Групповой проект для класса. У нас есть модель, которая классифицирует собак по сравнению с кошками, но я пытаюсь (безуспешно) выяснить, как добавить некоторый код, который мог бы загрузить pi c через Flask, независимо от того, предсказывает ли модель кошку или собаку и
Начиная со строки 84, мы успешно обрабатываем данные тестирования и проверки, но я надеюсь добавить код, в который мы можем загрузить данные, а затем запустить модель на нескольких рисунках.
Я запускаю это в строке 164, но ничего не получаю. Надеясь на руководство по функции, где мы можем загрузить данные, а затем снова запустить модель. Любой совет ценится
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import PIL
import time
from datetime import timedelta
import os
import math
os.environ['KMP_DUPLICATE_LIB_OK']='True'
get_ipython().run_line_magic('matplotlib', 'inline')
import os
import zipfile
local_zip = 'cats_and_dogs_filtered.zip'
zip_ref = zipfile.ZipFile(local_zip, 'r')
zip_ref.extractall('final_home')
zip_ref.close()
# plot dog photos from the dogs vs cats dataset
from matplotlib import pyplot
from matplotlib.image import imread
# define location of dataset
folder = 'final_home/cats_and_dogs_filtered/train/dogs/'
# plot first few images
for i in range(9):
# define subplot
pyplot.subplot(330 + 1 + i)
# define filename
filename = folder + 'dog.' + str(i) + '.jpg'
# load image pixels
image = imread(filename)
# plot raw pixel data
pyplot.imshow(image)
# show the figure
pyplot.show()
# plot dog photos from the dogs vs cats dataset
from matplotlib import pyplot
from matplotlib.image import imread
# define location of dataset
folder = 'final_home/cats_and_dogs_filtered/train/cats/'
# plot first few images
for i in range(9):
# define subplot
pyplot.subplot(330 + 1 + i)
# define filename
filename = folder + 'cat.' + str(i) + '.jpg'
# load image pixels
image = imread(filename)
# plot raw pixel data
pyplot.imshow(image)
# show the figure
pyplot.show()
#import plaidml.keras
#plaidml.keras.install_backend()
import keras
#image augmentation artifically expand the size of training dataset by creating
#motivate version of images
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Model
from keras.layers import Input, Flatten, Dense, Dropout, GlobalAveragePooling2D
from keras.applications.mobilenet import MobileNet
import math
TRAIN_DATA_DIR = 'final_home/cats_and_dogs_filtered/train/'
VALIDATION_DATA_DIR = 'final_home/cats_and_dogs_filtered/validation/'
TRAIN_SAMPLES = 2000
VALIDATION_SAMPLES = 100
NUM_CLASSES=2
IMG_WIDTH, IMG_HEIGHT = 224, 224
BATCH_SIZE=64
train_datagen = ImageDataGenerator(rescale=1./255,
rotation_range=20,
width_shift_range=0.2,
height_shift_range=0.2,
zoom_range=0.2)
val_datagen = ImageDataGenerator(rescale=1./255)
train_generator = train_datagen.flow_from_directory(
TRAIN_DATA_DIR,
target_size=(IMG_WIDTH, IMG_HEIGHT),
batch_size=BATCH_SIZE,
shuffle=True,
seed=12345,
class_mode='categorical')
validation_generator = val_datagen.flow_from_directory(
VALIDATION_DATA_DIR,
target_size=(IMG_WIDTH, IMG_HEIGHT),
batch_size=BATCH_SIZE,
shuffle=False,
class_mode='categorical')
def model_maker():
base_model = MobileNet(include_top=False, input_shape = (IMG_WIDTH,IMG_HEIGHT,3))
for layer in base_model.layers[:]:
layer.trainable = False # Freeze the layers
input = Input(shape=(IMG_WIDTH, IMG_HEIGHT, 3))
custom_model = base_model(input)
custom_model = GlobalAveragePooling2D()(custom_model)
custom_model = Dense(64, activation='relu')(custom_model)
custom_model = Dropout(0.5)(custom_model)
predictions = Dense(NUM_CLASSES, activation='softmax')(custom_model)
return Model(inputs=input, outputs=predictions)
model = model_maker()
model.compile(loss='categorical_crossentropy',
optimizer= keras.optimizers.Adam(lr=0.001),
metrics=['acc'])
model.fit_generator(train_generator,
steps_per_epoch = math.ceil(float(TRAIN_SAMPLES) / BATCH_SIZE),
epochs=10,
validation_data = validation_generator,
validation_steps = math.ceil(float(VALIDATION_SAMPLES) / BATCH_SIZE))
model.save('final_home/model.h5')
#####################
##### VARIABLES #####
#####################
IMG_WIDTH, IMG_HEIGHT = 224, 224
VALIDATION_DATA_DIR = 'final_home/cats_and_dogs_filtered/validation/'
VALIDATION_BATCH_SIZE = 64
#####################
## DATA GENERATORS ##
#####################
validation_datagen = ImageDataGenerator(
rescale=1./255)
validation_generator = validation_datagen.flow_from_directory(
VALIDATION_DATA_DIR,
target_size=(IMG_WIDTH, IMG_HEIGHT),
batch_size=VALIDATION_BATCH_SIZE,
shuffle=False,
class_mode='categorical')
ground_truth = validation_generator.classes
### Test Data - Trying to be able to load test data from upload or whatever
#####################
