hatchling to setuptools

.dockerignore

@@ -1 +1 @@
-.venv
+.venv

.github/ISSUE_TEMPLATE/bugs.yaml

@@ -7,12 +7,12 @@ body:
     attributes:
       value: |
         ## Instructions To Reproduce the 🐛 Bug:
-        
+
         1. Background explanation
 
   - type: textarea
     attributes:
-      label: Full runnable code or full changes you made:
+      label: "Full runnable code or full changes you made:"
       description: Please provide the code or changes that led to the bug.
       placeholder: |
         ```
@@ -22,7 +22,7 @@ body:
 
   - type: textarea
     attributes:
-      label: What exact command you ran:
+      label: "What exact command you ran:"
       description: Describe the exact command you ran that triggered the bug.
     validations:
       required: true
@@ -51,4 +51,4 @@ body:
       description: Indicate your environment details.
       options:
         - label: "I'm using the latest version!"
-        - label: "It's not a user-side mistake!"
+        - label: "It's not a user-side mistake!"

.github/ISSUE_TEMPLATE/documentation.yaml

@@ -6,7 +6,7 @@ body:
     attributes:
       value: |
         ## 📚 Documentation Issue
-        
+
         This issue category is for problems about existing documentation, not for asking how-to questions.
 
   - type: input

.github/ISSUE_TEMPLATE/feature-request.yaml

@@ -6,7 +6,7 @@ body:
     attributes:
       value: |
         ## 🚀 Feature
-        
+
         A clear and concise description of the feature proposal.
 
   - type: textarea
@@ -25,6 +25,6 @@ body:
     attributes:
       value: |
         ## Note
-        
+
         We only consider adding new features if they are relevant to this library.
         Consider if this new feature deserves to be here or should be a new library.

.pre-commit-config.yaml

@@ -63,4 +63,4 @@ repos:
         additional_dependencies:
           - mdformat-gfm
           - mdformat_frontmatter
-        exclude: CHANGELOG.md
+        exclude: CHANGELOG.md

Dockerfile

@@ -21,4 +21,4 @@ RUN pip install -r requirements.txt
 EXPOSE 8000
 
 # Entry point
-CMD ["python3", "app.py"]
+CMD ["python3", "app.py"]

README.md

@@ -21,28 +21,40 @@ Language Segment-Anything is an open-source project that combines the power of i
 
 ### Installation
 
+#### Installing PyTorch Dependencies
+
+Before installing `lang-sam`, please install PyTorch using the following command:
+
+```bash
+pip install torch==2.4.1 torchvision==0.19.1 --extra-index-url https://download.pytorch.org/whl/cu124
+
 ```
+
 pip install -U git+https://github.com/luca-medeiros/lang-segment-anything.git
+
 ```
 
 Or
 Clone the repository and install the required packages:
 
 ```
+
 git clone https://github.com/luca-medeiros/lang-segment-anything && cd lang-segment-anything
 pip install -e .
+
 ```
 
