Horse Or Human Using TensorFlow 2.0
Table of Contents
Beginning
Imports
Python
from functools import partial
from pathlib import Path
PyPi
from holoviews.operation.datashader import datashade
from tensorflow.keras.models import load_model
from tensorflow.keras import layers
from tensorflow.keras.applications.inception_v3 import InceptionV3
from tensorflow.keras.optimizers import RMSprop
from tensorflow.keras.preprocessing.image import ImageDataGenerator
import cv2
import holoviews
import hvplot.pandas
import matplotlib.pyplot as pyplot
import numpy
import pandas
import tensorflow
Graeae
from graeae import EmbedHoloviews, Timer, ZipDownloader
Setup
The Timer
TIMER = Timer()
Plotting
Embed = partial(
EmbedHoloviews,
folder_path="../../files/posts/keras/horse-or-human-using-tensorflow-20")
holoviews.extension("bokeh")
Storage
MODELS = Path("~/models/horses-vs-humans/").expanduser()
if not MODELS.is_dir():
MODELS.mkdir()
Middle
The Data Set
OUTPUT = "~/data/datasets/images/horse-or-human/training/"
URL = ("https://storage.googleapis.com/"
"laurencemoroney-blog.appspot.com/"
"horse-or-human.zip")
download = ZipDownloader(url=URL, target=OUTPUT)
download()
Files exist, not downloading
:RESULTS:
2019-08-13 13:51:57,970 [1mZipDownloader[0m start: ([1mZipDownloader[0m) Started: 2019-08-13 13:51:57.970533 2019-08-13 13:51:57,972 [1mZipDownloader[0m download: Downloading the zip file 2019-08-13 13:52:08,157 [1mZipDownloader[0m end: ([1mZipDownloader[0m) Ended: 2019-08-13 13:52:08.157484 2019-08-13 13:52:08,159 [1mZipDownloader[0m end: ([1mZipDownloader[0m) Elapsed: 0:00:10.186951
output_path = download.target
The convention for training models for computer vision appears to be that you use the folder names to label the contents of the images within them. In this case we have horses and humans.
Here's what some of the files themselves are named.
horses_path = output_path/"horses"
humans_path = output_path/"humans"
for path in (horses_path, humans_path):
print(path.name)
for index, image in enumerate(path.iterdir()):
print(f"File: {image.name}")
if index == 9:
break
print()
horses File: horse48-5.png File: horse45-8.png File: horse13-5.png File: horse34-4.png File: horse46-5.png File: horse02-3.png File: horse06-3.png File: horse32-1.png File: horse25-3.png File: horse04-3.png humans File: human01-07.png File: human02-11.png File: human13-07.png File: human10-10.png File: human15-06.png File: human05-15.png File: human06-18.png File: human16-28.png File: human02-24.png File: human10-05.png
So, in this case you can tell what they are from the file-names as well. How many images are there?
horse_files = list(horses_path.iterdir())
human_files = list(humans_path.iterdir())
print(f"Horse Images: {len(horse_files)}")
print(f"Human Images: {len(human_files)}")
print(f"Image Shape: {pyplot.imread(str(horse_files[0])).shape}")
Horse Images: 500 Human Images: 527 Image Shape: (300, 300, 4)
This is sort of a small data-set, and it's odd that there are more humans than horses. Let's see what some of them look like. I'm assuming all the files have the same shape. In this case it looks like they are 300 x 300 with four channels (RGB and alpha?).
height = width = 300
count = 4
columns = 2
horse_plots = [datashade(holoviews.RGB.load_image(str(horse)).opts(
height=height,
width=width,
))
for horse in horse_files[:count]]
human_plots = [datashade(holoviews.RGB.load_image(str(human))).opts(
height=height,
width=width,
)
for human in human_files[:count]]
plot = holoviews.Layout(horse_plots + human_plots).cols(2).opts(
title="Horses and Humans")
Embed(plot=plot, file_name="horses_and_humans",
height_in_pixels=900)()
As you can see, the people in the images aren't really humans (and it may not be so obvious, but they aren't horses either), these are computer-generated images.
The Model
input_shape = (300, 300, 3)
base_model = InceptionV3(input_shape=input_shape, include_top=False)
base_model.trainable = False
print(base_model.summary())
Model: "inception_v3"
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_1 (InputLayer) [(None, 300, 300, 3) 0
__________________________________________________________________________________________________
conv2d (Conv2D) (None, 149, 149, 32) 864 input_1[0][0]
__________________________________________________________________________________________________
batch_normalization (BatchNorma (None, 149, 149, 32) 96 conv2d[0][0]
__________________________________________________________________________________________________
activation (Activation) (None, 149, 149, 32) 0 batch_normalization[0][0]
__________________________________________________________________________________________________
conv2d_1 (Conv2D) (None, 147, 147, 32) 9216 activation[0][0]
__________________________________________________________________________________________________
batch_normalization_1 (BatchNor (None, 147, 147, 32) 96 conv2d_1[0][0]
__________________________________________________________________________________________________
activation_1 (Activation) (None, 147, 147, 32) 0 batch_normalization_1[0][0]
__________________________________________________________________________________________________
conv2d_2 (Conv2D) (None, 147, 147, 64) 18432 activation_1[0][0]
__________________________________________________________________________________________________
batch_normalization_2 (BatchNor (None, 147, 147, 64) 192 conv2d_2[0][0]
__________________________________________________________________________________________________
activation_2 (Activation) (None, 147, 147, 64) 0 batch_normalization_2[0][0]
__________________________________________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 73, 73, 64) 0 activation_2[0][0]
__________________________________________________________________________________________________
conv2d_3 (Conv2D) (None, 73, 73, 80) 5120 max_pooling2d[0][0]
__________________________________________________________________________________________________
batch_normalization_3 (BatchNor (None, 73, 73, 80) 240 conv2d_3[0][0]
__________________________________________________________________________________________________
activation_3 (Activation) (None, 73, 73, 80) 0 batch_normalization_3[0][0]
__________________________________________________________________________________________________
conv2d_4 (Conv2D) (None, 71, 71, 192) 138240 activation_3[0][0]
__________________________________________________________________________________________________
batch_normalization_4 (BatchNor (None, 71, 71, 192) 576 conv2d_4[0][0]
__________________________________________________________________________________________________
activation_4 (Activation) (None, 71, 71, 192) 0 batch_normalization_4[0][0]
__________________________________________________________________________________________________
max_pooling2d_1 (MaxPooling2D) (None, 35, 35, 192) 0 activation_4[0][0]
__________________________________________________________________________________________________
conv2d_8 (Conv2D) (None, 35, 35, 64) 12288 max_pooling2d_1[0][0]
__________________________________________________________________________________________________
batch_normalization_8 (BatchNor (None, 35, 35, 64) 192 conv2d_8[0][0]
__________________________________________________________________________________________________
activation_8 (Activation) (None, 35, 35, 64) 0 batch_normalization_8[0][0]
__________________________________________________________________________________________________
conv2d_6 (Conv2D) (None, 35, 35, 48) 9216 max_pooling2d_1[0][0]
__________________________________________________________________________________________________
conv2d_9 (Conv2D) (None, 35, 35, 96) 55296 activation_8[0][0]
__________________________________________________________________________________________________
batch_normalization_6 (BatchNor (None, 35, 35, 48) 144 conv2d_6[0][0]
__________________________________________________________________________________________________
batch_normalization_9 (BatchNor (None, 35, 35, 96) 288 conv2d_9[0][0]
__________________________________________________________________________________________________
activation_6 (Activation) (None, 35, 35, 48) 0 batch_normalization_6[0][0]
__________________________________________________________________________________________________
activation_9 (Activation) (None, 35, 35, 96) 0 batch_normalization_9[0][0]
__________________________________________________________________________________________________
average_pooling2d (AveragePooli (None, 35, 35, 192) 0 max_pooling2d_1[0][0]
__________________________________________________________________________________________________
conv2d_5 (Conv2D) (None, 35, 35, 64) 12288 max_pooling2d_1[0][0]
__________________________________________________________________________________________________
conv2d_7 (Conv2D) (None, 35, 35, 64) 76800 activation_6[0][0]
__________________________________________________________________________________________________
conv2d_10 (Conv2D) (None, 35, 35, 96) 82944 activation_9[0][0]
__________________________________________________________________________________________________
conv2d_11 (Conv2D) (None, 35, 35, 32) 6144 average_pooling2d[0][0]
__________________________________________________________________________________________________
batch_normalization_5 (BatchNor (None, 35, 35, 64) 192 conv2d_5[0][0]
__________________________________________________________________________________________________
batch_normalization_7 (BatchNor (None, 35, 35, 64) 192 conv2d_7[0][0]
__________________________________________________________________________________________________
batch_normalization_10 (BatchNo (None, 35, 35, 96) 288 conv2d_10[0][0]
