Upload 3 files

LICENSE

@@ -0,0 +1,189 @@
+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 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 the definition of
+"control", an entity controls another entity when such entity:
+(i) has the power, direct or indirect, to cause the direction or
+management of such other entity, whether by contract or otherwise,
+(ii) owns fifty percent (50%) or more of the outstanding shares, or
+(iii) has beneficial ownership of such entity.
+
+"You" (or "Your") shall mean an individual or Legal Entity
+exercising permissions granted by this License.
+
+"Source" shall mean the preferred form for making modifications,
+including but not limited to software source code, documentation
+source, and configuration files.
+
+"Object" 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
+(which shall not include communication that is conspicuously
+marked or otherwise designated in writing by the copyright owner
+as "Not a Contribution").
+
+"Derivative Works" shall mean any work, whether in Source or Object
+form, that is based upon (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 the definition of "Contribution",
+any such Contribution intentionally submitted for inclusion in the Work
+by You to the Licensor shall be deemed to have been made 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.
+
+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 use, reproduce, modify, merge, publish,
+   distribute, sublicense, and/or sell copies of the Work, and to
+   permit persons to whom the Work is furnished to do so, subject to
+   the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Work.
+
+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, trademark, patent,
+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 notice 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 Support. You are not required to accept
+   warranty or support for the Work under this License. However, if You
+   choose to accept warranty or support, 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 support.
+
+END OF TERMS AND CONDITIONS
+
+Copyright 2025 Trendyol
+
+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.

requirements.txt

@@ -0,0 +1,7 @@
+torch==2.7.1
+torchvision==0.22.1
+opencv-python==4.12.0.88
+numpy
+requests
+Pillow
+onnxruntime==1.22.1

