def predict_dataset(
ds_type: str = 'test',
cpu=True,
sample_size=config.BEST_MODEL_PARAMS['sample_size'],
with_oversampling=config.BEST_MODEL_PARAMS['with_oversampling'],
with_focal_loss=config.BEST_MODEL_PARAMS['with_focal_loss'],
with_weighted_loss=config.BEST_MODEL_PARAMS['with_weighted_loss'],
confusion_matrix_filename='test_confusion_matrix'):
learn = load_saved_learner(sample_size=sample_size,
with_oversampling=with_oversampling,
with_focal_loss=with_focal_loss,
with_weighted_loss=with_weighted_loss,
cpu=cpu)
classes = {c: i for i, c in enumerate(learn.data.classes)}
# create a DF with filepath and class label (int)
data = pd.read_csv(config.PROCESSED_DATA_DIR / 'labels_full.csv')
data = data[data['ds_type'] == ds_type][['name', 'label']]
data['label_int'] = data.label.apply(lambda x: classes[x])
print(f'Running predictions on {data.shape[0]} data samples')
data['pred_probability'] = pd.Series(dtype=object)
for k, i in enumerate(data.index):
pred = learn.predict(
open_image(config.PROCESSED_DATA_DIR / data.loc[i, 'name'],
convert_mode='L'))
data.loc[i, 'y_pred'] = pred[0].data.item()
data.at[i, 'pred_probability'] = pred[2].numpy()
if k % 200 == 0 and k > 0:
print(f'{k} images done..')
data.to_csv(config.DATA_DIR / 'predictions.csv', index=False)
print(f'Building classification interpretation..')
interp = ClassificationInterpretation(
learn=learn,
losses=np.zeros(data.shape[0]),
preds=tensor(data['pred_probability'].to_list()),
y_true=tensor(data.label_int.to_list()))
mat = interp.confusion_matrix()
# sum diagonal / all data_size *100
accuracy = np.trace(mat) / mat.sum() * 100
print(mat)
print(f'Accuracy: {accuracy}')
interp.plot_confusion_matrix(return_fig=True).savefig(
f'test_{confusion_matrix_filename}', dpi=200)
joblib.dump(mat, f'test_{confusion_matrix_filename}.pkl')
return mat, accuracy
def plot_learning_rate(sample_size=300, image_size=224, load_learner=True):
data = load_dataset(sample_size=sample_size, image_size=image_size)
if load_learner:
learn = load_saved_learner()
learn.data = data
else:
learn = cnn_learner(data, models.resnet50, metrics=accuracy)
learn.model = torch.nn.DataParallel(learn.model)
learn.lr_find()
learn.recorder.plot(return_fig=True).savefig('learning_rate.png', dpi=200)
def improve_saved_model(sample_size=300, image_size=224, n_cycles=5,
max_lr=slice(1e-6,1e-4), save=False,
with_focal_loss=False, with_oversampling=True,
with_weighted_loss=True):
data = load_dataset(sample_size=sample_size, image_size=image_size)
learn = load_saved_learner(with_focal_loss=with_focal_loss, with_oversampling=with_oversampling,
sample_size=sample_size, with_weighted_loss=with_weighted_loss)
learn.data = data
learn.unfreeze()
learn.fit_one_cycle(n_cycles, max_lr=max_lr)
if save:
save_learner(learn, with_focal_loss=with_focal_loss, with_oversampling=with_oversampling,
sample_size=sample_size, with_weighted_loss=with_weighted_loss)
_save_classification_interpert(learn)
def make_prediction_sample(
image_path,
cpu=True,
sample_size=config.BEST_MODEL_PARAMS['sample_size'],
with_oversampling=config.BEST_MODEL_PARAMS['with_oversampling'],
with_focal_loss=config.BEST_MODEL_PARAMS['with_focal_loss'],
with_weighted_loss=config.BEST_MODEL_PARAMS['with_weighted_loss'],
):
learn = load_saved_learner(sample_size=sample_size,
with_oversampling=with_oversampling,
with_focal_loss=with_focal_loss,
with_weighted_loss=with_weighted_loss,
cpu=cpu)
# load image in grayscale
image = open_image(image_path, convert_mode='L')
cat = learn.predict(image)
print(cat)
class_prob = {k: float(v) for k, v in zip(learn.data.classes, cat[2])}
return cat[0].obj, class_prob