__________________________________________________________________________________________________
batch_normalization_11 (BatchNo (None, 35, 35, 32) 96 conv2d_11[0][0]
__________________________________________________________________________________________________
activation_5 (Activation) (None, 35, 35, 64) 0 batch_normalization_5[0][0]
__________________________________________________________________________________________________
activation_7 (Activation) (None, 35, 35, 64) 0 batch_normalization_7[0][0]
__________________________________________________________________________________________________
activation_10 (Activation) (None, 35, 35, 96) 0 batch_normalization_10[0][0]
__________________________________________________________________________________________________
activation_11 (Activation) (None, 35, 35, 32) 0 batch_normalization_11[0][0]
__________________________________________________________________________________________________
mixed0 (Concatenate) (None, 35, 35, 256) 0 activation_5[0][0]
activation_7[0][0]
activation_10[0][0]
activation_11[0][0]
__________________________________________________________________________________________________
conv2d_15 (Conv2D) (None, 35, 35, 64) 16384 mixed0[0][0]
__________________________________________________________________________________________________
batch_normalization_15 (BatchNo (None, 35, 35, 64) 192 conv2d_15[0][0]
__________________________________________________________________________________________________
activation_15 (Activation) (None, 35, 35, 64) 0 batch_normalization_15[0][0]
__________________________________________________________________________________________________
conv2d_13 (Conv2D) (None, 35, 35, 48) 12288 mixed0[0][0]
__________________________________________________________________________________________________
conv2d_16 (Conv2D) (None, 35, 35, 96) 55296 activation_15[0][0]
__________________________________________________________________________________________________
batch_normalization_13 (BatchNo (None, 35, 35, 48) 144 conv2d_13[0][0]
__________________________________________________________________________________________________
batch_normalization_16 (BatchNo (None, 35, 35, 96) 288 conv2d_16[0][0]
__________________________________________________________________________________________________
activation_13 (Activation) (None, 35, 35, 48) 0 batch_normalization_13[0][0]
__________________________________________________________________________________________________
activation_16 (Activation) (None, 35, 35, 96) 0 batch_normalization_16[0][0]
__________________________________________________________________________________________________
average_pooling2d_1 (AveragePoo (None, 35, 35, 256) 0 mixed0[0][0]
__________________________________________________________________________________________________
conv2d_12 (Conv2D) (None, 35, 35, 64) 16384 mixed0[0][0]
__________________________________________________________________________________________________
conv2d_14 (Conv2D) (None, 35, 35, 64) 76800 activation_13[0][0]
__________________________________________________________________________________________________
conv2d_17 (Conv2D) (None, 35, 35, 96) 82944 activation_16[0][0]
__________________________________________________________________________________________________
conv2d_18 (Conv2D) (None, 35, 35, 64) 16384 average_pooling2d_1[0][0]
__________________________________________________________________________________________________
batch_normalization_12 (BatchNo (None, 35, 35, 64) 192 conv2d_12[0][0]
__________________________________________________________________________________________________
batch_normalization_14 (BatchNo (None, 35, 35, 64) 192 conv2d_14[0][0]
__________________________________________________________________________________________________
batch_normalization_17 (BatchNo (None, 35, 35, 96) 288 conv2d_17[0][0]
__________________________________________________________________________________________________
batch_normalization_18 (BatchNo (None, 35, 35, 64) 192 conv2d_18[0][0]
__________________________________________________________________________________________________
activation_12 (Activation) (None, 35, 35, 64) 0 batch_normalization_12[0][0]
__________________________________________________________________________________________________
activation_14 (Activation) (None, 35, 35, 64) 0 batch_normalization_14[0][0]
__________________________________________________________________________________________________
activation_17 (Activation) (None, 35, 35, 96) 0 batch_normalization_17[0][0]
__________________________________________________________________________________________________
activation_18 (Activation) (None, 35, 35, 64) 0 batch_normalization_18[0][0]
__________________________________________________________________________________________________
mixed1 (Concatenate) (None, 35, 35, 288) 0 activation_12[0][0]
activation_14[0][0]
activation_17[0][0]
activation_18[0][0]
__________________________________________________________________________________________________
conv2d_22 (Conv2D) (None, 35, 35, 64) 18432 mixed1[0][0]
__________________________________________________________________________________________________
batch_normalization_22 (BatchNo (None, 35, 35, 64) 192 conv2d_22[0][0]
__________________________________________________________________________________________________
activation_22 (Activation) (None, 35, 35, 64) 0 batch_normalization_22[0][0]
__________________________________________________________________________________________________
conv2d_20 (Conv2D) (None, 35, 35, 48) 13824 mixed1[0][0]
__________________________________________________________________________________________________
conv2d_23 (Conv2D) (None, 35, 35, 96) 55296 activation_22[0][0]
__________________________________________________________________________________________________
batch_normalization_20 (BatchNo (None, 35, 35, 48) 144 conv2d_20[0][0]
__________________________________________________________________________________________________
batch_normalization_23 (BatchNo (None, 35, 35, 96) 288 conv2d_23[0][0]
__________________________________________________________________________________________________
activation_20 (Activation) (None, 35, 35, 48) 0 batch_normalization_20[0][0]
__________________________________________________________________________________________________
activation_23 (Activation) (None, 35, 35, 96) 0 batch_normalization_23[0][0]
__________________________________________________________________________________________________
average_pooling2d_2 (AveragePoo (None, 35, 35, 288) 0 mixed1[0][0]
__________________________________________________________________________________________________
conv2d_19 (Conv2D) (None, 35, 35, 64) 18432 mixed1[0][0]
__________________________________________________________________________________________________
conv2d_21 (Conv2D) (None, 35, 35, 64) 76800 activation_20[0][0]
__________________________________________________________________________________________________
conv2d_24 (Conv2D) (None, 35, 35, 96) 82944 activation_23[0][0]
__________________________________________________________________________________________________
conv2d_25 (Conv2D) (None, 35, 35, 64) 18432 average_pooling2d_2[0][0]
__________________________________________________________________________________________________
batch_normalization_19 (BatchNo (None, 35, 35, 64) 192 conv2d_19[0][0]
__________________________________________________________________________________________________
batch_normalization_21 (BatchNo (None, 35, 35, 64) 192 conv2d_21[0][0]
__________________________________________________________________________________________________
batch_normalization_24 (BatchNo (None, 35, 35, 96) 288 conv2d_24[0][0]
__________________________________________________________________________________________________
batch_normalization_25 (BatchNo (None, 35, 35, 64) 192 conv2d_25[0][0]
__________________________________________________________________________________________________
activation_19 (Activation) (None, 35, 35, 64) 0 batch_normalization_19[0][0]
__________________________________________________________________________________________________
activation_21 (Activation) (None, 35, 35, 64) 0 batch_normalization_21[0][0]
__________________________________________________________________________________________________
activation_24 (Activation) (None, 35, 35, 96) 0 batch_normalization_24[0][0]
__________________________________________________________________________________________________
activation_25 (Activation) (None, 35, 35, 64) 0 batch_normalization_25[0][0]
__________________________________________________________________________________________________
mixed2 (Concatenate) (None, 35, 35, 288) 0 activation_19[0][0]
activation_21[0][0]
activation_24[0][0]
activation_25[0][0]
__________________________________________________________________________________________________
conv2d_27 (Conv2D) (None, 35, 35, 64) 18432 mixed2[0][0]
__________________________________________________________________________________________________
batch_normalization_27 (BatchNo (None, 35, 35, 64) 192 conv2d_27[0][0]
__________________________________________________________________________________________________
activation_27 (Activation) (None, 35, 35, 64) 0 batch_normalization_27[0][0]
__________________________________________________________________________________________________
conv2d_28 (Conv2D) (None, 35, 35, 96) 55296 activation_27[0][0]
__________________________________________________________________________________________________
batch_normalization_28 (BatchNo (None, 35, 35, 96) 288 conv2d_28[0][0]
