Akash-Rawat

preds = model.predict(val_images) 
plt.figure(figsize=(20,20))
for n , i in enumerate(list(np.random.randint(0,len(val_images),36))) : 
    plt.subplot(6,6,n+1)
    plt.imshow(val_images[i])    
    plt.axis('off')
    x =np.argmax(preds[i]) # takes the maximum of of the 6 probabilites. 
    plt.title((class_names[x]))

Akash-Rawat

Epoch 1/20
30/30 [==============================] - ETA: 0s - loss: 0.6868 - accuracy: 0.5508
Epoch 00001: accuracy improved from -inf to 0.55085, saving model to modelPedestrianDetection.h5
30/30 [==============================] - 1s 42ms/step - loss: 0.6868 - accuracy: 0.5508 - val_loss: 0.6735 - val_accuracy: 0.5787
Epoch 2/20
28/30 [===========================>..] - ETA: 0s - loss: 0.6447 - accuracy: 0.6451
Epoch 00002: accuracy improved from 0.55085 to 0.64407, saving model to modelPedestrianDetection.h5
30/30 [==============================] - 1s 32ms/step - loss: 0.6434 - accuracy: 0.6441 - val_loss: 0.6594 - val_accuracy: 0.6128
Epoch 3/20
28/30 [===========================>..] - ETA: 0s - loss: 0.5339 - accuracy: 0.7489

Akash-Rawat

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d (Conv2D)              (None, 198, 198, 16)      448       
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 99, 99, 16)        0         
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 97, 97, 32)        4640      
_________________________________________________________________

Akash-Rawat

from tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping
from tensorflow.keras.callbacks import ReduceLROnPlateau
es = EarlyStopping(monitor='accuracy', mode='max', verbose=1, patience=7)
filepath = "modelPedestrianDetection.h5"
ckpt = ModelCheckpoint(filepath, monitor='accuracy', verbose=1, save_best_only=True, mode='max')
rlp = ReduceLROnPlateau(monitor='accuracy', patience=3, verbose=1)

Akash-Rawat

model = models.Sequential()
model.add(layers.Conv2D(16, (3, 3), activation='relu', input_shape=(200, 200, 3)))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(32, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Flatten())
model.add(layers.Dense(128, activation='relu'))
model.add(layers.Dense(2))
model.summary()

Akash-Rawat

def load_data():
    datasets = ['Pedestrian-Detection/Train/Train', 'Pedestrian-Detection/Test/Test', 'Pedestrian-Detection/Val/Val']
    output = []

    for dataset in datasets:
        imags = []
        labels = []
        directoryA = dataset +"/Annotations"
        directoryIMG = dataset +"/JPEGImages/"
        file = os.listdir(directoryA)

Akash-Rawat

history = neuralnetwork_cnn.fit_generator(
    generator=training_set, validation_data=validation_set,
    callbacks=[es, ckpt, rlp], epochs = 5, 
)

#output

Epoch 1/5
1842/1843 [============================>.] - ETA: 0s - loss: 0.0524 - acc: 0.9855
Epoch 00001: acc improved from -inf to 0.98548, saving model to modelMedicalMNIST.h5

Akash-Rawat

def cnn(image_size, num_classes):
    classifier = Sequential()
    classifier.add(Conv2D(64, (5, 5), input_shape=image_size, activation='relu', padding='same'))
    classifier.add(MaxPooling2D(pool_size = (2, 2)))
    classifier.add(Conv2D(128, (3, 3), activation='relu', padding='same'))
    classifier.add(MaxPooling2D(pool_size = (2, 2)))
    classifier.add(Flatten())
    classifier.add(Dense(num_classes, activation = 'softmax'))
    classifier.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['acc'])
    return classifier

Akash-Rawat

image_size = (32, 32, 3)
datagen=ImageDataGenerator(rescale = 1./255,
                           shear_range=0.2,
                           zoom_range=0.2,
                           horizontal_flip=True,
                           )
                           
training_set=datagen.flow_from_directory(train_dir,
                                         target_size=image_size[:2],
                                         batch_size=32,

Akash-Rawat

def show_mri(med):
  num = len(med)
  if num == 0:
    return None
  rows = int(math.sqrt(num))
  cols = (num+1)//rows
  f, axs = plt.subplots(rows, cols)
  fig = 0
  for b in med:
    img = image.load_img(b)