feat: hash used as identifier

src/classifier/classifier_image.py

@@ -12,21 +12,20 @@ from utils.grid_maker import gridder
 from utils.metadata_handler import metadata2md
 
 def cetacean_classify(cetacean_classifier):
-    files = st.session_state.files
     images = st.session_state.images
     observations = st.session_state.observations
-
-    batch_size, row_size, page = gridder(files)
+    hashes = st.session_state.image_hashes
+    batch_size, row_size, page = gridder(hashes)
     
     grid = st.columns(row_size)
     col = 0
-
-    for file in files: 
-        image = images[file.name]
+    o=1
+    for hash in hashes: 
+        image = images[hash]
         
         with grid[col]:
             st.image(image, use_column_width=True)
-            observation = observations[file.name].to_dict()
+            observation = observations[hash].to_dict()
             # run classifier model on `image`, and persistently store the output
             out = cetacean_classifier(image) # get top 3 matches
             st.session_state.whale_prediction1 = out['predictions'][0]
@@ -44,14 +43,14 @@ def cetacean_classify(cetacean_classifier):
                 # get index of pred1 from WHALE_CLASSES, none if not present
                 print(f"[D] pred1: {pred1}")
                 ix = viewer.WHALE_CLASSES.index(pred1) if pred1 in viewer.WHALE_CLASSES else None
-                selected_class = st.selectbox(f"Species for {file.name}", viewer.WHALE_CLASSES, index=ix)
+                selected_class = st.selectbox(f"Species for observation {str(o)}", viewer.WHALE_CLASSES, index=ix)
             
             observation['predicted_class'] = selected_class
             if selected_class != st.session_state.whale_prediction1:
                 observation['class_overriden'] = selected_class
             
             st.session_state.public_observation = observation
-            st.button(f"Upload observation for {file.name} to THE INTERNET!", on_click=push_observations)
+            st.button(f"Upload observation {str(o)} to THE INTERNET!", on_click=push_observations)
             # TODO: the metadata only fills properly if `validate` was clicked.
             st.markdown(metadata2md())
 
@@ -62,7 +61,8 @@ def cetacean_classify(cetacean_classifier):
 
             whale_classes = out['predictions'][:]
             # render images for the top 3 (that is what the model api returns)
-            st.markdown(f"Top 3 Predictions for {file.name}")
+            st.markdown(f"Top 3 Predictions for observation {str(o)}")
             for i in range(len(whale_classes)):
                 viewer.display_whale(whale_classes, i)
+        o += 1
         col = (col + 1) % row_size

src/input/input_handling.py

@@ -66,6 +66,7 @@ def setup_input(
     uploaded_files = viewcontainer.file_uploader("Upload an image", type=allowed_image_types, accept_multiple_files=True)
     observations = {}
     images = {}
+    image_hashes =[]
     if uploaded_files is not None:
         for file in uploaded_files:
 
@@ -108,11 +109,13 @@ def setup_input(
             observation = InputObservation(image=file, latitude=latitude, longitude=longitude, 
                                         author_email=author_email, date=image_datetime, time=None, 
                                         date_option=date_option, time_option=time_option)
-            observations[file.name] = observation
-            images[file.name] = image
+            image_hash = observation.to_dict()["image_md5"]
+            observations[image_hash] = observation
+            images[image_hash] = image
+            image_hashes.append(image_hash)
     
     st.session_state.images = images
     st.session_state.files = uploaded_files
-
-    return observations
+    st.session_state.observations = observations
+    st.session_state.image_hashes = image_hashes
 

src/input/input_validator.py

@@ -96,7 +96,8 @@ def decimal_coords(coords:tuple, ref:str) -> Fraction:
     return decimal_degrees
 
 
-def get_image_latlon(image_file: UploadedFile) -> tuple[float, float] | None:
+#def get_image_latlon(image_file: UploadedFile) -> tuple[float, float] | None:
+def get_image_latlon(image_file: UploadedFile) :
     """
     Extracts the latitude and longitude from the EXIF metadata of an uploaded image file.
 

src/main.py

@@ -9,6 +9,7 @@ from streamlit_folium import st_folium
 from transformers import pipeline
 from transformers import AutoModelForImageClassification
 
+from maps.obs_map import add_header_text
 from datasets import disable_caching
 disable_caching()
 
@@ -44,6 +45,9 @@ st.set_page_config(layout="wide")
 if "handler" not in st.session_state:
     st.session_state['handler'] = setup_logging()
 
+if "image_hashes" not in st.session_state:
+    st.session_state.image_hashes = []
+
 if "observations" not in st.session_state:
     st.session_state.observations = {}
 
@@ -100,7 +104,7 @@ def main() -> None:
 
 
     # create a sidebar, and parse all the input (returned as `observations` object)
-    observations = setup_input(viewcontainer=st.sidebar)
+    setup_input(viewcontainer=st.sidebar)
 
         
     if 0:## WIP
@@ -118,7 +122,7 @@ def main() -> None:
     with tab_map:
         # visual structure: a couple of toggles at the top, then the map inlcuding a
         # dropdown for tileset selection.
-        sw_map.add_header_text()
+        add_header_text()
         tab_map_ui_cols = st.columns(2)
         with tab_map_ui_cols[0]:
             show_db_points = st.toggle("Show Points from DB", True)
@@ -179,12 +183,8 @@ def main() -> None:
     # Display submitted observation
     if st.sidebar.button("Validate"):
         # create a dictionary with the submitted observation
-        submitted_data = observations
-        st.session_state.observations = observations
-            
         tab_log.info(f"{st.session_state.observations}")
-
-        df = pd.DataFrame(submitted_data, index=[0])
+        df = pd.DataFrame(st.session_state.observations, index=[0])
         with tab_coords:
             st.table(df)
         

src/utils/grid_maker.py

@@ -1,13 +1,13 @@
 import streamlit as st
 import math
 
-def gridder(files):
+def gridder(items):
     cols = st.columns(3)
     with cols[0]:
         batch_size = st.select_slider("Batch size:",range(10,110,10), value=10)
     with cols[1]:
         row_size = st.select_slider("Row size:", range(1,6), value = 5)
-    num_batches = math.ceil(len(files)/batch_size)
+    num_batches = math.ceil(len(items)/batch_size)
     with cols[2]:
         page = st.selectbox("Page", range(1,num_batches+1))
     return batch_size, row_size, page