__________________________________________________________________________________________________
activation_28 (Activation) (None, 35, 35, 96) 0 batch_normalization_28[0][0]
__________________________________________________________________________________________________
conv2d_26 (Conv2D) (None, 17, 17, 384) 995328 mixed2[0][0]
__________________________________________________________________________________________________
conv2d_29 (Conv2D) (None, 17, 17, 96) 82944 activation_28[0][0]
__________________________________________________________________________________________________
batch_normalization_26 (BatchNo (None, 17, 17, 384) 1152 conv2d_26[0][0]
__________________________________________________________________________________________________
batch_normalization_29 (BatchNo (None, 17, 17, 96) 288 conv2d_29[0][0]
__________________________________________________________________________________________________
activation_26 (Activation) (None, 17, 17, 384) 0 batch_normalization_26[0][0]
__________________________________________________________________________________________________
activation_29 (Activation) (None, 17, 17, 96) 0 batch_normalization_29[0][0]
__________________________________________________________________________________________________
max_pooling2d_2 (MaxPooling2D) (None, 17, 17, 288) 0 mixed2[0][0]
__________________________________________________________________________________________________
mixed3 (Concatenate) (None, 17, 17, 768) 0 activation_26[0][0]
activation_29[0][0]
max_pooling2d_2[0][0]
__________________________________________________________________________________________________
conv2d_34 (Conv2D) (None, 17, 17, 128) 98304 mixed3[0][0]
__________________________________________________________________________________________________
batch_normalization_34 (BatchNo (None, 17, 17, 128) 384 conv2d_34[0][0]
__________________________________________________________________________________________________
activation_34 (Activation) (None, 17, 17, 128) 0 batch_normalization_34[0][0]
__________________________________________________________________________________________________
conv2d_35 (Conv2D) (None, 17, 17, 128) 114688 activation_34[0][0]
__________________________________________________________________________________________________
batch_normalization_35 (BatchNo (None, 17, 17, 128) 384 conv2d_35[0][0]
__________________________________________________________________________________________________
activation_35 (Activation) (None, 17, 17, 128) 0 batch_normalization_35[0][0]
__________________________________________________________________________________________________
conv2d_31 (Conv2D) (None, 17, 17, 128) 98304 mixed3[0][0]
__________________________________________________________________________________________________
conv2d_36 (Conv2D) (None, 17, 17, 128) 114688 activation_35[0][0]
__________________________________________________________________________________________________
batch_normalization_31 (BatchNo (None, 17, 17, 128) 384 conv2d_31[0][0]
__________________________________________________________________________________________________
batch_normalization_36 (BatchNo (None, 17, 17, 128) 384 conv2d_36[0][0]
__________________________________________________________________________________________________
activation_31 (Activation) (None, 17, 17, 128) 0 batch_normalization_31[0][0]
__________________________________________________________________________________________________
activation_36 (Activation) (None, 17, 17, 128) 0 batch_normalization_36[0][0]
__________________________________________________________________________________________________
conv2d_32 (Conv2D) (None, 17, 17, 128) 114688 activation_31[0][0]
__________________________________________________________________________________________________
conv2d_37 (Conv2D) (None, 17, 17, 128) 114688 activation_36[0][0]
__________________________________________________________________________________________________
batch_normalization_32 (BatchNo (None, 17, 17, 128) 384 conv2d_32[0][0]
__________________________________________________________________________________________________
batch_normalization_37 (BatchNo (None, 17, 17, 128) 384 conv2d_37[0][0]
__________________________________________________________________________________________________
activation_32 (Activation) (None, 17, 17, 128) 0 batch_normalization_32[0][0]
__________________________________________________________________________________________________
activation_37 (Activation) (None, 17, 17, 128) 0 batch_normalization_37[0][0]
__________________________________________________________________________________________________
average_pooling2d_3 (AveragePoo (None, 17, 17, 768) 0 mixed3[0][0]
__________________________________________________________________________________________________
conv2d_30 (Conv2D) (None, 17, 17, 192) 147456 mixed3[0][0]
__________________________________________________________________________________________________
conv2d_33 (Conv2D) (None, 17, 17, 192) 172032 activation_32[0][0]
__________________________________________________________________________________________________
conv2d_38 (Conv2D) (None, 17, 17, 192) 172032 activation_37[0][0]
__________________________________________________________________________________________________
conv2d_39 (Conv2D) (None, 17, 17, 192) 147456 average_pooling2d_3[0][0]
__________________________________________________________________________________________________
batch_normalization_30 (BatchNo (None, 17, 17, 192) 576 conv2d_30[0][0]
__________________________________________________________________________________________________
batch_normalization_33 (BatchNo (None, 17, 17, 192) 576 conv2d_33[0][0]
__________________________________________________________________________________________________
batch_normalization_38 (BatchNo (None, 17, 17, 192) 576 conv2d_38[0][0]
__________________________________________________________________________________________________
batch_normalization_39 (BatchNo (None, 17, 17, 192) 576 conv2d_39[0][0]
__________________________________________________________________________________________________
activation_30 (Activation) (None, 17, 17, 192) 0 batch_normalization_30[0][0]
__________________________________________________________________________________________________
activation_33 (Activation) (None, 17, 17, 192) 0 batch_normalization_33[0][0]
__________________________________________________________________________________________________
activation_38 (Activation) (None, 17, 17, 192) 0 batch_normalization_38[0][0]
__________________________________________________________________________________________________
activation_39 (Activation) (None, 17, 17, 192) 0 batch_normalization_39[0][0]
__________________________________________________________________________________________________
mixed4 (Concatenate) (None, 17, 17, 768) 0 activation_30[0][0]
activation_33[0][0]
activation_38[0][0]
activation_39[0][0]
__________________________________________________________________________________________________
conv2d_44 (Conv2D) (None, 17, 17, 160) 122880 mixed4[0][0]
__________________________________________________________________________________________________
batch_normalization_44 (BatchNo (None, 17, 17, 160) 480 conv2d_44[0][0]
__________________________________________________________________________________________________
activation_44 (Activation) (None, 17, 17, 160) 0 batch_normalization_44[0][0]
__________________________________________________________________________________________________
conv2d_45 (Conv2D) (None, 17, 17, 160) 179200 activation_44[0][0]
__________________________________________________________________________________________________
batch_normalization_45 (BatchNo (None, 17, 17, 160) 480 conv2d_45[0][0]
__________________________________________________________________________________________________
activation_45 (Activation) (None, 17, 17, 160) 0 batch_normalization_45[0][0]
__________________________________________________________________________________________________
conv2d_41 (Conv2D) (None, 17, 17, 160) 122880 mixed4[0][0]
__________________________________________________________________________________________________
conv2d_46 (Conv2D) (None, 17, 17, 160) 179200 activation_45[0][0]
__________________________________________________________________________________________________
batch_normalization_41 (BatchNo (None, 17, 17, 160) 480 conv2d_41[0][0]
__________________________________________________________________________________________________
batch_normalization_46 (BatchNo (None, 17, 17, 160) 480 conv2d_46[0][0]
__________________________________________________________________________________________________
activation_41 (Activation) (None, 17, 17, 160) 0 batch_normalization_41[0][0]
__________________________________________________________________________________________________
activation_46 (Activation) (None, 17, 17, 160) 0 batch_normalization_46[0][0]
__________________________________________________________________________________________________
conv2d_42 (Conv2D) (None, 17, 17, 160) 179200 activation_41[0][0]
__________________________________________________________________________________________________
conv2d_47 (Conv2D) (None, 17, 17, 160) 179200 activation_46[0][0]
__________________________________________________________________________________________________
batch_normalization_42 (BatchNo (None, 17, 17, 160) 480 conv2d_42[0][0]
__________________________________________________________________________________________________
batch_normalization_47 (BatchNo (None, 17, 17, 160) 480 conv2d_47[0][0]
__________________________________________________________________________________________________
activation_42 (Activation) (None, 17, 17, 160) 0 batch_normalization_42[0][0]
__________________________________________________________________________________________________
activation_47 (Activation) (None, 17, 17, 160) 0 batch_normalization_47[0][0]
__________________________________________________________________________________________________
average_pooling2d_4 (AveragePoo (None, 17, 17, 768) 0 mixed4[0][0]
__________________________________________________________________________________________________
conv2d_40 (Conv2D) (None, 17, 17, 192) 147456 mixed4[0][0]
__________________________________________________________________________________________________
conv2d_43 (Conv2D) (None, 17, 17, 192) 215040 activation_42[0][0]
__________________________________________________________________________________________________
conv2d_48 (Conv2D) (None, 17, 17, 192) 215040 activation_47[0][0]
__________________________________________________________________________________________________
conv2d_49 (Conv2D) (None, 17, 17, 192) 147456 average_pooling2d_4[0][0]
__________________________________________________________________________________________________
batch_normalization_40 (BatchNo (None, 17, 17, 192) 576 conv2d_40[0][0]
__________________________________________________________________________________________________
batch_normalization_43 (BatchNo (None, 17, 17, 192) 576 conv2d_43[0][0]
__________________________________________________________________________________________________
batch_normalization_48 (BatchNo (None, 17, 17, 192) 576 conv2d_48[0][0]
__________________________________________________________________________________________________
batch_normalization_49 (BatchNo (None, 17, 17, 192) 576 conv2d_49[0][0]
__________________________________________________________________________________________________
activation_40 (Activation) (None, 17, 17, 192) 0 batch_normalization_40[0][0]
__________________________________________________________________________________________________
activation_43 (Activation) (None, 17, 17, 192) 0 batch_normalization_43[0][0]
__________________________________________________________________________________________________
activation_48 (Activation) (None, 17, 17, 192) 0 batch_normalization_48[0][0]
__________________________________________________________________________________________________
activation_49 (Activation) (None, 17, 17, 192) 0 batch_normalization_49[0][0]
__________________________________________________________________________________________________
mixed5 (Concatenate) (None, 17, 17, 768) 0 activation_40[0][0]
activation_43[0][0]
activation_48[0][0]
activation_49[0][0]
__________________________________________________________________________________________________
conv2d_54 (Conv2D) (None, 17, 17, 160) 122880 mixed5[0][0]
__________________________________________________________________________________________________
batch_normalization_54 (BatchNo (None, 17, 17, 160) 480 conv2d_54[0][0]
__________________________________________________________________________________________________
activation_54 (Activation) (None, 17, 17, 160) 0 batch_normalization_54[0][0]
__________________________________________________________________________________________________
conv2d_55 (Conv2D) (None, 17, 17, 160) 179200 activation_54[0][0]
__________________________________________________________________________________________________
batch_normalization_55 (BatchNo (None, 17, 17, 160) 480 conv2d_55[0][0]
__________________________________________________________________________________________________
activation_55 (Activation) (None, 17, 17, 160) 0 batch_normalization_55[0][0]
__________________________________________________________________________________________________
conv2d_51 (Conv2D) (None, 17, 17, 160) 122880 mixed5[0][0]
__________________________________________________________________________________________________
conv2d_56 (Conv2D) (None, 17, 17, 160) 179200 activation_55[0][0]
__________________________________________________________________________________________________
batch_normalization_51 (BatchNo (None, 17, 17, 160) 480 conv2d_51[0][0]
__________________________________________________________________________________________________
batch_normalization_56 (BatchNo (None, 17, 17, 160) 480 conv2d_56[0][0]
__________________________________________________________________________________________________
activation_51 (Activation) (None, 17, 17, 160) 0 batch_normalization_51[0][0]
__________________________________________________________________________________________________
activation_56 (Activation) (None, 17, 17, 160) 0 batch_normalization_56[0][0]
__________________________________________________________________________________________________
conv2d_52 (Conv2D) (None, 17, 17, 160) 179200 activation_51[0][0]
__________________________________________________________________________________________________
conv2d_57 (Conv2D) (None, 17, 17, 160) 179200 activation_56[0][0]
__________________________________________________________________________________________________
batch_normalization_52 (BatchNo (None, 17, 17, 160) 480 conv2d_52[0][0]
__________________________________________________________________________________________________
batch_normalization_57 (BatchNo (None, 17, 17, 160) 480 conv2d_57[0][0]
__________________________________________________________________________________________________
activation_52 (Activation) (None, 17, 17, 160) 0 batch_normalization_52[0][0]
__________________________________________________________________________________________________
activation_57 (Activation) (None, 17, 17, 160) 0 batch_normalization_57[0][0]
__________________________________________________________________________________________________
average_pooling2d_5 (AveragePoo (None, 17, 17, 768) 0 mixed5[0][0]
__________________________________________________________________________________________________
conv2d_50 (Conv2D) (None, 17, 17, 192) 147456 mixed5[0][0]
__________________________________________________________________________________________________
conv2d_53 (Conv2D) (None, 17, 17, 192) 215040 activation_52[0][0]
__________________________________________________________________________________________________
conv2d_58 (Conv2D) (None, 17, 17, 192) 215040 activation_57[0][0]
__________________________________________________________________________________________________
conv2d_59 (Conv2D) (None, 17, 17, 192) 147456 average_pooling2d_5[0][0]
__________________________________________________________________________________________________
batch_normalization_50 (BatchNo (None, 17, 17, 192) 576 conv2d_50[0][0]
__________________________________________________________________________________________________
batch_normalization_53 (BatchNo (None, 17, 17, 192) 576 conv2d_53[0][0]
__________________________________________________________________________________________________
batch_normalization_58 (BatchNo (None, 17, 17, 192) 576 conv2d_58[0][0]
__________________________________________________________________________________________________
batch_normalization_59 (BatchNo (None, 17, 17, 192) 576 conv2d_59[0][0]
__________________________________________________________________________________________________
activation_50 (Activation) (None, 17, 17, 192) 0 batch_normalization_50[0][0]
__________________________________________________________________________________________________
activation_53 (Activation) (None, 17, 17, 192) 0 batch_normalization_53[0][0]
__________________________________________________________________________________________________
activation_58 (Activation) (None, 17, 17, 192) 0 batch_normalization_58[0][0]
__________________________________________________________________________________________________
activation_59 (Activation) (None, 17, 17, 192) 0 batch_normalization_59[0][0]
__________________________________________________________________________________________________
mixed6 (Concatenate) (None, 17, 17, 768) 0 activation_50[0][0]
activation_53[0][0]
activation_58[0][0]
activation_59[0][0]
__________________________________________________________________________________________________
conv2d_64 (Conv2D) (None, 17, 17, 192) 147456 mixed6[0][0]
__________________________________________________________________________________________________
batch_normalization_64 (BatchNo (None, 17, 17, 192) 576 conv2d_64[0][0]
__________________________________________________________________________________________________
activation_64 (Activation) (None, 17, 17, 192) 0 batch_normalization_64[0][0]
__________________________________________________________________________________________________
conv2d_65 (Conv2D) (None, 17, 17, 192) 258048 activation_64[0][0]
__________________________________________________________________________________________________
batch_normalization_65 (BatchNo (None, 17, 17, 192) 576 conv2d_65[0][0]
__________________________________________________________________________________________________
activation_65 (Activation) (None, 17, 17, 192) 0 batch_normalization_65[0][0]
__________________________________________________________________________________________________
conv2d_61 (Conv2D) (None, 17, 17, 192) 147456 mixed6[0][0]
__________________________________________________________________________________________________
conv2d_66 (Conv2D) (None, 17, 17, 192) 258048 activation_65[0][0]