 #### Docker Installation
 
 Build and run the image.
 
 ```
+
 git clone https://github.com/luca-medeiros/lang-segment-anything && cd lang-segment-anything
 docker build --tag lang-segment-anything:latest .
 docker run --gpus all -p 8000:8000 lang-segment-anything:latest
-```
 
+````
 
 ### Usage
 
@@ -61,15 +73,14 @@ model = LangSAM()
 image_pil = Image.open("./assets/car.jpeg").convert("RGB")
 text_prompt = "wheel."
 results = model.predict([image_pil], [text_prompt])
-```
+````
 
 ## Examples
 
 ![car.png](/assets/outputs/car.png)
 
 ![fruits.png](/assets/outputs/fruits.png)
 
-
 ## Acknowledgments
 
 This project is based on/used the following repositories:

lang_sam/lang_sam.py

@@ -20,8 +20,7 @@ def predict(
         box_threshold: float = 0.3,
         text_threshold: float = 0.25,
     ):
-        """
-        Predicts masks for given images and text prompts using GDINO and SAM models.
+        """Predicts masks for given images and text prompts using GDINO and SAM models.
 
         Parameters:
             images_pil (list[Image.Image]): List of input images.

lang_sam/models/gdino.py

@@ -1,7 +1,7 @@
-import numpy as np
 import torch
 from PIL import Image
 from transformers import AutoModelForZeroShotObjectDetection, AutoProcessor
+
 from lang_sam.models.utils import get_device_type
 
 device_type = get_device_type()

lang_sam/models/sam.py

@@ -5,6 +5,7 @@
 from omegaconf import OmegaConf
 from sam2.automatic_mask_generator import SAM2AutomaticMaskGenerator
 from sam2.sam2_image_predictor import SAM2ImagePredictor
+
 from lang_sam.models.utils import get_device_type
 
 DEVICE = torch.device(get_device_type())

lang_sam/models/utils.py

@@ -1,4 +1,5 @@
 import logging
+
 import torch
 
 

lang_sam/server.py

@@ -18,8 +18,7 @@ def setup(self, device: str) -> None:
         print("LangSAM model initialized.")
 
     def decode_request(self, request) -> dict:
-        """
-        Decode the incoming request to extract parameters and image bytes.
+        """Decode the incoming request to extract parameters and image bytes.
 
         Assumes the request is sent as multipart/form-data with fields:
         - sam_type: str
@@ -50,15 +49,17 @@ def decode_request(self, request) -> dict:
         }
 
     def predict(self, inputs: dict) -> dict:
-        """
-        Perform prediction using the LangSAM model.
+        """Perform prediction using the LangSAM model.
 
         Yields:
             dict: Contains the processed output image.
         """
         print("Starting prediction with parameters:")
         print(
-            f"sam_type: {inputs['sam_type']}, box_threshold: {inputs['box_threshold']}, text_threshold: {inputs['text_threshold']}, text_prompt: {inputs['text_prompt']}"
+            f"sam_type: {inputs['sam_type']}, \
+                box_threshold: {inputs['box_threshold']}, \
+                text_threshold: {inputs['text_threshold']}, \
+                text_prompt: {inputs['text_prompt']}"
         )
 
         if inputs["sam_type"] != self.model.sam_type:
@@ -96,8 +97,7 @@ def predict(self, inputs: dict) -> dict:
         return {"output_image": output_image}
 
     def encode_response(self, output: dict) -> Response:
-        """
-        Encode the prediction result into an HTTP response.
+        """Encode the prediction result into an HTTP response.
 
         Returns:
             Response: Contains the processed image in PNG format.

pyproject.toml

@@ -1,26 +1,24 @@
+[build-system]
+requires = ["setuptools", "wheel"]
+build-backend = "setuptools.build_meta"
+
 [project]
 name = "lang-sam"
 version = "0.1.0"
 description = "Language segment-anything"
 readme = "README.md"
-documentation = "https://github.com/luca-medeiros/lang-segment-anything/blob/main/README.md"
-repository = "https://github.com/luca-medeiros/lang-segment-anything"
 authors = [
   { name = "Luca Medeiros", email = "[email protected]" },
 ]
-packages = [
-    { include = "lang_sam" },
-]
 requires-python = ">=3.11"
 dynamic = ["dependencies"]
 
 [tool.setuptools.dynamic]
 dependencies = {file = ["requirements.txt"]}
 
-[build-system]
-requires = ["hatchling"]
-build-backend = "hatchling.build"
-
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["lang_sam", "lang_sam.*"]
 
 [tool.ruff]
 target-version = "py311"

requirements.txt

@@ -6,9 +6,5 @@ sam-2 @ git+https://github.com/facebookresearch/segment-anything-2@7e1596c0b6462
 supervision==0.23.0 ; python_full_version > '3.10'
 transformers==4.44.2
 uvloop==0.20.0
-
-
---extra-index-url https://download.pytorch.org/whl/cu124
 torch==2.4.1
---extra-index-url https://download.pytorch.org/whl/cu124
-torchvision==0.19.1
+torchvision==0.19.1