The following generator is throwing an exception.
How can I resolve this issue?
import osimport numpy as npimport pandas as pdimport tensorflow as tffrom sklearn.model_selection import train_test_splitimport autokeras as akDATA_COLUMN_COUNT = 12 LABEL_COLUMN_INDEX = 2FEATURE_START_INDEX = 3NUM_OF_FEATURES = DATA_COLUMN_COUNT - FEATURE_START_INDEXNUM_OF_CLASSES = 3 BATCH_SIZE = 64EPOCHS = 111MAX_TRIALS = 10STEPS_PER_EPOCH = 200VALIDATION_STEPS = 50def load_data(file_path): data = pd.read_csv(file_path, header=None, sep='\s+', usecols=range(0, DATA_COLUMN_COUNT)) print("Sample data with usecols and correct separator:") print(data.head()) label_conversion = {'H': 0, 'E': 1, 'C': 2} y = data.iloc[:, LABEL_COLUMN_INDEX].map(label_conversion) y = tf.keras.utils.to_categorical(y, num_classes=len(label_conversion)) x = data.iloc[:, FEATURE_START_INDEX:].to_numpy() return x, ydef data_generator(file_paths, batch_size, num_classes): while True: for file_path in file_paths: x, y = load_data(file_path) # Remove the redundant to_categorical call # y = tf.keras.utils.to_categorical(y, num_classes) for i in range(0, len(x), batch_size): end = i + batch_size batch_x = x[i:end] batch_y = y[i:end] if batch_x.shape[0] < batch_size: padding = batch_size - batch_x.shape[0] batch_x = np.pad(batch_x, ((0, padding), (0, 0)), mode='constant', constant_values=0) # Ensure batch_y has the correct number of dimensions before padding batch_y = np.pad(batch_y, ((0, padding), (0, 0)), mode='constant', constant_values=0) yield batch_x, batch_ydef create_generators(folder_path, batch_size, num_classes, validation_split=0.2): files = [os.path.join(folder_path, f) for f in os.listdir(folder_path) if f.endswith('.dat')] train_files, validation_files = train_test_split(files, test_size=validation_split) train_gen = data_generator(train_files, batch_size, num_classes) validation_gen = data_generator(validation_files, batch_size, num_classes) return train_gen, validation_genif __name__ == "__main__": data_folder = r'/home/my_username/my_project_v2_original_data' train_gen, val_gen = create_generators(data_folder, BATCH_SIZE, NUM_OF_CLASSES) train_dataset = tf.data.Dataset.from_generator( lambda: train_gen, output_signature=( tf.TensorSpec(shape=(None, NUM_OF_FEATURES), dtype=tf.float32), tf.TensorSpec(shape=(None, NUM_OF_CLASSES), dtype=tf.float32) ) ) validation_dataset = tf.data.Dataset.from_generator( lambda: val_gen, output_signature=( tf.TensorSpec(shape=(None, NUM_OF_FEATURES), dtype=tf.float32), tf.TensorSpec(shape=(None, NUM_OF_CLASSES), dtype=tf.float32) ) ) clf = ak.StructuredDataClassifier(max_trials=MAX_TRIALS, overwrite=True, num_classes=NUM_OF_CLASSES) # Fit the model clf.fit(train_dataset, epochs=EPOCHS, steps_per_epoch=STEPS_PER_EPOCH, validation_data=validation_dataset, validation_steps=VALIDATION_STEPS) best_hps = clf.tuner.get_best_hyperparameters()[0] print(best_hps) model = clf.export_model() # Save the model model.save("cnn_autokeras_by_chunk_without_ohe") # Evaluate the model evaluation = clf.evaluate(validation_dataset) print(evaluation)C:\Users\pc\AppData\Local\Programs\Python\Python311\python.exe C:/git/my_project_v2/my_project_v2/my_project_v2_autokeras/cnn_autokeras_by_original_by_chunk.pyUsing TensorFlow backend2024-02-12 23:14:56.551477: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.To enable the following instructions: SSE SSE2 SSE3 SSE4.1 SSE4.2 AVX, in other operations, rebuild TensorFlow with the appropriate compiler flags.Sample data with usecols and correct separator: 0 1 2 3 4 5 6 7 8 9 10 110 0 SER C 0.000 0.000 0.000 1 1 1 1 1 01 1 ASN C 5.651 8.805 0.000 1 1 1 1 1 02 2 ALA C 5.582 5.602 9.099 0 0 0 1 1 03 3 MET C 5.756 7.791 7.902 0 0 0 0 0 04 4 ILE E 6.853 10.406 11.253 0 0 0 0 0 0Sample data with usecols and correct separator: 0 1 2 3 4 5 6 7 8 9 10 110 0 PRO C 0.000 0.000 0.000 1 1 1 1 1 01 1 ILE E 6.388 10.133 0.000 1 1 1 1 1 02 2 MET E 7.090 9.464 12.018 0 0 0 0 1 03 3 LEU E 6.281 9.841 12.931 0 0 0 0 0 04 4 ARG E 6.628 