__________________________________________________________________________________________________
batch_normalization_61 (BatchNo (None, 17, 17, 192) 576 conv2d_61[0][0]
__________________________________________________________________________________________________
batch_normalization_66 (BatchNo (None, 17, 17, 192) 576 conv2d_66[0][0]
__________________________________________________________________________________________________
activation_61 (Activation) (None, 17, 17, 192) 0 batch_normalization_61[0][0]
__________________________________________________________________________________________________
activation_66 (Activation) (None, 17, 17, 192) 0 batch_normalization_66[0][0]
__________________________________________________________________________________________________
conv2d_62 (Conv2D) (None, 17, 17, 192) 258048 activation_61[0][0]
__________________________________________________________________________________________________
conv2d_67 (Conv2D) (None, 17, 17, 192) 258048 activation_66[0][0]
__________________________________________________________________________________________________
batch_normalization_62 (BatchNo (None, 17, 17, 192) 576 conv2d_62[0][0]
__________________________________________________________________________________________________
batch_normalization_67 (BatchNo (None, 17, 17, 192) 576 conv2d_67[0][0]
__________________________________________________________________________________________________
activation_62 (Activation) (None, 17, 17, 192) 0 batch_normalization_62[0][0]
__________________________________________________________________________________________________
activation_67 (Activation) (None, 17, 17, 192) 0 batch_normalization_67[0][0]
__________________________________________________________________________________________________
average_pooling2d_6 (AveragePoo (None, 17, 17, 768) 0 mixed6[0][0]
__________________________________________________________________________________________________
conv2d_60 (Conv2D) (None, 17, 17, 192) 147456 mixed6[0][0]
__________________________________________________________________________________________________
conv2d_63 (Conv2D) (None, 17, 17, 192) 258048 activation_62[0][0]
__________________________________________________________________________________________________
conv2d_68 (Conv2D) (None, 17, 17, 192) 258048 activation_67[0][0]
__________________________________________________________________________________________________
conv2d_69 (Conv2D) (None, 17, 17, 192) 147456 average_pooling2d_6[0][0]
__________________________________________________________________________________________________
batch_normalization_60 (BatchNo (None, 17, 17, 192) 576 conv2d_60[0][0]
__________________________________________________________________________________________________
batch_normalization_63 (BatchNo (None, 17, 17, 192) 576 conv2d_63[0][0]
__________________________________________________________________________________________________
batch_normalization_68 (BatchNo (None, 17, 17, 192) 576 conv2d_68[0][0]
__________________________________________________________________________________________________
batch_normalization_69 (BatchNo (None, 17, 17, 192) 576 conv2d_69[0][0]
__________________________________________________________________________________________________
activation_60 (Activation) (None, 17, 17, 192) 0 batch_normalization_60[0][0]
__________________________________________________________________________________________________
activation_63 (Activation) (None, 17, 17, 192) 0 batch_normalization_63[0][0]
__________________________________________________________________________________________________
activation_68 (Activation) (None, 17, 17, 192) 0 batch_normalization_68[0][0]
__________________________________________________________________________________________________
activation_69 (Activation) (None, 17, 17, 192) 0 batch_normalization_69[0][0]
__________________________________________________________________________________________________
mixed7 (Concatenate) (None, 17, 17, 768) 0 activation_60[0][0]
activation_63[0][0]
activation_68[0][0]
activation_69[0][0]
__________________________________________________________________________________________________
conv2d_72 (Conv2D) (None, 17, 17, 192) 147456 mixed7[0][0]
__________________________________________________________________________________________________
batch_normalization_72 (BatchNo (None, 17, 17, 192) 576 conv2d_72[0][0]
__________________________________________________________________________________________________
activation_72 (Activation) (None, 17, 17, 192) 0 batch_normalization_72[0][0]
__________________________________________________________________________________________________
conv2d_73 (Conv2D) (None, 17, 17, 192) 258048 activation_72[0][0]
__________________________________________________________________________________________________
batch_normalization_73 (BatchNo (None, 17, 17, 192) 576 conv2d_73[0][0]
__________________________________________________________________________________________________
activation_73 (Activation) (None, 17, 17, 192) 0 batch_normalization_73[0][0]
__________________________________________________________________________________________________
conv2d_70 (Conv2D) (None, 17, 17, 192) 147456 mixed7[0][0]
__________________________________________________________________________________________________
conv2d_74 (Conv2D) (None, 17, 17, 192) 258048 activation_73[0][0]
__________________________________________________________________________________________________
batch_normalization_70 (BatchNo (None, 17, 17, 192) 576 conv2d_70[0][0]
__________________________________________________________________________________________________
batch_normalization_74 (BatchNo (None, 17, 17, 192) 576 conv2d_74[0][0]
__________________________________________________________________________________________________
activation_70 (Activation) (None, 17, 17, 192) 0 batch_normalization_70[0][0]
__________________________________________________________________________________________________
activation_74 (Activation) (None, 17, 17, 192) 0 batch_normalization_74[0][0]
__________________________________________________________________________________________________
conv2d_71 (Conv2D) (None, 8, 8, 320) 552960 activation_70[0][0]
__________________________________________________________________________________________________
conv2d_75 (Conv2D) (None, 8, 8, 192) 331776 activation_74[0][0]
__________________________________________________________________________________________________
batch_normalization_71 (BatchNo (None, 8, 8, 320) 960 conv2d_71[0][0]
__________________________________________________________________________________________________
batch_normalization_75 (BatchNo (None, 8, 8, 192) 576 conv2d_75[0][0]
__________________________________________________________________________________________________
activation_71 (Activation) (None, 8, 8, 320) 0 batch_normalization_71[0][0]
__________________________________________________________________________________________________
activation_75 (Activation) (None, 8, 8, 192) 0 batch_normalization_75[0][0]
__________________________________________________________________________________________________
max_pooling2d_3 (MaxPooling2D) (None, 8, 8, 768) 0 mixed7[0][0]
__________________________________________________________________________________________________
mixed8 (Concatenate) (None, 8, 8, 1280) 0 activation_71[0][0]
activation_75[0][0]
max_pooling2d_3[0][0]
__________________________________________________________________________________________________
conv2d_80 (Conv2D) (None, 8, 8, 448) 573440 mixed8[0][0]
__________________________________________________________________________________________________
batch_normalization_80 (BatchNo (None, 8, 8, 448) 1344 conv2d_80[0][0]
__________________________________________________________________________________________________
activation_80 (Activation) (None, 8, 8, 448) 0 batch_normalization_80[0][0]
__________________________________________________________________________________________________
conv2d_77 (Conv2D) (None, 8, 8, 384) 491520 mixed8[0][0]
__________________________________________________________________________________________________
conv2d_81 (Conv2D) (None, 8, 8, 384) 1548288 activation_80[0][0]
__________________________________________________________________________________________________
batch_normalization_77 (BatchNo (None, 8, 8, 384) 1152 conv2d_77[0][0]
__________________________________________________________________________________________________
batch_normalization_81 (BatchNo (None, 8, 8, 384) 1152 conv2d_81[0][0]
__________________________________________________________________________________________________
activation_77 (Activation) (None, 8, 8, 384) 0 batch_normalization_77[0][0]
__________________________________________________________________________________________________
activation_81 (Activation) (None, 8, 8, 384) 0 batch_normalization_81[0][0]
__________________________________________________________________________________________________
conv2d_78 (Conv2D) (None, 8, 8, 384) 442368 activation_77[0][0]
__________________________________________________________________________________________________
conv2d_79 (Conv2D) (None, 8, 8, 384) 442368 activation_77[0][0]
__________________________________________________________________________________________________
conv2d_82 (Conv2D) (None, 8, 8, 384) 442368 activation_81[0][0]
__________________________________________________________________________________________________
conv2d_83 (Conv2D) (None, 8, 8, 384) 442368 activation_81[0][0]
__________________________________________________________________________________________________
average_pooling2d_7 (AveragePoo (None, 8, 8, 1280) 0 mixed8[0][0]
__________________________________________________________________________________________________
conv2d_76 (Conv2D) (None, 8, 8, 320) 409600 mixed8[0][0]
__________________________________________________________________________________________________
batch_normalization_78 (BatchNo (None, 8, 8, 384) 1152 conv2d_78[0][0]
__________________________________________________________________________________________________
batch_normalization_79 (BatchNo (None, 8, 8, 384) 1152 conv2d_79[0][0]
__________________________________________________________________________________________________
batch_normalization_82 (BatchNo (None, 8, 8, 384) 1152 conv2d_82[0][0]
__________________________________________________________________________________________________
batch_normalization_83 (BatchNo (None, 8, 8, 384) 1152 conv2d_83[0][0]
__________________________________________________________________________________________________
conv2d_84 (Conv2D) (None, 8, 8, 192) 245760 average_pooling2d_7[0][0]
__________________________________________________________________________________________________
batch_normalization_76 (BatchNo (None, 8, 8, 320) 960 conv2d_76[0][0]
__________________________________________________________________________________________________
activation_78 (Activation) (None, 8, 8, 384) 0 batch_normalization_78[0][0]
__________________________________________________________________________________________________
activation_79 (Activation) (None, 8, 8, 384) 0 batch_normalization_79[0][0]
__________________________________________________________________________________________________
activation_82 (Activation) (None, 8, 8, 384) 0 batch_normalization_82[0][0]
__________________________________________________________________________________________________
activation_83 (Activation) (None, 8, 8, 384) 0 batch_normalization_83[0][0]
__________________________________________________________________________________________________
batch_normalization_84 (BatchNo (None, 8, 8, 192) 576 conv2d_84[0][0]
__________________________________________________________________________________________________
activation_76 (Activation) (None, 8, 8, 320) 0 batch_normalization_76[0][0]
__________________________________________________________________________________________________
mixed9_0 (Concatenate) (None, 8, 8, 768) 0 activation_78[0][0]
activation_79[0][0]
__________________________________________________________________________________________________
concatenate (Concatenate) (None, 8, 8, 768) 0 activation_82[0][0]
activation_83[0][0]
__________________________________________________________________________________________________
activation_84 (Activation) (None, 8, 8, 192) 0 batch_normalization_84[0][0]
__________________________________________________________________________________________________
mixed9 (Concatenate) (None, 8, 8, 2048) 0 activation_76[0][0]
mixed9_0[0][0]
concatenate[0][0]
activation_84[0][0]
__________________________________________________________________________________________________
conv2d_89 (Conv2D) (None, 8, 8, 448) 917504 mixed9[0][0]
__________________________________________________________________________________________________
batch_normalization_89 (BatchNo (None, 8, 8, 448) 1344 conv2d_89[0][0]
__________________________________________________________________________________________________
activation_89 (Activation) (None, 8, 8, 448) 0 batch_normalization_89[0][0]
__________________________________________________________________________________________________
conv2d_86 (Conv2D) (None, 8, 8, 384) 786432 mixed9[0][0]
__________________________________________________________________________________________________
conv2d_90 (Conv2D) (None, 8, 8, 384) 1548288 activation_89[0][0]
__________________________________________________________________________________________________
batch_normalization_86 (BatchNo (None, 8, 8, 384) 1152 conv2d_86[0][0]
__________________________________________________________________________________________________
batch_normalization_90 (BatchNo (None, 8, 8, 384) 1152 conv2d_90[0][0]
__________________________________________________________________________________________________
activation_86 (Activation) (None, 8, 8, 384) 0 batch_normalization_86[0][0]
__________________________________________________________________________________________________
activation_90 (Activation) (None, 8, 8, 384) 0 batch_normalization_90[0][0]
__________________________________________________________________________________________________
conv2d_87 (Conv2D) (None, 8, 8, 384) 442368 activation_86[0][0]
__________________________________________________________________________________________________
conv2d_88 (Conv2D) (None, 8, 8, 384) 442368 activation_86[0][0]
__________________________________________________________________________________________________
conv2d_91 (Conv2D) (None, 8, 8, 384) 442368 activation_90[0][0]
__________________________________________________________________________________________________
conv2d_92 (Conv2D) (None, 8, 8, 384) 442368 activation_90[0][0]
__________________________________________________________________________________________________
average_pooling2d_8 (AveragePoo (None, 8, 8, 2048) 0 mixed9[0][0]
__________________________________________________________________________________________________
conv2d_85 (Conv2D) (None, 8, 8, 320) 655360 mixed9[0][0]
__________________________________________________________________________________________________
batch_normalization_87 (BatchNo (None, 8, 8, 384) 1152 conv2d_87[0][0]
__________________________________________________________________________________________________
batch_normalization_88 (BatchNo (None, 8, 8, 384) 1152 conv2d_88[0][0]
__________________________________________________________________________________________________
batch_normalization_91 (BatchNo (None, 8, 8, 384) 1152 conv2d_91[0][0]
__________________________________________________________________________________________________
batch_normalization_92 (BatchNo (None, 8, 8, 384) 1152 conv2d_92[0][0]
__________________________________________________________________________________________________
conv2d_93 (Conv2D) (None, 8, 8, 192) 393216 average_pooling2d_8[0][0]
__________________________________________________________________________________________________
batch_normalization_85 (BatchNo (None, 8, 8, 320) 960 conv2d_85[0][0]
__________________________________________________________________________________________________
activation_87 (Activation) (None, 8, 8, 384) 0 batch_normalization_87[0][0]
__________________________________________________________________________________________________
activation_88 (Activation) (None, 8, 8, 384) 0 batch_normalization_88[0][0]
__________________________________________________________________________________________________
activation_91 (Activation) (None, 8, 8, 384) 0 batch_normalization_91[0][0]
__________________________________________________________________________________________________
activation_92 (Activation) (None, 8, 8, 384) 0 batch_normalization_92[0][0]
__________________________________________________________________________________________________
batch_normalization_93 (BatchNo (None, 8, 8, 192) 576 conv2d_93[0][0]
__________________________________________________________________________________________________
activation_85 (Activation) (None, 8, 8, 320) 0 batch_normalization_85[0][0]
__________________________________________________________________________________________________
mixed9_1 (Concatenate) (None, 8, 8, 768) 0 activation_87[0][0]
activation_88[0][0]
__________________________________________________________________________________________________
concatenate_1 (Concatenate) (None, 8, 8, 768) 0 activation_91[0][0]
activation_92[0][0]
__________________________________________________________________________________________________
activation_93 (Activation) (None, 8, 8, 192) 0 batch_normalization_93[0][0]
__________________________________________________________________________________________________
mixed10 (Concatenate) (None, 8, 8, 2048) 0 activation_85[0][0]
mixed9_1[0][0]
concatenate_1[0][0]
activation_93[0][0]
==================================================================================================
Total params: 21,802,784
Trainable params: 0
Non-trainable params: 21,802,784
__________________________________________________________________________________________________
None
Create the Output Layers
x = layers.GlobalAveragePooling2D()(base_model.output)
x = layers.Dense(1024, activation="relu")(x)
x = layers.Dropout(0.2)(x)
x = layers.Dense(1, activation="sigmoid")(x)
Now build the model combining the pre-built layer with a Dense layer (that we're going to train). Since we only have two classes the activation function is the sigmoid.
model = tensorflow.keras.Model(
base_model.input,
x,
)
Compile the Model
model.compile(optimizer = RMSprop(lr=0.0001),
loss = 'binary_crossentropy',
metrics = ['acc'])
Train the Model
A Model Saver
best_model = MODELS/"inception_transfer.hdf5"
checkpoint = tensorflow.keras.callbacks.ModelCheckpoint(
str(best_model), monitor="val_acc", verbose=1,
save_best_only=True)
A good Enough Callback
class GoodEnough(tensorflow.keras.callbacks.Callback):
def on_epoch_end(self, epoch, logs={}):
if logs.get('acc') > 0.999:
print("\nReached 99.9% accuracy so cancelling training!")
self.model.stop_training = True
A Data Generator
This bundles up the steps to build the data generator.
