Upload folder using huggingface_hub

.gitignore

@@ -0,0 +1,2 @@
+# Exclude the downloaded EMNIST data folder
+data/

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

Model/OCR_Model.py

@@ -0,0 +1,96 @@
+import torch
+import torch.nn as nn
+import torchvision
+import torchvision.transforms as transforms
+from torch.utils.data import DataLoader
+import torch.optim as optim
+from datetime import datetime
+
+class OCRModel(nn.Module):
+    def __init__(self):
+        super().__init__()
+        self.stack = nn.Sequential(
+            # === FIRST BLOCK ====
+            nn.Conv2d(in_channels=1, out_channels=32, kernel_size=3, stride=1, padding=1),
+            nn.ReLU(),
+            nn.MaxPool2d(kernel_size=2, stride=2),
+            # === NEXT BLOCK ====
+            nn.Conv2d(in_channels=32, out_channels=64, kernel_size=3, stride=1, padding=1),
+            nn.ReLU(),
+            nn.MaxPool2d(kernel_size=2, stride=2),
+            # === Linear Flatten ===
+            nn.Flatten(),
+            nn.Linear(64 * 7 * 7, 128),
+            nn.ReLU(),
+            nn.Linear(128, 128),
+            nn.ReLU(),
+            nn.Linear(128, 64),
+            nn.ReLU(),
+            nn.Linear(64, 47)
+        )
+    
+    def forward(self, x):
+        return self.stack(x)
+
+if __name__ == "__main__":
+
+    print(f"[{datetime.now()}][Info] Setting data transformation Formula... ")
+    # AI model training retrieval
+    transform = transforms.Compose([
+        transforms.ToTensor(),
+        transforms.Lambda(lambda x: x.transpose(1, 2)),
+        transforms.Normalize((0.1751,), (0.3332,))
+    ])
+
+    print(f"[{datetime.now()}][Status] Downloading Dataset... Pulling from EMNIST dataset..")
+    train_dataset = torchvision.datasets.EMNIST(
+        root='./data',
+        split='balanced',
+        train=True,
+        download=True,
+        transform=transform
+    )
+
+    print(f"[{datetime.now()}][Status] Done, preparing data for training...")
+    train_loader = DataLoader(dataset=train_dataset, batch_size = 64, shuffle=True, num_workers=0, pin_memory=True)
+
+    # === Initialize Trainer ===
+    print(f"[{datetime.now()}][Status] Data retrieved.  Initializing Model Trainer...")
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    model = OCRModel().to(device)
+    print(f"[{datetime.now()}][Status] Loaded Model")
+    criterion = nn.CrossEntropyLoss()
+    optimizer = optim.Adam(model.parameters(), lr=0.001)
+    print(f"[{datetime.now()}][Status] Criterion and Optimizer Formulas have been loaded.  ")
+    epochs = 10
+
+    print(f"[{datetime.now()}][Status] Initializing Training Loop for {epochs} epochs. ")
+    for epoch in range(epochs):
+        model.train()
+        running_loss = 0
+        correct = 0
+        total = 0
+
+        for inputs, labels in train_loader:
+            inputs, labels = inputs.to(device), labels.to(device)
+
+            optimizer.zero_grad()
+            outputs = model(inputs)
+            loss = criterion(outputs, labels)
+            loss.backward()
+            optimizer.step()
+
+            running_loss += loss.item() * inputs.size(0)
+            _, predicted = outputs.max(1)
+            total += labels.size(0)
+            correct += predicted.eq(labels).sum().item()
+
+        epoch_loss = running_loss / total
+        epoch_acc = 100.0 * correct/total
+        print(f"[TRAINING] Epoch {epoch+1}/{epochs}, Loss is {epoch_loss:.4f}, Accuracy, {epoch_acc:.2f}%")
+
+    print(f"[{datetime.now()}][Status] Training Done")
+    print(f"[{datetime.now()}][Info] Saving Model to disk...")
+    torch.save(model.state_dict(), "OCR_Model.pt")
+    print(f"[{datetime.now()}][Status] Done! Exiting program...")
+    exit(0)

