eval.h5 & test.h5 datasets not generated in data_cooked directory
tfromb opened this issue · 2 comments
Im doing the E2EDeepLearning tutorial. When I try to read in the datasets in TrainModel from the exploration phase, the eval.h5 and test.h5 files are not generated and so can not be opened. I've gone back to the DataExploration phase and run the code, however, they still aren't generating. I received a StopIteration as shown below. How can I fix this?
Thanks
`StopIteration Traceback (most recent call last)
~\Documents\Tomi\AirSim\AutonomousDrivingCookbook-master\AirSimE2EDeepLearning\Cooking.py in generatorForH5py(data_mappings, chunk_size)
129 raise StopIteration
--> 130 raise StopIteration
131
StopIteration:
The above exception was the direct cause of the following exception:
RuntimeError Traceback (most recent call last)
in
1 train_eval_test_split = [0.7, 0.2, 0.1]
2 full_path_raw_folders = [os.path.join(RAW_DATA_DIR, f) for f in DATA_FOLDERS]
----> 3 Cooking.cook(full_path_raw_folders, COOKED_DATA_DIR, train_eval_test_split)
~\Documents\Tomi\AirSim\AutonomousDrivingCookbook-master\AirSimE2EDeepLearning\Cooking.py in cook(folders, output_directory, train_eval_test_split)
196 for i in range(0, len(split_mappings), 1):
197 print('Processing {0}...'.format(output_files[i]))
--> 198 saveH5pyData(split_mappings[i], output_files[i])
199 print('Finished saving {0}.'.format(output_files[i]))
~\Documents\Tomi\AirSim\AutonomousDrivingCookbook-master\AirSimE2EDeepLearning\Cooking.py in saveH5pyData(data_mappings, target_file_path)
162 dset_previous_state[:] = previous_state_chunk
163
--> 164 for image_names_chunk, label_chunk, previous_state_chunk in gen:
165 image_chunk = np.asarray(readImagesFromPath(image_names_chunk))
166
RuntimeError: generator raised StopIteration`
It works fine for me, check if you are using Keras 2.1.2, you cannot use newer version of Keras on AirSimE2EDeepLearning. It should be written on the readme really. I will update..
Are you on python 3.7? If so, that's your issue.