utils.py

@@ -0,0 +1,170 @@
+import cv2
+import numpy as np
+import requests
+from PIL import Image
+from io import BytesIO
+import torch
+from pathlib import Path
+import torch.nn.functional as F
+from typing import Dict, Any, List, Union
+from torchvision.transforms.functional import normalize
+
+INPUT_SIZE = [1200, 1800]
+
+def keep_large_components(a: np.ndarray) -> np.ndarray:
+    """Remove small connected components from a binary mask, keeping only large regions.
+    
+    Args:
+        a: Input binary mask as numpy array
+        
+    Returns:
+        Processed mask with only large connected components remaining
+    """
+    dilate_kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE,(9, 9))
+    a_mask = (a > 25).astype(np.uint8) * 255
+
+    # Apply the Component analysis function
+    analysis = cv2.connectedComponentsWithStats(a_mask, 4, cv2.CV_32S)
+    (totalLabels, label_ids, values, centroid) = analysis
+
+    # Find the components to be kept
+    h, w = a.shape[:2]
+    area_limit = 50000 * (h * w) / (INPUT_SIZE[1] * INPUT_SIZE[0])
+    i_to_keep = []
+    for i in range(1, totalLabels):
+        area = values[i, cv2.CC_STAT_AREA]
+        if area > area_limit:
+            i_to_keep.append(i)
+
+    if len(i_to_keep) > 0:
+        # Or masks to be kept
+        final_mask = np.zeros_like(a, dtype=np.uint8)
+        for i in i_to_keep:
+            componentMask = (label_ids == i).astype("uint8") * 255
+            final_mask = cv2.bitwise_or(final_mask, componentMask)
+
+        # Remove other components
+        # Keep edges
+        final_mask = cv2.dilate(final_mask, dilate_kernel, iterations = 2)
+        a = cv2.bitwise_and(a, final_mask)
+        a = a.reshape((a.shape[0], a.shape[1], 1))
+        
+    return a
+
+def read_img(img: Union[str, Path]) -> np.ndarray:
+    """Read an image from a URL or local path.
+    
+    Args:
+        img: URL or file path to image
+        
+    Returns:
+        Image as numpy array in RGB format
+    """
+    if img[0: 4] == 'http':
+        response = requests.get(img)
+        im = np.asarray(Image.open(BytesIO(response.content)))
+        
+    else:
+        im = cv2.imread(str(img))
+        im = cv2.cvtColor(im, cv2.COLOR_BGR2RGB)
+
+    return im
+
+def preprocess_input(im: np.ndarray) -> torch.Tensor:
+    """Preprocess image for model input.
+    
+    Args:
+        im: Input image as numpy array
+        
+    Returns:
+        Preprocessed image as normalized torch tensor
+    """
+    if len(im.shape) < 3:
+        im = im[:, :, np.newaxis]
+        
+    if im.shape[2] == 4:  # if image has alpha channel, remove it
+        im = im[:,:,:3]
+
+    im_tensor = torch.tensor(im, dtype=torch.float32).permute(2,0,1)
+    im_tensor = F.upsample(torch.unsqueeze(im_tensor,0), INPUT_SIZE, mode="bilinear").type(torch.uint8)
+    image = torch.divide(im_tensor,255.0)
+    image = normalize(image,[0.5,0.5,0.5],[1.0,1.0,1.0])
+
+    if torch.cuda.is_available():
+        image=image.cuda()
+    
+    return image
+
+def postprocess_output(result: List[torch.Tensor]) -> np.ndarray:
+    """Postprocess model output.
+    
+    Args:
+        result: Model output as list of tensors
+        
+    Returns:
+        Processed binary mask as numpy array
+    """
+    result = torch.squeeze(F.upsample(
+        result[0][0], (INPUT_SIZE[1], INPUT_SIZE[0]), mode='bilinear'), 0)
+    ma = torch.max(result)
+    mi = torch.min(result)
+    result = (result-mi)/(ma-mi)
+
+    # a is alpha channel. 255 means foreground, 0 means background.
+    a = (result*255).permute(1,2,0).cpu().data.numpy().astype(np.uint8)
+    
+    # postprocessing
+    a = keep_large_components(a)
+
+    return a
+
+def postprocess_output_onnx(result: np.ndarray) -> np.ndarray:
+    """Postprocess ONNX model output.
+    
+    Args:
+        result: Model output as numpy array
+        
+    Returns:
+        Processed binary mask as numpy array
+    """
+    result = torch.squeeze(F.upsample(
+        torch.from_numpy(result).unsqueeze(0), (INPUT_SIZE[1], INPUT_SIZE[0]), mode='bilinear'), 0)
+    ma = torch.max(result)
+    mi = torch.min(result)
+    result = (result-mi)/(ma-mi)
+
+    # a is alpha channel. 255 means foreground, 0 means background.
+    a = (result*255).permute(1,2,0).cpu().data.numpy().astype(np.uint8)
+    
+    # postprocessing
+    a = keep_large_components(a)
+
+    return a
+
+def process_image(src: str, ort_session: Any, model_path: str, outname: str) -> None:
+    """Process an image through ONNX model to generate alpha mask and save result.
+    
+    Args:
+        src: Source image URL or path
+        ort_session: ONNX runtime inference session
+        model_path: Path to ONNX model file 
+        outname: Output filename for saving result
+        
+    Returns:
+        None
+    """
+    # Load and preprocess image
+    image_orig = read_img(src)
+    image = preprocess_input(image_orig)
+    
+    # Prepare ONNX input
+    inputs: Dict[str, Any] = {ort_session.get_inputs()[0].name: image.numpy()}
+    
+    # Get ONNX output and post-process
+    result = ort_session.run(None, inputs)[0][0]
+    alpha = postprocess_output_onnx(result)
+    
+    # Combine RGB image with alpha mask and save
+    img_w_alpha = np.dstack((cv2.cvtColor(image_orig, cv2.COLOR_BGR2RGB), alpha))
+    cv2.imwrite(outname, img_w_alpha)
+    print(f"Saved: {outname}")