Complete 8th tutorial code

Author: pythonlessons

CHANGELOG.md

@@ -1,13 +1,15 @@
 ## [1.0.2] - 2022-03-... (unreleased)
 ### Changed
 - changes `OnnxInferenceModel` in `mltu.torch.inferenceModels` to load custom metadata from saved ONNX model
+- improved `mltu.dataProvider` to remove bad samples from dataset on epoch end
 
 ### Added:
 - added `mltu.torch.losses`, used to create PyTorch losses, that may be used in training and validation
 - added CTC loss to `mltu.torch.losses` that can be used for training CTC based models
 - added `Model2onnx` and `Tensorboard` callbacks to `mltu.torch.callbacks`, used to create PyTorch callbacks, that may be used in training and validation
-- added `CERMetric` to `mltu.torch.metrics`, used to create PyTorch metrics, that may be used in training and validation
-- created 08 pytorch tutorial, that shows how to use mltu.torch to train CTC based models
+- added `CERMetric` and `WERMetric` to `mltu.torch.metrics`, used to create PyTorch metrics, that may be used in training and validation
+- created 08 pytorch tutorial, that shows how to use `mltu.torch` to train CTC based models
+
 
 ## [1.0.1] - 2022-03-06
 ### Changed
@@ -36,7 +38,7 @@
 - 
 ### Added:
 - added 05_sound_to_text tutorial
-- added WavReader to mltu/preprocessors, used to read wav files and convert them to numpy arrays
+- added `WavReader` to `mltu/preprocessors`, used to read wav files and convert them to numpy arrays
 
 
 ## [0.1.7] - 2022-02-03
@@ -46,11 +48,11 @@
 
 ## [0.1.5] - 2022-01-10
 ### Changed
-- seperated CWERMetric to SER and WER Metrics in mltu.metrics, Character/word rate was calculatted in a wrong way
+- seperated `CWERMetric` to `CER` and `WER` Metrics in `mltu.metrics`, Character/word rate was calculatted in a wrong way
 - created @setter for augmentors and transformers in DataProvider, to properlly add augmentors and transformers to the pipeline
 - augmentors and transformers must inherit from `mltu.augmentors.base.Augmentor` and `mltu.transformers.base.Transformer` respectively
 - updated ImageShowCV2 transformer documentation
-- fixed OnnxInferenceModel in mltu.inferenceModels to use CPU even if GPU is available with force_cpu=True flag
+- fixed OnnxInferenceModel in `mltu.inferenceModels` to use CPU even if GPU is available with force_cpu=True flag
 
 ### Added:
 - added RandomSharpen to mltu.augmentors, used for simple image augmentation;

README.md

@@ -22,4 +22,5 @@ Each tutorial has its own requirements.txt file for a specific mltu version. As
 4. [Handwritten sentence recognition with TensorFlow](https://pylessons.com/handwritten-sentence-recognition), code in ```Tutorials\04_sentence_recognition``` folder;
 5. [Introduction to speech recognition with TensorFlow](https://pylessons.com/speech-recognition), code in ```Tutorials\05_speech_recognition``` folder;
 6. [Introduction to PyTorch in a practical way](https://pylessons.com/pytorch-introduction), code in ```Tutorials\06_pytorch_introduction``` folder;
-7. [Using custom wrapper to simplify PyTorch models training pipeline](https://pylessons.com/pytorch-introduction), code in ```Tutorials\07_pytorch_wrapper``` folder;
+7. [Using custom wrapper to simplify PyTorch models training pipeline](https://pylessons.com/pytorch-introduction), code in ```Tutorials\07_pytorch_wrapper``` folder;
+8. [Handwriting words recognition with PyTorch](https://pylessons.com/handwriting-recognition-pytorch), code in ```Tutorials\08_handwriting_recognition_torch``` folder;

Tutorials/08_handwriting_recognition_torch/README.md

@@ -0,0 +1,9 @@
+# Using custom wrapper to simplify PyTorch models training pipeline
+### Construct an accurate handwriting recognition model with PyTorch! Understand how to use MLTU package, to simplify the PyTorch models training pipeline, and discover methods to enhance your model's accuracy!<br><br>
+
+# **Detailed tutorial**:
+### [Handwriting words recognition with PyTorch](https://pylessons.com/handwriting-recognition-pytorch)
+
+<p align="center">
+    <img src="https://pylessons.com/media/Tutorials/mltu/handwriting-recognition-pytorch/handwriting-recognition-pytorch.png">
+</p>

Tutorials/08_handwriting_recognition_torch/requirements.txt

@@ -0,0 +1,4 @@
+torch==1.13.1
+tensorboard==2.10.1
+onnx==1.12.0
+torchsummaryX

Tutorials/08_handwriting_recognition_torch/train_torch.py

@@ -16,7 +16,7 @@
 from mltu.torch.callbacks import EarlyStopping, ModelCheckpoint, TensorBoard, Model2onnx, ReduceLROnPlateau
 
 from mltu.preprocessors import ImageReader
-from mltu.transformers import ImageResizer, LabelIndexer, LabelPadding
+from mltu.transformers import ImageResizer, LabelIndexer, LabelPadding, ImageShowCV2
 from mltu.augmentors import RandomBrightness, RandomRotate, RandomErodeDilate, RandomSharpen
 
 from model import Network
@@ -80,12 +80,14 @@ def download_and_unzip(url, extract_to='Datasets', chunk_size=1024*1024):
     batch_size=configs.batch_size,
     data_preprocessors=[ImageReader()],
     transformers=[
+        # ImageShowCV2(), # uncomment to show images during training
         ImageResizer(configs.width, configs.height, keep_aspect_ratio=False),
         LabelIndexer(configs.vocab),
         LabelPadding(max_word_length=configs.max_text_length, padding_value=len(configs.vocab))
         ],
     use_cache=True,
 )
+
 # Split the dataset into training and validation sets
 train_dataProvider, test_dataProvider = data_provider.split(split = 0.9)
 

mltu/__init__.py

@@ -1 +1 @@
-__version__ = "1.0.1"
+__version__ = "1.0.2"

mltu/torch/losses.py

@@ -26,15 +26,9 @@ def forward(self, output, target):
         # Remove padding and blank tokens from target
         target_lengths = torch.sum(target != self.blank, dim=1)
         target_unpadded = target[target != self.blank].view(-1)
-        # target_unpadded = []
-        # for i in range(target.size(0)):
-        #     target_unpadded.append(target[i, :target_lengths[i]])
-        # target_unpadded = torch.cat(target_unpadded)
-
 
         output = output.permute(1, 0, 2)  # (sequence_length, batch_size, num_classes)
         output_lengths = torch.full(size=(output.size(1),), fill_value=output.size(0), dtype=torch.int64)
-        # target_lengths = torch.full(size=(output.size(1),), fill_value=target.size(1), dtype=torch.int64)
 
         loss = self.ctc_loss(output, target_unpadded, output_lengths, target_lengths)
 

mltu/transformers.py

@@ -157,7 +157,7 @@ def __call__(self, data: np.ndarray, label: np.ndarray):
         """
         if self.verbose:
             if isinstance(label, (str, int, float)):
-                logger.info('Label: ', label)
+                logger.info(f'Label: {label}')
 
         cv2.imshow('image', data)
         cv2.waitKey(0)