OCR_Model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:030eeddc939424023edd3b03c556ba804d5d4b7a429e29f6ac27efe206ba3fbe
+size 1797539

README.md

@@ -1,3 +1,14 @@
----
-license: apache-2.0
----
+# OCR-Model
+Simple OCR for recognizing just individual characters as of now.
+![alt text](image.png)
+![alt text](image-1.png)
+_______________________________
+This was a project I made, for fun, mainly because I wanted to practice AI, and learn more Neural networks, and also contribute to my Github.  <br>
+<p>        <br></p>
+The AI can only recognize individual characters by themselves, although I eventually plan to make it recognize full sentences and paragraphs like this.  It uses a Convolutional Neural Network(CNN), followed by a dense MLP in order to analyze and process them.  A softmax function is then applied to output its classifications.  <br>
+<br>
+<p>&nbsp; Also, I plan on this being my first REPO to have a release.  
+  I will add the releases soon, as both its ZIP, and its EXE, 
+  which contain the model's pt and the program for interacting with it.  </p>
+
+<p>Latest notes:  The AI is extremely inaccurate, i plan on fixing that later.</p>

model_prediction_wrapper.py

@@ -0,0 +1,79 @@
+import torch
+from PIL import Image
+import os
+import torchvision.transforms as transforms
+from Model.OCR_Model import OCRModel
+import torchvision.transforms.functional as F
+import torch.nn.functional as C
+from guizero import App, Text, MenuBar
+from tkinter import filedialog
+
+def prediction_decode(output):
+    probabilities = C.softmax(output, dim=1)
+    conf, index_t = torch.max(probabilities, dim=1)
+    predicted_index = index_t.item()
+    conf_p = conf.item() * 100
+    labels = [
+    '0', '1', '2', '3', '4', '5', '6', '7', '8', '9',
+    'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 
+    'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 
+    'U', 'V', 'W', 'X', 'Y', 'Z',
+    'a', 'b', 'd', 'e', 'f', 'g', 'h', 'n', 'q', 'r', 't'
+    ]
+    predicted_char = labels[predicted_index]
+
+    return predicted_char, conf_p
+
+def predict():
+    file_path = filedialog.askopenfilename(
+        title="Open Image",
+        filetypes=[("Image Files", "*.png *.jpg *.jpeg *.bmp"), ("All Files", "*.*")]
+        )
+    if file_path:
+        print("[Status] Opening Image...")
+        try:
+            image = Image.open(file_path).convert("L")
+
+            transform = transforms.Compose([
+                transforms.Resize((28, 28)),
+                transforms.ToTensor(),
+                transforms.Normalize(mean=(0.1751,), std=(0.3332,))
+            ])
+
+            x = transform(image).unsqueeze(0)
+            x = torch.transpose(x, 2, 3) 
+
+            print(f"[AI] AI is thinking...")
+            with torch.no_grad():
+                predicted = model(x)
+
+            print(f"[AI] Decoding prediction...")
+            predicted_digit, conf = prediction_decode(predicted)
+            result.value = f"I feel {conf:.2f}% confident that I saw the digit {predicted_digit}"
+            print(f"[AI] I feel {conf:.2f}% confident that I read the digit {predicted_digit}")
+        except Exception as e:
+            result.value = f"Error :/"
+            print(f"[Error] {e}")
+    else:
+        print("[Status] Cancelled")
+
+print("[Status] Loading Model...")
+script_dir = os.path.dirname(os.path.abspath(__file__))
+model_path = os.path.join(script_dir, "OCR_Model.pt")
+state_dic = torch.load(model_path, weights_only=True)
+model = OCRModel()
+model.load_state_dict(state_dic)
+model.eval()
+print("[Info] Model Loaded")    
+
+app = App("Optical Character Recognizer(Digits)", width=500, height=250)
+info = Text(app, text="Welcome to Optical Character Recognizer.  Upload file for recognition.")
+info2 = Text(app, text="As of now, this app cannot recognize characters as full sentences, \n like this.  Such changes is for the future to be added.")
+menu = MenuBar(app, 
+               toplevel=["File"],
+               options=[ 
+                   [ ["Open", predict] ] 
+                ])
+result = Text(app, text=" ")
+
+app.display()