class Data:
"""creates the data generators
Args:
path: path to the images
validation_split: fraction that goes to the validation set
batch_size: size for the batches in the epochs
"""
def __init__(self, path: str, validation_split: float=0.2,
batch_size: int=20) -> None:
self.path = path
self.validation_split = validation_split
self.batch_size = batch_size
self._data_generator = None
self._testing_data_generator = None
self._training_generator = None
self._validation_generator = None
return
@property
def data_generator(self) -> ImageDataGenerator:
"""The data generator for training and validation"""
if self._data_generator is None:
self._data_generator = ImageDataGenerator(
rescale=1/255,
rotation_range=40,
width_shift_range=0.2,
height_shift_range=0.2,
horizontal_flip=True,
shear_range=0.2,
zoom_range=0.2,
fill_mode="nearest",
validation_split=self.validation_split)
return self._data_generator
@property
def training_generator(self):
"""The training data generator"""
if self._training_generator is None:
self._training_generator = (self.data_generator
.flow_from_directory)(
self.path,
batch_size=self.batch_size,
class_mode="binary",
target_size=(300, 300),
subset="training",
)
return self._training_generator
@property
def validation_generator(self):
"""the validation data generator"""
if self._validation_generator is None:
self._validation_generator = (self.data_generator
.flow_from_directory)(
self.path,
batch_size=self.batch_size,
class_mode="binary",
target_size = (300, 300),
subset="validation",
)
return self._validation_generator
def __str__(self) -> str:
return (f"(Data) - Path: {self.path}, "
f"Validation Split: {self.validation_split},"
f"Batch Size: {self.batch_size}")
A Model Builder
class Network:
"""The model to categorize the images
Args:
model: model to train
path: path to the training data
epochs: number of epochs to train
batch_size: size of the batches for each epoch
convolution_layers: layers of cnn/max-pooling
callbacks: things to stop the training
set_steps: whether to set the training steps-per-epoch
"""
def __init__(self, model, path: str, epochs: int=15,
batch_size: int=128, convolution_layers: int=3,
set_steps: bool=True,
callbacks: list=None) -> None:
self.model = model
self.path = path
self.epochs = epochs
self.batch_size = batch_size
self.convolution_layers = convolution_layers
self.set_steps = set_steps
self.callbacks = callbacks
self._data = None
self._model = None
self.history = None
return
@property
def data(self) -> Data:
"""The data generator builder"""
if self._data is None:
self._data = Data(self.path, batch_size=self.batch_size)
return self._data
def summary(self) -> None:
"""Prints the model summary"""
print(self.model.summary())
return
def train(self) -> None:
"""Trains the model"""
callbacks = self.callbacks if self.callbacks else []
arguments = dict(
generator=self.data.training_generator,
validation_data=self.data.validation_generator,
epochs = self.epochs,
callbacks = callbacks,
verbose=2,
)
if self.set_steps:
arguments["steps_per_epoch"] = int(
self.data.training_generator.samples/self.batch_size)
arguments["validation_steps"] = int(
self.data.validation_generator.samples/self.batch_size)
self.history = self.model.fit_generator(**arguments)
return
def __str__(self) -> str:
return (f"(Network) - \nPath: {self.path}\n Epochs: {self.epochs}\n "
f"Batch Size: {self.batch_size}\n Callbacks: {self.callbacks}\n"
f"Data: {self.data}\n"
f"Callbacks: {self.callbacks}")
Train It
good_enough = GoodEnough()
network = Network(model, Path(OUTPUT).expanduser(),
set_steps = True,
epochs = 40,
callbacks=[checkpoint, good_enough],
batch_size=1)
with TIMER:
network.train()
2019-08-03 19:28:04,102 graeae.timers.timer start: Started: 2019-08-03 19:28:04.102954 I0803 19:28:04.102986 139918777980736 timer.py:70] Started: 2019-08-03 19:28:04.102954 Found 20000 images belonging to 2 classes. Found 5000 images belonging to 2 classes. Epoch 1/10 Epoch 00001: val_acc improved from -inf to 0.43660, saving model to /home/athena/models/dogs-vs-cats/inception_transfer.hdf5 20000/20000 - 615s - loss: 0.7032 - acc: 0.4977 - val_loss: 0.8069 - val_acc: 0.4366 Epoch 2/10 Epoch 00002: val_acc improved from 0.43660 to 0.43780, saving model to /home/athena/models/dogs-vs-cats/inception_transfer.hdf5 20000/20000 - 631s - loss: 0.6933 - acc: 0.5049 - val_loss: 0.7958 - val_acc: 0.4378 Epoch 3/10 Epoch 00003: val_acc did not improve from 0.43780 20000/20000 - 670s - loss: 0.6932 - acc: 0.4990 - val_loss: 0.8142 - val_acc: 0.4230 Epoch 4/10 Epoch 00004: val_acc improved from 0.43780 to 0.45020, saving model to /home/athena/models/dogs-vs-cats/inception_transfer.hdf5 20000/20000 - 666s - loss: 0.6932 - acc: 0.4990 - val_loss: 0.7856 - val_acc: 0.4502 Epoch 5/10 Epoch 00005: val_acc did not improve from 0.45020 20000/20000 - 636s - loss: 0.6932 - acc: 0.4983 - val_loss: 0.7982 - val_acc: 0.4312 Epoch 6/10 Epoch 00006: val_acc did not improve from 0.45020 20000/20000 - 618s - loss: 0.6932 - acc: 0.4999 - val_loss: 0.8018 - val_acc: 0.4326 Epoch 7/10 Epoch 00007: val_acc did not improve from 0.45020 20000/20000 - 614s - loss: 0.6932 - acc: 0.4999 - val_loss: 0.7870 - val_acc: 0.4484 Epoch 8/10 Epoch 00008: val_acc improved from 0.45020 to 0.45660, saving model to /home/athena/models/dogs-vs-cats/inception_transfer.hdf5 20000/20000 - 607s - loss: 0.6932 - acc: 0.4981 - val_loss: 0.7773 - val_acc: 0.4566 Epoch 9/10 Epoch 00009: val_acc did not improve from 0.45660 20000/20000 - 608s - loss: 0.6932 - acc: 0.4891 - val_loss: 0.7811 - val_acc: 0.4414 Epoch 10/10 Epoch 00010: val_acc did not improve from 0.45660 20000/20000 - 619s - loss: 0.6932 - acc: 0.5010 - val_loss: 0.7878 - val_acc: 0.4474 2019-08-03 21:12:49,142 graeae.timers.timer end: Ended: 2019-08-03 21:12:49.142478 I0803 21:12:49.142507 139918777980736 timer.py:77] Ended: 2019-08-03 21:12:49.142478 2019-08-03 21:12:49,143 graeae.timers.timer end: Elapsed: 1:44:45.039524 I0803 21:12:49.143225 139918777980736 timer.py:78] Elapsed: 1:44:45.039524
End
Sources
- Horses Or Humans Dataset. Moroney Laurence. Feb 2019. url: http://laurencemoroney.com/horses-or-humans-dataset
Raw
#+begin_comment import os import tensorflow as tf from tensorflow.keras import layers from tensorflow.keras import Model >
Epoch 00002: val_acc improved from 0.88780 to 0.89268, saving model to /home/athena/models/horses-vs-humans/inception_transfer.hdf5 822/822 - 61s - loss: 0.7190 - acc: 0.5255 - val_loss: 0.5419 - val_acc: 0.8927 Epoch 3/40
Epoch 00003: val_acc improved from 0.89268 to 0.92195, saving model to /home/athena/models/horses-vs-humans/inception_transfer.hdf5 822/822 - 61s - loss: 0.7102 - acc: 0.5170 - val_loss: 0.5290 - val_acc: 0.9220 Epoch 4/40
Epoch 00004: val_acc did not improve from 0.92195 822/822 - 60s - loss: 0.7103 - acc: 0.5097 - val_loss: 0.5357 - val_acc: 0.8146 Epoch 5/40
Epoch 00005: val_acc did not improve from 0.92195 822/822 - 60s - loss: 0.7051 - acc: 0.5012 - val_loss: 0.5330 - val_acc: 0.6780 Epoch 6/40
Epoch 00006: val_acc did not improve from 0.92195 822/822 - 64s - loss: 0.7006 - acc: 0.5012 - val_loss: 0.5969 - val_acc: 0.5317 Epoch 7/40
Epoch 00007: val_acc did not improve from 0.92195 822/822 - 63s - loss: 0.7009 - acc: 0.5109 - val_loss: 0.5356 - val_acc: 0.9122 Epoch 8/40
Epoch 00008: val_acc did not improve from 0.92195 822/822 - 62s - loss: 0.7025 - acc: 0.4878 - val_loss: 0.5103 - val_acc: 0.9073 Epoch 9/40
