alstat

(x_train, y_train), (x_test, y_test) = cifar100.load_data(label_mode = "fine")

alstat

library(keras)

# Define the constants
CONST_N <- 2000
CONST_EPOCHS <- 30
CONST_PIXEL_MAX <- 255

alstat

from numpy import arange, product, vstack, zeros
from keras.models import Sequential
from keras.layers import  Activation, Dense, Dropout
from keras.datasets import cifar100
from keras.utils.np_utils import to_categorical
from matplotlib.pylab import axis, imshow, savefig, show, subplots

# Define the constants
CONST_N = 2000
CONST_EPOCHS = 30

alstat

install.packages("keras")

alstat

using Images
using MLDatasets
using Flux: ADAM,
            argmax, 
            Chain, 
            crossentropy, 
            Dense, 
            params,
            relu, 
            softmax, 

alstat

using Flux: onehotbatch

x_vec = [float.(reshape(x_train[:, :, :, i], :)) for i in 1:1000];
X = hcat(x_vec...);            
Y = onehotbatch(y_train_fine[1:1000], 0:99);

alstat

using Flux: ADAM,
            argmax, 
            Chain,
            Dense, 
            params,
            relu, 
            softmax

m = Chain(
    Dense(32^2 * 3, 32 * 10, relu),

alstat

using Images
vcat([hcat([CIFAR100.convert2image(x_train[:, :, :, i + 20*j]) for i in 1:20]...) for j in 0:9]...)

alstat

CIFAR100.convert2image(x_train[:, :, :, 1])

alstat

size(x_train)          # (32, 32, 3, 50000)
size(y_train_coarse)   # (50000,) 
size(y_train_fine)     # (50000,)

typeof(x_train)        # Array{FixedPointNumbers.Normed{UInt8,8},4}
typeof(y_train_coarse) # Array{Int64,1}
typeof(y_train_fine)   # Array{Int64,1}