def __init__(
self,
image_dir: str,
job_dir: str,
epochs_train_dense: typing.Union[int, str] = EPOCHS_TRAIN_DENSE,
epochs_train_all: typing.Union[int, str] = EPOCHS_TRAIN_ALL,
learning_rate_dense: typing.Union[float, str] = LEARNING_RATE_DENSE,
learning_rate_all: typing.Union[float, str] = LEARNING_RATE_ALL,
batch_size: typing.Union[int, str] = BATCH_SIZE,
dropout_rate: typing.Union[float, str] = DROPOUT_RATE,
base_model_name: str = BASE_MODEL_NAME,
loss: str = LOSS,
**kwargs,
) -> None:
self.image_dir = Path(image_dir).resolve()
self.job_dir = Path(job_dir).resolve()
self.logger = get_logger(__name__, self.job_dir)
self.samples_train = load_json(self.job_dir / 'train_samples.json')
self.samples_val = load_json(self.job_dir / 'val_samples.json')
self.class_mapping = load_json(self.job_dir / 'class_mapping.json')
self.n_classes = len(self.class_mapping)
self.epochs_train_dense = int(epochs_train_dense)
self.epochs_train_all = int(epochs_train_all)
self.learning_rate_dense = float(learning_rate_dense)
self.learning_rate_all = float(learning_rate_all)
self.batch_size = int(batch_size)
self.dropout_rate = float(dropout_rate)
self.base_model_name = base_model_name
self.loss = loss
self.use_multiprocessing, self.workers = use_multiprocessing()
plt.style.use('ggplot')
from typing import List, Union, Tuple, Any
from pathlib import Path
from sklearn.metrics import confusion_matrix, accuracy_score, classification_report
from vis.visualization import visualize_cam
from imageatm.handlers.image_classifier import ImageClassifier
from imageatm.handlers.data_generator import ValDataGenerator
from imageatm.utils.io import load_json
from imageatm.utils.images import load_image
from imageatm.utils.logger import get_logger
from imageatm.utils.tf_keras import use_multiprocessing, load_model
BATCH_SIZE = 16
BASE_MODEL_NAME = 'MobileNet'
USE_MULTIPROCESSING, WORKERS = use_multiprocessing()
TYPE_IMAGE_LIST = List[List[Tuple[int, np.array,
dict]]] # used for type hinting
class Evaluation:
"""Calculates performance metrics for trained models.
Loads the best model (validation accuracy) from *models* directory in job directory.
All metrics and graphs are based on *test_samples.json* in job directory.
Attributes:
image_dir: Path of image directory.
job_dir: Path to job directory with samples.
batch_size: Number of images per batch (default 64).
def test__use_multiprocessing_false(self, mock):
use_multi, num_worker = use_multiprocessing()
assert use_multi == False
assert num_worker == 1
def test__use_multiprocessing_true(self, mock1, mock2):
use_multi, num_worker = use_multiprocessing()
assert use_multi == True
assert num_worker == 4711