##### VARIABLES #####
#####################
test_datagen = ImageDataGenerator(
rescale=1./255)
IMG_WIDTH, IMG_HEIGHT = 224, 224
TEST_DATA_DIR = 'final_home/cats_and_dogs_filtered/new/'
VALIDATION_BATCH_SIZE = 64
test_generator = test_datagen.flow_from_directory(
TEST_DATA_DIR,
target_size=(IMG_WIDTH, IMG_HEIGHT),
batch_size=16,
class_mode=None, # only data, no labels
shuffle=False) # keep data in same order as labels
probabilities = model.predict_generator(test_generator, steps=(1000/VALIDATION_BATCH_SIZE))
predictions = model.predict_generator(validation_generator, steps=(1000/VALIDATION_BATCH_SIZE))
# continued attemp to load test data
# probablities_table is a dict with index, prediction, ground truth
probablities_table = {}
for index, val in enumerate(probabilities):
#get argmax index
index_of_highest_probability = np.argmax(val)
value_of_highest_probability = val[index_of_highest_probability]
probablities_table[index] = [value_of_highest_probability, index_of_highest_probability,ground_truth[index]]
assert len(predictions) == len(ground_truth) == len(prediction_table)
# prediction_table is a dict with index, prediction, ground truth
prediction_table = {}
for index, val in enumerate(predictions):
#get argmax index
index_of_highest_probability = np.argmax(val)
value_of_highest_probability = val[index_of_highest_probability]
prediction_table[index] = [value_of_highest_probability, index_of_highest_probability,ground_truth[index]]
assert len(predictions) == len(ground_truth) == len(prediction_table)
# Helper function that finds images that are closest
# Input parameters:
# prediction_table: dictionary from the image index to the prediction
# and ground truth for that image
# get_highest_probability: boolean flag to indicate if the results
# need to be highest (True) or lowest (False) probabilities
# label: id of category
# number_of_items: num of results to return
# only_false_predictions: boolean flag to indicate if results
# should only contain incorrect predictions
def get_images_with_sorted_probabilities(prediction_table, get_highest_probability,
label, number_of_items, only_false_predictions=False):
sorted_prediction_table = [ (k, prediction_table[k]) for k in sorted(prediction_table, key=prediction_table.get, reverse= get_highest_probability)]
result = []
for index, key in enumerate(sorted_prediction_table):
image_index, [probability, predicted_index, gt] = key
if predicted_index == label:
if only_false_predictions == True:
if predicted_index != gt:
result.append([image_index, [probability, predicted_index, gt] ])
else:
result.append([image_index, [probability, predicted_index, gt] ])
if len(result) >= number_of_items:
return result
import matplotlib.image as mpimg
import matplotlib.pyplot as plt
# Helper functions to plot the nearest images given a query image
def plot_images(filenames, distances, message):
images = []
for filename in filenames:
images.append(mpimg.imread(filename))
plt.figure(figsize=(20,15))
columns = 5
for i, image in enumerate(images):
ax = plt.subplot(len(images) / columns + 1, columns, i + 1)
ax.set_title( "\n\n"+ filenames[i].split("/")[-1]+"\n"+"\nProbability: " +
str(float("{0:.2f}".format(distances[i]))))
plt.suptitle( message, fontsize=20, fontweight='bold')
plt.axis('off')
plt.imshow(image)
def display(sorted_indicies, message, fnames):
similar_image_paths = []
distances = []
for name, value in sorted_indicies:
[probability, predicted_index, gt] = value
similar_image_paths.append(VALIDATION_DATA_DIR + fnames[name])
distances.append(probability)
plot_images(similar_image_paths,distances, message)
# Most confident predictions of 'dog'
indices = get_images_with_sorted_probabilities(prediction_table, True, 1, 10, False)
print(indices)
message = 'Images with the highest probability of containing dogs'
display(indices[:10], message, validation_generator.filenames)
# Least confident predictions of 'dog'
indices = get_images_with_sorted_probabilities(prediction_table, False, 1, 10, False)
message = 'Images with the lowest probability of containing dogs'
display(indices[:10], message, validation_generator.filenames)
# Most confident predictions of 'cat'
indices = get_images_with_sorted_probabilities(prediction_table, True, 0, 10, False)
print(indices)
message = 'Images with the highest probability of containing cats'
display(indices[:10], message, validation_generator.filenames)
# Least confident predictions of 'cat'
indices = get_images_with_sorted_probabilities(prediction_table, False, 0, 10, False)
message = 'Images with the lowest probability of containing cats'
display(indices[:10], message, validation_generator.filenames)