5.599 9.306 0 0 0 0 0 02024-02-12 23:14:58.258253: W tensorflow/core/framework/op_kernel.cc:1827] INVALID_ARGUMENT: ValueError: generator already executingTraceback (most recent call last): File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\ops\script_ops.py", line 270, in __call__ ret = func(*args) ^^^^^^^^^^^ File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\autograph\impl\api.py", line 643, in wrapper return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\data\ops\from_generator_op.py", line 198, in generator_py_func values = next(generator_state.get_iterator(iterator_id)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ValueError: generator already executingTraceback (most recent call last): File "C:\git\my_project_v2\my_project_v2\my_project_v2_autokeras\cnn_autokeras_by_original_by_chunk.py", line 97, in <module>2024-02-12 23:14:58.260762: W tensorflow/core/framework/op_kernel.cc:1827] INVALID_ARGUMENT: ValueError: generator already executingTr aclf.fit(train_dataset, epochs=EPOCHS, steps_per_epoch=STEPS_PER_EPOCH, validation_data=validation_dataset, validation_steps=VALIDATION_STEPS)ceback (most recent call last): File " File "C:\Users\pc\AppData\Local\Programs\Python\Python311\Lib\site-packages\autokeras\tasks\structured_data.py", line 326, in fitC:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\ops\script_ops.py", line 270, in __call__ ret = func(*args) ^^^^^^^^^^^ File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\autograph\impl\api.py", line 643, in wrapper return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\data\ops\from_generator_op.py", line 198, in generator_py_func values = next(generator_state.get_iterator(iterator_id)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ValueError: generator already executing2024-02-12 23:14:58.263112: W tensorflow/core/framework/op_kernel.cc:1827] INVALID_ARGUMENT: ValueError: generator already executingTraceback (most recent call last): File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\ops\script_ops.py", line 270, in __call__ ret = func(*args) ^^^^^^^^^^^ File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\autograph\impl\api.py", line 643, in wrapper return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\data\ops\from_generator_op.py", line 198, in generator_py_func values = next(generator_state.get_iterator(iterator_id)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ValueError: generator already executing2024-02-12 23:14:58.265071: W tensorflow/core/framework/op_kernel.cc:1827] INVALID_ARGUMENT: ValueError: generator already executingTraceback (most recent call last): File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\ops\script_ops.py", line 270, in __call__ ret = func(*args) ^^^^^^^^^^^ File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\autograph\impl\api.py", line 643, in wrapper return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\data\ops\from_generator_op.py", line 198, in generator_py_func values = next(generator_state.get_iterator(iterator_id)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ValueError: generator already executing2024-02-12 23:14:58.266913: W tensorflow/core/framework/op_kernel.cc:1827] INVALID_ARGUMENT: ValueError: generator already executingTraceback (most recent call last): File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\ops\script_ops.py", line 270, in __call__ ret = func(*args) ^^^^^^^^^^^ File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\autograph\impl\api.py", line 643, in wrapper return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\data\ops\from_generator_op.py", line 198, in generator_py_func values = next(generator_state.get_iterator(iterator_id)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ValueError: generator already executing2024-02-12 23:14:58.271889: W tensorflow/core/framework/op_kernel.cc:1827] INVALID_ARGUMENT: ValueError: generator already executingTraceback (most recent call