Epoch 00009: val_acc did not improve from 0.92195 822/822 - 60s - loss: 0.6972 - acc: 0.5207 - val_loss: 0.5321 - val_acc: 0.7561 Epoch 10/40
Epoch 00010: val_acc did not improve from 0.92195 822/822 - 61s - loss: 0.6946 - acc: 0.5316 - val_loss: 0.5102 - val_acc: 0.9220 Epoch 11/40
Epoch 00011: val_acc did not improve from 0.92195 822/822 - 62s - loss: 0.6966 - acc: 0.5365 - val_loss: 0.5149 - val_acc: 0.8488 Epoch 12/40
Epoch 00012: val_acc did not improve from 0.92195 822/822 - 62s - loss: 0.6981 - acc: 0.5073 - val_loss: 0.5266 - val_acc: 0.8293 Epoch 13/40
Epoch 00013: val_acc did not improve from 0.92195 822/822 - 62s - loss: 0.6949 - acc: 0.5182 - val_loss: 0.5046 - val_acc: 0.8780 Epoch 14/40
Epoch 00014: val_acc improved from 0.92195 to 0.95122, saving model to /home/athena/models/horses-vs-humans/inception_transfer.hdf5 822/822 - 62s - loss: 0.6957 - acc: 0.5170 - val_loss: 0.4872 - val_acc: 0.9512 Epoch 15/40
Epoch 00015: val_acc did not improve from 0.95122 822/822 - 61s - loss: 0.6944 - acc: 0.5049 - val_loss: 0.4904 - val_acc: 0.9366 Epoch 16/40
Epoch 00016: val_acc did not improve from 0.95122 822/822 - 60s - loss: 0.6920 - acc: 0.5158 - val_loss: 0.5201 - val_acc: 0.7463 Epoch 17/40
Epoch 00017: val_acc did not improve from 0.95122 822/822 - 60s - loss: 0.6951 - acc: 0.4988 - val_loss: 0.4872 - val_acc: 0.8488 Epoch 18/40
Epoch 00018: val_acc improved from 0.95122 to 0.97073, saving model to /home/athena/models/horses-vs-humans/inception_transfer.hdf5 822/822 - 61s - loss: 0.6927 - acc: 0.5377 - val_loss: 0.4889 - val_acc: 0.9707 Epoch 19/40
Epoch 00019: val_acc did not improve from 0.97073 822/822 - 63s - loss: 0.6900 - acc: 0.5255 - val_loss: 0.4912 - val_acc: 0.7854 Epoch 20/40
Epoch 00020: val_acc did not improve from 0.97073 822/822 - 64s - loss: 0.6927 - acc: 0.5243 - val_loss: 0.4651 - val_acc: 0.8878 Epoch 21/40
Epoch 00021: val_acc did not improve from 0.97073 822/822 - 64s - loss: 0.6914 - acc: 0.5304 - val_loss: 0.4368 - val_acc: 0.9659 Epoch 22/40
Epoch 00022: val_acc improved from 0.97073 to 0.97561, saving model to /home/athena/models/horses-vs-humans/inception_transfer.hdf5 822/822 - 65s - loss: 0.6881 - acc: 0.5341 - val_loss: 0.4350 - val_acc: 0.9756 Epoch 23/40
Epoch 00023: val_acc did not improve from 0.97561 822/822 - 62s - loss: 0.6914 - acc: 0.5401 - val_loss: 0.4421 - val_acc: 0.8439 Epoch 24/40
Epoch 00024: val_acc improved from 0.97561 to 0.99024, saving model to /home/athena/models/horses-vs-humans/inception_transfer.hdf5 822/822 - 61s - loss: 0.6887 - acc: 0.5511 - val_loss: 0.3974 - val_acc: 0.9902 Epoch 25/40
Epoch 00025: val_acc did not improve from 0.99024 822/822 - 62s - loss: 0.6855 - acc: 0.5535 - val_loss: 0.3716 - val_acc: 0.9902 Epoch 26/40
Epoch 00026: val_acc did not improve from 0.99024 822/822 - 63s - loss: 0.6865 - acc: 0.5389 - val_loss: 0.3736 - val_acc: 0.9610 Epoch 27/40
Epoch 00027: val_acc did not improve from 0.99024 822/822 - 60s - loss: 0.6823 - acc: 0.5718 - val_loss: 0.3799 - val_acc: 0.9220 Epoch 28/40
Epoch 00028: val_acc did not improve from 0.99024 822/822 - 61s - loss: 0.6875 - acc: 0.5474 - val_loss: 0.3530 - val_acc: 0.9902 Epoch 29/40
Epoch 00029: val_acc did not improve from 0.99024 822/822 - 60s - loss: 0.6881 - acc: 0.5487 - val_loss: 0.3376 - val_acc: 0.9902 Epoch 30/40
Epoch 00030: val_acc did not improve from 0.99024 822/822 - 62s - loss: 0.6857 - acc: 0.5462 - val_loss: 0.3216 - val_acc: 0.9707 Epoch 31/40
Epoch 00031: val_acc did not improve from 0.99024 822/822 - 62s - loss: 0.6847 - acc: 0.5450 - val_loss: 0.3025 - val_acc: 0.9902 Epoch 32/40
Epoch 00032: val_acc improved from 0.99024 to 0.99512, saving model to /home/athena/models/horses-vs-humans/inception_transfer.hdf5 822/822 - 64s - loss: 0.6821 - acc: 0.5535 - val_loss: 0.2852 - val_acc: 0.9951 Epoch 33/40
Epoch 00033: val_acc did not improve from 0.99512 822/822 - 62s - loss: 0.6793 - acc: 0.5669 - val_loss: 0.2617 - val_acc: 0.9854 Epoch 34/40
Epoch 00034: val_acc did not improve from 0.99512 822/822 - 60s - loss: 0.6772 - acc: 0.5937 - val_loss: 0.2565 - val_acc: 0.9707 Epoch 35/40
Epoch 00035: val_acc did not improve from 0.99512 822/822 - 61s - loss: 0.6766 - acc: 0.5803 - val_loss: 0.2190 - val_acc: 0.9951 Epoch 36/40
Epoch 00036: val_acc did not improve from 0.99512 822/822 - 63s - loss: 0.6726 - acc: 0.5937 - val_loss: 0.2423 - val_acc: 0.9463 Epoch 37/40
Epoch 00037: val_acc did not improve from 0.99512 822/822 - 61s - loss: 0.6735 - acc: 0.5669 - val_loss: 0.2106 - val_acc: 0.9902 Epoch 38/40
Epoch 00038: val_acc improved from 0.99512 to 1.00000, saving model to /home/athena/models/horses-vs-humans/inception_transfer.hdf5 822/822 - 61s - loss: 0.6718 - acc: 0.5949 - val_loss: 0.1868 - val_acc: 1.0000 Epoch 39/40
Epoch 00039: val_acc did not improve from 1.00000 822/822 - 60s - loss: 0.6647 - acc: 0.6119 - val_loss: 0.2140 - val_acc: 0.9610 Epoch 40/40
Epoch 00040: val_acc did not improve from 1.00000 822/822 - 60s - loss: 0.6671 - acc: 0.5815 - val_loss: 0.1823 - val_acc: 0.9707 2019-08-18 14:37:14,814 graeae.timers.timer end: Ended: 2019-08-18 14:37:14.814322 I0818 14:37:14.814355 139914340390720 timer.py:77] Ended: 2019-08-18 14:37:14.814322 2019-08-18 14:37:14,815 graeae.timers.timer end: Elapsed: 0:41:03.671258 I0818 14:37:14.815070 139914340390720 timer.py:78] Elapsed: 0:41:03.671258 #+end_example
So, we got 100% accuracy… that seems to be an overfitting. Also, why didn't the callback stop it? On further inspection I noticed that the training accuracy never gets to 100%, while the validation accuracy does… that seems odd.
history_ = pandas.DataFrame.from_dict(model.history.history)
history = history_.rename(columns={"loss": "Training Loss",
"acc": "Training Accuracy",
"val_loss": "Validation Loss",
"val_acc": "Validation Accuracy"})
plot = history.hvplot().opts(
title="Loss and Accuracy of the Horses Vs Humans Model",
height=800,
width=1000,
)
Embed(plot=plot, file_name="model_history")()
So this is a little weird - should Validation Accuracy start out that high? Maybe, since the original network is pre-trained… And why does the Validation Loss improve faster than the Training Loss?
Testing
I don't remember downloading this, but there's a separate folder called "validation" which I'm assuming has a different set of image files.
model = load_model(best_model)
target_size = (300, 300)
def predict(model, filename):
loaded = cv2.imread(str(filename))
x = cv2.resize(loaded, target_size)/255
x = numpy.reshape(x, (1, 300, 300, 3))
return model.predict(x)
path = Path("~/data/datasets/images/horse-or-human/validation/").expanduser()
target_size = (300, 300)
correct = 0
for index, filename in enumerate((path/"horses").iterdir()):
prediction = predict(model, filename)
correct += 0 if prediction[0] > 0.5 else 1
print(f"Fraction of horses correctly classified: {correct/(index + 1):.2f}")
Fraction of horses correctly classified: 0.99
correct = 0
for index, filename in enumerate((path/"humans").iterdir()):
prediction = predict(model, filename)
correct += 1 if prediction[0] > 0.5 else 0
print(f"Fraction of humans correctly classified: {correct/(index + 1):.2f}")
Fraction of humans correctly classified: 1.00
The testing images are slightly different in that they are on a white background, rather than a simulated background.
End
Sources
- Horses Or Humans Dataset. Moroney Laurence. Feb 2019. url: http://laurencemoroney.com/horses-or-humans-dataset