attention-ocr
attention-ocr copied to clipboard
emedvedev
A Tensorflow model for text recognition (CNN + seq2seq with visual attention) available as a Python package and compatible with Google Cloud ML Engine.
given num-epoch 200 but the training is continuing Step 328+, for how many steps it will continue?
aocr train ./data/training.tfrecords --max-width 200 --max-height 100 --model-dir ./checkpoint --max-prediction 236 --num-epoch 200
Hi, I am trying to export `aocr` to tensorflowjs. But I am stuck at the point of exporting this model into a file. When running the `aocr export ANY_LOCATION` I...
Hello, I appreciate your work, I hope you can help me with the method to upgrade to Tensorflow 2.0,Looking forward to your help,thanks very much!
Hi, How can I visualise attention masks using SavedModel format? I would appreciate any hints.
Can someone please share either the checkpoint or a Saved model trained on Synth 90k? The pre-trained model shared on the original repository does not work when I try to...
I'm attempting to train a custom `aocr` model on an internal dataset. I've labeled the data using a directory of images, and an annotation file as described in the README....
First of all thank you for this amazing OCR. It works great for me. When i run inference on exported frozen graph i get a lot of messages inside terminal...
Can you tell me when can we expect this package with tensorflow 2.1.0 ?
Hi i prepared a datasets having 15226 images with respective annotations. I'm new to machine learning. Training images: 15226 Batch size: 65 Epoch: 1000 Max width: 260 Max height: 70...
2021-01-29 15:28:13.823161: W tensorflow/stream_executor/platform/default/dso_loader.cc:60] Could not load dynamic library 'cudart64_110.dll'; dlerror: cudart64_110.d ll not found 2021-01-29 15:28:13.831735: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU...
