Merge pull request #15 from inaturalist/ci

Adding Tests

.github/workflows/CI.yml

@@ -0,0 +1,34 @@
+name: inatVisionAPI CI
+
+on: [push, pull_request]
+
+jobs:
+  build:
+    runs-on: ubuntu-20.04
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Use Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.11.6'
+          cache: 'pip'
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt
+      - name: Test with pytest
+        run: |
+          coverage run -m pytest -s && coverage report --show-missing
+
+  notify:
+    name: Notify Slack
+    needs: build
+    if: ${{ success() || failure() }}
+    runs-on: ubuntu-20.04
+    steps:
+      - uses: iRoachie/[email protected]
+        if: env.SLACK_WEBHOOK_URL != null
+        env:
+          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_BUILDS_WEBHOOK_URL }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/CICD-dev.yml

@@ -8,26 +8,26 @@ on:
 
 jobs:
   build-and-test:
-    name: Build/Test 
+    name: Build/Test
     runs-on: ubuntu-20.04
-    steps:    
+    steps:
     - uses: actions/checkout@v4
 
   build-and-push-dev-docker-image:
-    name: Build/Push Dev Docker Image 
+    name: Build/Push Dev Docker Image
     runs-on: ubuntu-20.04
-    steps:    
+    steps:
     - uses: actions/checkout@v4
 
     - name: Login to Docker Hub
       uses: docker/login-action@v3
       with:
         username: ${{ secrets.DOCKERHUB_USERNAME }}
-        password: ${{ secrets.DOCKERHUB_TOKEN }}  
-    
+        password: ${{ secrets.DOCKERHUB_TOKEN }}
+
     - name: Set up Docker Buildx
       uses: docker/setup-buildx-action@v3
-    
+
     - name: Build/Push dev vision-api
       uses: docker/build-push-action@v5
       with:

.github/workflows/CICD-main.yml

@@ -7,26 +7,26 @@ on:
 
 jobs:
   build-and-test:
-    name: Build/Test 
+    name: Build/Test
     runs-on: ubuntu-20.04
-    steps:    
+    steps:
     - uses: actions/checkout@v4
 
   build-and-push-staging-docker-image:
-    name: Build/Push Staging Docker Image 
+    name: Build/Push Staging Docker Image
     runs-on: ubuntu-20.04
-    steps:    
+    steps:
     - uses: actions/checkout@v4
 
     - name: Login to Docker Hub
       uses: docker/login-action@v3
       with:
         username: ${{ secrets.DOCKERHUB_USERNAME }}
-        password: ${{ secrets.DOCKERHUB_TOKEN }}  
-    
+        password: ${{ secrets.DOCKERHUB_TOKEN }}
+
     - name: Set up Docker Buildx
       uses: docker/setup-buildx-action@v3
-    
+
     - name: Build/Push staging vision-api
       uses: docker/build-push-action@v5
       with:

docker/logrotate-cron.sh

@@ -1,2 +1,2 @@
 #!/bin/sh
-/usr/sbin/logrotate -s /var/vision/script/logrotate.status /var/vision/script/logrotate.conf 
+/usr/sbin/logrotate -s /var/vision/script/logrotate.status /var/vision/script/logrotate.conf

lib/inat_inferrer.py

@@ -24,6 +24,7 @@ class InatInferrer:
     def __init__(self, config):
         self.config = config
         self.setup_taxonomy(config)
+        self.setup_synonyms(config)
         self.setup_vision_model(config)
         self.setup_elevation_dataframe(config)
         self.setup_geo_model(config)
@@ -35,8 +36,15 @@ def setup_taxonomy(self, config):
             config["tf_elev_thresholds"] if "tf_elev_thresholds" in config else None
         )
 
+    def setup_synonyms(self, config):
+        self.synonyms = None
+        if "synonyms_path" in config:
+            if not os.path.exists(config["synonyms_path"]):
+                return None
+            self.synonyms = pd.read_csv(config["synonyms_path"])
+
     def setup_vision_model(self, config):
-        self.vision_inferrer = VisionInferrer(config["vision_model_path"], self.taxonomy)
+        self.vision_inferrer = VisionInferrer(config["vision_model_path"])
 
     def setup_elevation_dataframe(self, config):
         self.geo_elevation_cells = None
@@ -72,20 +80,6 @@ def setup_geo_model(self, config):
                 elevation=list(self.geo_elevation_cells.elevation)
             )
 
-    def prepare_image_for_inference(self, file_path):
-        mime_type = magic.from_file(file_path, mime=True)
-        # attempt to convert non jpegs
-        if mime_type != "image/jpeg":
-            im = Image.open(file_path)
-            image = im.convert("RGB")
-        else:
-            image = tf.io.read_file(file_path)
-            image = tf.image.decode_jpeg(image, channels=3)
-        image = tf.image.convert_image_dtype(image, tf.float32)
-        image = tf.image.central_crop(image, 0.875)
-        image = tf.image.resize(image, [299, 299], tf.image.ResizeMethod.NEAREST_NEIGHBOR)
-        return tf.expand_dims(image, 0)
-
     def vision_predict(self, image, debug=False):
         if debug:
             start_time = time.time()
@@ -125,7 +119,7 @@ def predictions_for_image(self, file_path, lat, lng, filter_taxon, score_without
                               debug=False):
         if debug:
             start_time = time.time()
-        image = self.prepare_image_for_inference(file_path)
+        image = InatInferrer.prepare_image_for_inference(file_path)
         raw_vision_scores = self.vision_predict(image, debug)
         raw_geo_scores = self.geo_model_predict(lat, lng, debug)
         top100 = self.combine_results(raw_vision_scores, raw_geo_scores, filter_taxon,
@@ -359,6 +353,21 @@ def h3_04_bounds(self, taxon_id):
             "nelng": geomodel_results["lng"].max()
         }
 
+    @staticmethod
+    def prepare_image_for_inference(file_path):
+        mime_type = magic.from_file(file_path, mime=True)
+        # attempt to convert non jpegs
+        if mime_type != "image/jpeg":
+            im = Image.open(file_path)
+            image = im.convert("RGB")
+        else:
+            image = tf.io.read_file(file_path)
+            image = tf.image.decode_jpeg(image, channels=3)
+        image = tf.image.convert_image_dtype(image, tf.float32)
+        image = tf.image.central_crop(image, 0.875)
+        image = tf.image.resize(image, [299, 299], tf.image.ResizeMethod.NEAREST_NEIGHBOR)
+        return tf.expand_dims(image, 0)
+
     @staticmethod
     def add_lat_lng_to_h3_geo_dataframe(geo_df):
         geo_df = geo_df.h3.h3_to_geo()
@@ -373,7 +382,7 @@ def filter_geo_dataframe_by_bounds(geo_df, bounds):
         # centroid outside the bounds while part of the polygon is within the bounds. Add
         # a small buffer to ensure this returns any cell whose polygon is
         # even partially within the bounds
-        buffer = 0.6
+        buffer = 1.3
 
         # similarly, the centroid may be on the other side of the antimedirian, so lookup
         # cells that might be just over the antimeridian on either side