Feature/make the sowlv2 more efficient

.claude/settings.local.json

@@ -42,7 +42,16 @@
       "Bash(python -m pytest tests/unit/utils/test_path_config.py::TestIntegrationPatterns::test_video_pattern_consistency tests/unit/test_cli.py::TestCLIArgumentParsing::test_config_file_argument -v)",
       "Bash(git commit:*)",
       "Bash(git push:*)",
-      "Bash(sed:*)"
+      "Bash(sed:*)",
+      "Bash(python3:*)",
+      "Bash(python -m pytest tests/integration/test_optimizations.py::TestParallelProcessing::test_parallel_detection_multiple_prompts -v)",
+      "Bash(python -m pytest tests/integration/test_optimizations.py::TestOptimizedPipeline::test_optimized_image_processing -v)",
+      "Bash(python -m pytest tests/integration/test_optimizations.py::TestOptimizedPipeline::test_optimized_image_processing -v -s)",
+      "Bash(python:*)",
+      "WebFetch(domain:huggingface.co)",
+      "Bash(rg:*)",
+      "WebFetch(domain:github.com)",
+      "WebFetch(domain:github.com)"
     ],
     "deny": []
   }

.github/workflows/pyre.yml

@@ -1,46 +1,32 @@
-# This workflow uses actions that are not certified by GitHub.
-# They are provided by a third-party and are governed by
-# separate terms of service, privacy policy, and support
-# documentation.
-
-# This workflow integrates Pyre with GitHub's
-# Code Scanning feature.
-#
-# Pyre is a performant type checker for Python compliant with
-# PEP 484. Pyre can analyze codebases with millions of lines
-# of code incrementally – providing instantaneous feedback
-# to developers as they write code.
-#
-# See https://pyre-check.org
-
-name: Pyre
+name: Pyre & Pysa Analysis
 
 on:
-  workflow_dispatch:
   push:
-    branches: [ "main" ]
+    branches: [main]
   pull_request:
-    branches: [ "main" ]
-
-permissions:
-    contents: read
+    branches: [main]
 
 jobs:
   pyre:
-    permissions:
-      actions: read
-      contents: read
-      security-events: write
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
+
+      - name: Run Pyre Action
+        uses: facebook/pyre-action@v0.0.2
         with:
-          submodules: true
+          repo-directory: './'
+          requirements-path: 'requirements.txt'
+
+  pysa:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
 
-      - name: Run Pyre
-        uses: facebook/pyre-action@60697a7858f7cc8470d8cc494a3cf2ad6b06560d
+      - name: Run Pysa Action
+        uses: facebook/pysa-action@v0.0.1
         with:
-          # To customize these inputs:
-          # See https://github.com/facebook/pyre-action#inputs
           repo-directory: './'
           requirements-path: 'requirements.txt'
+          infer-types: true
+          include-default-sapp-filters: true

.github/workflows/tests.yml

@@ -6,10 +6,15 @@ on:
   pull_request:
     branches: [ main, develop ]
 
+permissions:
+  contents: read
+
 jobs:
   lint:
     runs-on: ubuntu-latest
     name: Code Quality (Lint)
+    permissions:
+      contents: read
 
     steps:
     - name: Checkout code
@@ -41,6 +46,8 @@ jobs:
 
   test:
     runs-on: ubuntu-latest
+    permissions:
+      contents: read
     strategy:
       matrix:
         python-version: ["3.10", "3.11", "3.12", "3.13"]
@@ -91,6 +98,8 @@ jobs:
 
   test-cross-platform:
     runs-on: ${{ matrix.os }}
+    permissions:
+      contents: read
     strategy:
       matrix:
         os: [ubuntu-latest, windows-latest, macos-latest]
@@ -118,6 +127,8 @@ jobs:
   security-scan:
     runs-on: ubuntu-latest
     name: Security Scan
+    permissions:
+      contents: read
 
     steps:
     - name: Checkout code

README.md

@@ -88,19 +88,20 @@ Note: If a single prompt contains spaces, it should be enclosed in quotes (e.g.,
 
 ### Command-Line Options:
 
-/
-| `--prompt`      | **(Required)** One or more text queries for object detection (e.g., `"cat"`, or `"dog" "person" "a red car"`).                       | `None`                               |
-| `--input`       | **(Required)** Path to the input: a single image file, a directory of image frames, or a video file.                                | `None`                               |
-| `--output`      | Directory where outputs (masks and overlays) will be saved. Created if it doesn't exist.                                           | `output/`                            |
-| `--owl-model`   | (Optional) OWLv2 model name from Hugging Face Model Hub.                                                                           | `google/owlv2-base-patch16-ensemble` |
-| `--sam-model`   | (Optional) SAM 2 model name from Hugging Face Model Hub.                                                                           | `facebook/sam2.1-hiera-small`        |
-| `--threshold`   | (Optional) Detection confidence threshold for OWLv2 (a float between 0 and 1).                                                     | `0.1`                                |
-| `--fps`         | (Optional) Frame sampling rate (frames per second) for video inputs.                                                               | `24`                                 |
-| `--device`      | (Optional) Compute device (`"cuda"` or `"cpu"`).                                                                                     | Auto-detects GPU, else `cpu`         |
-| `--no-merged`   | (Optional) Disables merged mode. Merged mode (where all masks are combined into a single output [image/video] ) is enabled by default.                   | Enabled                              |
-| `--no-binary`   | (Optional) Disables binary mask generation. Binary mask output is enabled by default.                                                  | Enabled                              |
-| `--no-overlay`  | (Optional) Disables overlay image generation. Overlay image output (original image with masks) is enabled by default.                  | Enabled                              |
-| `--config`      | (Optional) Path to a YAML configuration file to specify arguments (see [Configuration](#configuration)). Prompts can also be a list in YAML. | `None`                               |
+| Option | Description | Default |
+|--------|-------------|---------|
+| `--prompt` | **(Required)** One or more text queries for object detection (e.g., `"cat"`, or `"dog" "person" "a red car"`). | `None` |
+| `--input` | **(Required)** Path to the input: a single image file, a directory of image frames, or a video file. | `None` |
+| `--output` | Directory where outputs (masks and overlays) will be saved. Created if it doesn't exist. | `output/` |
+| `--owl-model` | (Optional) OWLv2 model name from Hugging Face Model Hub. | `google/owlv2-base-patch16-ensemble` |
+| `--sam-model` | (Optional) SAM 2 model name from Hugging Face Model Hub. | `facebook/sam2.1-hiera-small` |
+| `--threshold` | (Optional) Detection confidence threshold for OWLv2 (a float between 0 and 1). | `0.1` |
+| `--fps` | (Optional) Frame sampling rate (frames per second) for video inputs. | `24` |
+| `--device` | (Optional) Compute device (`"cuda"` or `"cpu"`). | Auto-detects GPU, else `cpu` |
+| `--no-merged` | (Optional) Disables merged mode. Merged mode (where all masks are combined into a single output [image/video]) is enabled by default. | Enabled |
+| `--no-binary` | (Optional) Disables binary mask generation. Binary mask output is enabled by default. | Enabled |
+| `--no-overlay` | (Optional) Disables overlay image generation. Overlay image output (original image with masks) is enabled by default. | Enabled |
+| `--config` | (Optional) Path to a YAML configuration file to specify arguments (see Configuration). Prompts can also be a list in YAML. | `None` |
 
 ### Examples: