Ответ Предупреждение о потоке тензора - ПРЕДУПРЕЖДЕНИЕ: тензорный поток: на входе закончились данные; прерывание трениро ⇐ Python

[Anonymous]

Результат

Код: Выделить всё

Training with fine tunning
Training steps per epoch: 18
Validation steps per epoch: 4
Training generator batch size: 32
Total training samples: 576
Total validation samples: 144
Epoch 1/5
/usr/local/lib/python3.10/dist-packages/keras/src/trainers/data_adapters/py_dataset_adapter.py:121: UserWarning: Your `PyDataset` class should call `super().__init__(**kwargs)` in its constructor. `**kwargs` can include `workers`, `use_multiprocessing`, `max_queue_size`. Do not pass these arguments to `fit()`, as they will be ignored.
self._warn_if_super_not_called()
18/18 ━━━━━━━━━━━━━━━━━━━━ 399s 19s/step - accuracy: 0.1593 - loss: 2.1888 - val_accuracy: 0.3281 - val_loss: 1.8363
Epoch 2/5
/usr/lib/python3.10/contextlib.py:153: UserWarning: Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches. You may need to use the `.repeat()` function when building your dataset.
self.gen.throw(typ, value, traceback)
18/18 ━━━━━━━━━━━━━━━━━━━━ 5s 294ms/step - accuracy: 0.0000e+00 - loss: 0.0000e+00 - val_accuracy: 0.3750 - val_loss: 1.8651
Epoch 3/5
18/18 ━━━━━━━━━━━━━━━━━━━━ 361s 18s/step - accuracy: 0.3593 - loss: 1.7475 - val_accuracy: 0.4141 - val_loss: 1.6302
Epoch 4/5
18/18 ━━━━━━━━━━━━━━━━━━━━ 41s 2s/step - accuracy: 0.0000e+00 - loss: 0.0000e+00 - val_accuracy: 0.4375 - val_loss: 1.4419
Epoch 5/5
18/18 ━━━━━━━━━━━━━━━━━━━━ 322s 18s/step - accuracy: 0.5175 - loss: 1.4328 - val_accuracy: 0.3984 - val_loss: 1.4993

Полный код
(https://drive.google.com/file/d/1jHqDnC ... sp=sharing)
Можете ли вы помочь мне устранить ошибку?

Подробнее здесь: https://stackoverflow.com/questions/791 ... -data-inte