator.labels[:, i])
        pred = predicted_vals[:,i]
        gt = gt.astype('int64')
        auc_vals.append(roc_auc_score(gt, pred))
        fpr_rf, tpr_rf, _ = roc_curve(gt, pred)
        plt.figure(1, figsize=(10, 10))
        plt.plot([0, 1], [0, 1], 'k--')

therealnaveenkamal

model = DenseNet121(weights='densenet.hdf5', include_top=False)
model = Model(inputs=model.input, outputs=Dense(len(labels), activation="sigmoid")(GlobalAveragePooling2D()(model.output)))
model.compile(optimizer='adam', loss=calcloss(negative_freqs, positive_freqs))
fitter = model.fit(traingenerator, validation_data=valgenerator, steps_per_epoch = 1000, epochs = 50)
model.save_weights("cxr_naveen.h5")

plt.plot(fitter.history['loss'])
plt.ylabel("loss")
plt.xlabel("epoch")
plt.title("Training Loss Curve")

therealnaveenkamal

def calcloss(positivewt, negativewt, al=1e-7):
    def weighted_loss(y_true, y_pred):
        loss = 0.0
        for i in range(len(positivewt)):
            loss += -((positivewt[i] * K.transpose(y_true)[i] * K.log(K.transpose(y_pred)[i] + al))+(negativewt[i]*(1 - K.transpose(y_true)[i])*K.log(1 - K.transpose(y_pred)[i] + al)))
        return K.mean(loss)
    return weighted_loss

therealnaveenkamal

data = {
    'Class': labels,
    'Positive': positive_freqs*negative_freqs,
    'Negative':negative_freqs*positive_freqs
}

X_axis = np.arange(len(labels))
fig, ax = plt.subplots(figsize=(10, 5))
ax.bar(X_axis-0.2, data['Positive'], width=0.4, color='b', label = "Positive")
ax.bar(X_axis+0.2, data['Negative'], width=0.4, color='r', label = 'Negative')

therealnaveenkamal

positive_freqs = np.mean(traingenerator.labels, axis = 0)
negative_freqs = 1 - positive_freqs
data = {
    'Class': labels,
    'Positive': positive_freqs,
    'Negative':negative_freqs
}

X_axis = np.arange(len(labels))
fig, ax = plt.subplots(figsize=(10, 5))

therealnaveenkamal

from keras.preprocessing.image import ImageDataGenerator

#To standardize the images, we use samplewise_center = True and samplewize_std_normalization = True
traingen = ImageDataGenerator(samplewise_center=True, samplewise_std_normalization= True)
traingenerator = traingen.flow_from_dataframe(
        dataframe=trainset,
        directory="images",
        x_col="Image",
        y_col= labels,
        class_mode="raw",

therealnaveenkamal

num = np.random.randint(trainset.shape[0])
sample = plt.imread(os.path.join(img_dir,trainset.iloc[[num]]["Image"].values[0]))
plt.figure(figsize=(15, 15))
plt.title(dataframe[dataframe["Image Index"] == trainset.iloc[[num]]["Image"].values[0]].values[0][1])
plt.imshow(sample, cmap = 'gray')
plt.colorbar()
trainset.iloc[[num]]

print("Maximum Pixel Value: ", sample.max())
print("Minimum Pixel Value: ", sample.min())

therealnaveenkamal

def isOverlap(s1, s2):
    total = set(s1).intersection(set(s2))
    return [len(total), total]
  
def overlapcheck(trainset, valset, testset):
    patid_train = []
    patid_val = []
    patid_test = []
    for name in trainset['Image'].values:
        patid_train.append(int(name.split("_")[0]))

therealnaveenkamal

dataframe = pd.read_csv("Data_Entry_2017_v2020.csv")

#Enumerating all column names
columns = ["Image"]
for i in dataframe["Finding Labels"].values:
    for j in i.split("|"):
        if j not in columns:
            columns.append(j)
labels = columns.copy()
labels.remove("Image")

therealnaveenkamal

import os
import cv2
import random
import numpy as np
import pandas as pd
import seaborn as sns
import tensorflow as tf
import matplotlib.pyplot as plt

from keras import backend as K