JoshVarty

learner = create_cnn(data, models.resnet34, metrics=error_rate)
learner.fit_one_cycle(5)

JoshVarty

learner = create_cnn(data, models.resnet34, metrics=error_rate)
learner.fit_one_cycle(5)

JoshVarty

from fastai.vision import *
from fastai.metrics import error_rate

path = 'data/kittencat/'

data = ImageDataBunch.from_folder(path, train=".", valid_pct=0.2,
        ds_tfms=get_transforms(), size=224, num_workers=4).normalize(imagenet_stats)

JoshVarty

from fastai.vision import *
from fastai.metrics import error_rate

path = 'data/kittencat/'

data = ImageDataBunch.from_folder(path, train=".", valid_pct=0.2,
        ds_tfms=get_transforms(), size=224, num_workers=4).normalize(imagenet_stats)

JoshVarty

learner = create_cnn(data, models.resnet34, metrics=error_rate)
learner.fit_one_cycle(5)

JoshVarty

path = 'data/paintings/'

data = ImageDataBunch.from_folder(path, train=".", valid_pct=0.2,
        ds_tfms=get_transforms(), size=224, num_workers=4).normalize(imagenet_stats)
        
data.show_batch(rows=3, figsize=(7,8))

JoshVarty

from fastai.vision import *
from fastai.metrics import error_rate

JoshVarty

#include <cstddef>
#include <iostream>
#include <string>
#include <vector>


#include <torch/torch.h>

JoshVarty

import tensorflow as tf
import numpy as np
import cifar_data_loader

(train_images, train_labels, test_images, test_labels, mean_image) = cifar_data_loader.load_data()

print(train_images.shape)
print(train_labels.shape)
print(test_images.shape)
print(test_labels.shape)

JoshVarty

input_minus_mean = input - mean_image                                                                     #Subtract mean from input images

layer1_weights = tf.get_variable("layer1_weights", [3, 3, 3, 64], initializer=tf.contrib.layers.variance_scaling_initializer())
layer1_bias = tf.Variable(tf.zeros([64]))
layer1_conv = tf.nn.conv2d(input_minus_mean, filter=layer1_weights, strides=[1,1,1,1], padding='SAME')    #Use input_minus_mean now
layer1_out = tf.nn.relu(layer1_conv + layer1_bias)