ResidentMario

import numpy as np
from keras.wrappers.scikit_learn import KerasClassifier
from sklearn.base import BaseEstimator

class KerasBatchClassifier(KerasClassifier, BaseEstimator):
    def __init__(self, model, **kwargs):
        super().__init__(model)
        self.fit_kwargs = kwargs
        self._estimator_type = 'classifier'

ResidentMario

from keras.wrappers.scikit_learn import KerasClassifier

# notice how we go back to stating hyperparameters at init time
# this is the "scikit-learn" way
model = KerasClassifier(
    twoLayerFeedForward, epochs=100, batch_size=500, verbose=0
)

# now fit and predict
model.fit(X, y)

ResidentMario

# import model base and layers
from keras.models import Sequential
from keras.layers import Dense

def twoLayerFeedForward():
    # stack the layers
    clf = Sequential()
    clf.add(Dense(9, activation='relu', input_dim=3))
    clf.add(Dense(9, activation='relu'))
    clf.add(Dense(3, activation='softmax'))

ResidentMario

# import a classifier object
from sklearn.svm import LinearSVC

# initialize it with hyperparameters
clf = LinearSVC(penalty='l2', loss='hinge')

# call fit on data to train the model
clf.fit(X, y)

# call predict to get predictions

ResidentMario

from t4 import list_packages, Package
MODULE_PATH = []


class DataPackageImporter:
    """
    Data package module loader. Executes package import code and adds the package to the
    module cache.
    """

ResidentMario

from importlib.machinery import ModuleSpec

class DataPackageFinder:
    """
    Data package module loader finder. This class sits on `sys.meta_path` and returns the
    loader it knows for a given path, if it knows a compatible loader.
    """

    @classmethod
    def find_spec(cls, fullname, path=None, target=None):

ResidentMario

import pathlib

sample_size = len(list(pathlib.Path('../data/images_cropped/').rglob('./*')))
batch_size = 16

hist = model.fit_generator(
    train_generator,
    steps_per_epoch=sample_size // batch_size,
    epochs=50,
    validation_data=validation_generator,

ResidentMario

from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras.losses import binary_crossentropy
from keras.callbacks import EarlyStopping
from keras.optimizers import RMSprop


model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3), input_shape=(128, 128, 3), activation='relu'))

ResidentMario

from keras.preprocessing.image import ImageDataGenerator

train_datagen = ImageDataGenerator(
    rotation_range=40,
    width_shift_range=0.2,
    height_shift_range=0.2,
    rescale=1/255,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True,

ResidentMario

import sys
import os
import pandas as pd
import requests

from tqdm import tqdm
import ratelim
from checkpoints import checkpoints
checkpoints.enable()