Train TensorFlow Lite Model for Custom Object (License Plate) Detection with Custom Dataset

[@adithyawickramasinghe3983]

This is really helpful and it's working perfectly. Thank you for that.... If you can please do a video on regocnizing the number plate with tensorflow and easyocr

[@Wikipedieu]

hi, could you help me? i'm already finish training my own dataset (big thanks) but i've got error during running your LicenseDetector.py the messages is "from tensorflow.lite.python.interpreter import Interpreter ModuleNotFoundError: No module named 'tensorflow.lite.python.interpreter'" may you have any solution to solve this problem, thank you. keep it up 🙌

[@svarsha2579]

Hi, the training part doesn't complete even after 6 hours. what could be the issue?

[@abdullahsuheylozmen3255]

I can't connect to the gpu while training the model. Even though TPU4 is selected, training takes place via the CPU.

[@animationp973]

same problem here

[@minhazulmahmudriyad1559]

Hi there how can i use other models of tfod zoo. Just cant find the other two(checkpoint,config) except model name. It would be great if you show us how to do it.

[@ceynacecia_]

2024-05-12 07:59:55.623431: W tensorflow/core/framework/dataset.cc:768] Input of GeneratorDatasetOp::Dataset will not be optimized because the dataset does not implement the AsGraphDefInternal() method needed to apply optimizations. how to fix?

[@TlTAN]

hi, is a really nice video, its working, but i have a question, my dataset is large, when the time of google colab is done, how can start the train again but from the las checkpoint?

[@uriel2348]

I think it deletes everything when the time is done. Try checking the colab pro, maybe there you can get more time

[@Ashwanth777]

hi bro is the code is running ?

[@DevMe-f5v]

sir is this compatible in flutter?

[@chaimaez6651]

my model takes so much time to train (hours..). is that normal or can there be a problem ?

[@animationp973]

same problem here

[@chandramohan1281]

How to create our own data set and use that ?

[@pocketgamer8446]

You can use the labelimg python package to label your own images

[@Anchal-p8l]

From where i get my key in roboflow

[@oliverexcellent]

Roboflow automatically generates a key for you when you get your dataset. Choose "Download dataset" and then "show download code"

[@mohanrajudhandapani3241]

Hello Brother I am getting error in this section and unable to proceed further , could you please help on this? pipeline_fname = '/content/models/mymodel/' + base_pipeline_file fine_tune_checkpoint = '/content/models/mymodel/' + model_name + '/checkpoint/ckpt-0' def get_num_classes(pbtxt_fname): from object_detection.utils import label_map_util label_map = label_map_util.load_labelmap(pbtxt_fname) categories = label_map_util.convert_label_map_to_categories( label_map, max_num_classes=90, use_display_name=True) category_index = label_map_util.create_category_index(categories) return len(category_index.keys()) num_classes = get_num_classes(label_map_pbtxt_fname) print('Total classes:', num_classes)

[@mohanrajudhandapani3241]

Error : NotFoundError Traceback (most recent call last) in () 9 category_index = label_map_util.create_category_index(categories) 10 return len(category_index.keys()) ---> 11 num_classes = get_num_classes(label_map_pbtxt_fname) 12 print('Total classes:', num_classes) 3 frames /usr/local/lib/python3.10/dist-packages/tensorflow/python/lib/io/file_io.py in _preread_check(self) 74 raise errors.PermissionDeniedError(None, None, 75 "File isn't open for reading") ---> 76 self._read_buf = _pywrap_file_io.BufferedInputStream( 77 compat.path_to_str(self.__name), 1024 * 512) 78 NotFoundError: /content/labelmap.pbtxt; No such file or directory

[@Anuj-t4s]

check the path and make sure that .pbtxt file created before

[@jaybryanodero8110]

send collab note book link bro

[@adityahatwar8143]

please share your colab code