last): File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\ops\script_ops.py", line 270, in __call__ ret = func(*args) ^^^^^^^^^^^ File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\autograph\impl\api.py", line 643, in wrapper return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\data\ops\from_generator_op.py", line 198, in generator_py_func values = next(generator_state.get_iterator(iterator_id)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ValueError: generator already executing2024-02-12 23:14:58.274866: W tensorflow/core/framework/op_kernel.cc:1827] INVALID_ARGUMENT: ValueError: generator already executingTraceback (most recent call last): File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\ops\script_ops.py", line 270, in __call__ ret = func(*args) ^^^^^^^^^^^ File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\autograph\impl\api.py", line 643, in wrapper return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\data\ops\from_generator_op.py", line 198, in generator_py_func values = next(generator_state.get_iterator(iterator_id)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ValueError: generator already executing history = super().fit( ^^^^^^^^^^^^ File "C:\Users\pc\AppData\Local\Programs\Python\Python311\Lib\site-packages\autokeras\tasks\structured_data.py", line 139, in fit history = super().fit( ^^^^^^^^^^^^ File "C:\Users\pc\AppData\Local\Programs\Python\Python311\Lib\site-packages\autokeras\auto_model.py", line 283, in fit self._analyze_data(dataset) File "C:\Users\pc\AppData\Local\Programs\Python\Python311\Lib\site-packages\autokeras\auto_model.py", line 369, in _analyze_data for x, y in dataset: File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\data\ops\iterator_ops.py", line 809, in __next__ return self._next_internal() ^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\data\ops\iterator_ops.py", line 772, in _next_internal ret = gen_dataset_ops.iterator_get_next( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\ops\gen_dataset_ops.py", line 3055, in iterator_get_nextSample data with usecols and correct separator: 0 1 2 3 4 5 6 7 8 9 10 110 0 MET C 0.000 0.000 0.000 1 1 1 1 1 01 1 THR C 7.281 10.424 0.000 1 1 1 1 1 02 2 PHE C 6.626 8.966 12.663 0 0 0 0 1 03 3 GLU C 6.220 9.739 12.658 0 0 0 0 0 04 4 LEU E 6.748 10.167 12.863 0 0 0 0 0 0 _ops.raise_from_not_ok_status(e, name) File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\framework\ops.py", line 5888, in raise_from_not_ok_status raise core._status_to_exception(e) from None # pylint: disable=protected-access ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^tensorflow.python.framework.errors_impl.InvalidArgumentError: {{function_node __wrapped__IteratorGetNext_output_types_2_device_/job:localhost/replica:0/task:0/device:CPU:0}} ValueError: generator already executingTraceback (most recent call last): File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\ops\script_ops.py", line 270, in __call__ ret = func(*args) ^^^^^^^^^^^ File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\autograph\impl\api.py", line 643, in wrapper return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\pc\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\data\ops\from_generator_op.py", line 198, in generator_py_func values = next(generator_state.get_iterator(iterator_id)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ValueError: generator already executing [[{{node PyFunc}}]] [Op:IteratorGetNext] name: 2024-02-12 23:14:58.675970: W tensorflow/core/kernels/data/generator_dataset_op.cc:108] Error occurred when finalizing GeneratorDataset iterator: FAILED_PRECONDITION: Python interpreter state is not initialized. The process may be terminated. [[{{node PyFunc}}]]2024-02-12 23:14:58.676507: W tensorflow/core/kernels/data/generator_dataset_op.cc:108] Error occurred when finalizing GeneratorDataset iterator: FAILED_PRECONDITION: Python interpreter state is not initialized. The process may be terminated. [[{{node PyFunc}}]]Process finished with exit code 1