philzetter
philzetter
Thank you for the fast response ! I'm using exactly the same code. My train_dataset looks like this: `[['CINCMC/images/one.jpg', 'one']]`
Could you sent me an example of your annotation files. I just need a few lines of the txt files. I think that's the problem.
I still get this error: ``` Traceback (most recent call last): File "/path/to/mltu/Tutorials/01_image_to_word/train.py", line 102, in model.fit( File "/path/to/python3.10/site-packages/keras/utils/traceback_utils.py", line 70, in error_handler raise e.with_traceback(filtered_tb) from None File "/path/to/python3.10/site-packages/keras/engine/data_adapter.py", line...
The result of: ``` for data in train_data_provider: print(data[0], data[1]) ``` looks like this: ``` [[[[102 102 102] [103 103 103] [104 104 104] ... [134 134 134] [138 138...
Tried the following code: ``` for data in train_data_provider: if data[0] is None or data[1] is None: print("something wrong in data") else: print(data[0].shape, data[1].shape) ``` Result is: `(1000, 32, 128,...
1000 is the size of my dataset and I'm loading it as described on to the dataset. I already sent the dataset above. Could you maybe show me a few...