[bug] fix wrong latlng to xy pixel conversion, update .gitignore and .dockerignore

.dockerignore

@@ -4,4 +4,5 @@ __cache__
 .idea
 tmp/
 .env*
-__pycache__
+__pycache__
+.DS_Store

.gitignore

@@ -4,4 +4,5 @@ __cache__
 .idea
 tmp/
 .env*
-*.onnx
+*.onnx
+.DS_Store

src/app.py

@@ -1,15 +1,17 @@
 import json
 import time
 from http import HTTPStatus
+from pathlib import Path
 from typing import Dict
 
 from aws_lambda_powertools.event_handler import content_types
 from aws_lambda_powertools.utilities.typing import LambdaContext
 
 from src import app_logger
-from src.io.coordinates_pixel_conversion import get_latlng_to_pixel_coordinates
+from src.io.coordinates_pixel_conversion import get_latlng_to_pixel_coordinates, get_point_latlng_to_pixel_coordinates
 from src.prediction_api.predictors import samexporter_predict
-from src.utilities.constants import CUSTOM_RESPONSE_MESSAGES
+from src.utilities.constants import CUSTOM_RESPONSE_MESSAGES, ROOT
+from src.utilities.serialize import serialize
 from src.utilities.utilities import base64_decode
 
 
@@ -57,20 +59,29 @@ def get_parsed_bbox_points(request_input: Dict) -> Dict:
     for prompt in request_input["prompt"]:
         app_logger.info(f"current prompt: {type(prompt)}, value:{prompt}.")
         data = prompt["data"]
-        app_logger.info(f"current data points: {type(data)}, value:{data}.")
-        data_ne = data["ne"]
-        app_logger.info(f"current data_ne point: {type(data_ne)}, value:{data_ne}.")
-        data_sw = data["sw"]
-        app_logger.info(f"current data_sw point: {type(data_sw)}, value:{data_sw}.")
-
-        diff_pixel_coords_origin_data_ne = get_latlng_to_pixel_coordinates(ne, data_ne, zoom, "ne")
-        app_logger.info(f'current diff prompt ne: {type(data)}, {data} => {diff_pixel_coords_origin_data_ne}.')
-        diff_pixel_coords_origin_data_sw = get_latlng_to_pixel_coordinates(ne, data_sw, zoom, "sw")
-        app_logger.info(f'current diff prompt sw: {type(data)}, {data} => {diff_pixel_coords_origin_data_sw}.')
-        prompt["data"] = [
-            diff_pixel_coords_origin_data_ne["x"], diff_pixel_coords_origin_data_ne["y"],
-            diff_pixel_coords_origin_data_sw["x"], diff_pixel_coords_origin_data_sw["y"]
-        ]
+        if prompt["type"] == "rectangle":
+            app_logger.info(f"current data points: {type(data)}, value:{data}.")
+            data_ne = data["ne"]
+            app_logger.info(f"current data_ne point: {type(data_ne)}, value:{data_ne}.")
+            data_sw = data["sw"]
+            app_logger.info(f"current data_sw point: {type(data_sw)}, value:{data_sw}.")
+
+            diff_pixel_coords_origin_data_ne = get_latlng_to_pixel_coordinates(ne, sw, data_ne, zoom, "ne")
+            app_logger.info(f'current diff prompt ne: {type(data)}, {data} => {diff_pixel_coords_origin_data_ne}.')
+            diff_pixel_coords_origin_data_sw = get_latlng_to_pixel_coordinates(ne, sw, data_sw, zoom, "sw")
+            app_logger.info(f'current diff prompt sw: {type(data)}, {data} => {diff_pixel_coords_origin_data_sw}.')
+            prompt["data"] = [
+                diff_pixel_coords_origin_data_ne["x"], diff_pixel_coords_origin_data_ne["y"],
+                diff_pixel_coords_origin_data_sw["x"], diff_pixel_coords_origin_data_sw["y"]
+            ]
+        elif prompt["type"] == "point":
+            current_point = get_latlng_to_pixel_coordinates(ne, sw, data, zoom, "point")
+            app_logger.info(f"current prompt: {type(current_point)}, value:{current_point}.")
+            new_prompt_data = [current_point['x'], current_point['y']]
+            app_logger.info(f"new_prompt_data: {type(new_prompt_data)}, value:{new_prompt_data}.")
+            prompt["data"] = new_prompt_data
+        else:
+            raise ValueError("valid prompt types are only 'point' and 'rectangle'")
 
     app_logger.info(f"bbox => {bbox}.")
     app_logger.info(f'## request_input["prompt"] updated => {request_input["prompt"]}.')
@@ -110,9 +121,13 @@ def lambda_handler(event: dict, context: LambdaContext):
         app_logger.info(f"body, #2: {type(body)}, {body}...")
 
         try:
+            prompt_latlng = body["prompt"]
+            app_logger.info(f"prompt_latlng:{prompt_latlng}.")
             body_request = get_parsed_bbox_points(body)
             app_logger.info(f"body_request=> {type(body_request)}, {body_request}.")
-            body_response = samexporter_predict(body_request["bbox"], body_request["prompt"], body_request["zoom"])
+            body_response = samexporter_predict(
+                body_request["bbox"], body_request["prompt"], body_request["zoom"], prompt_latlng
+            )
             app_logger.info(f"output body_response:{body_response}.")
             response = get_response(HTTPStatus.OK.value, start_time, context.aws_request_id, body_response)
         except Exception as ex2:

src/io/coordinates_pixel_conversion.py

@@ -45,17 +45,16 @@ def get_point_latlng_to_pixel_coordinates(latlng, zoom: int) -> PixelCoordinate:
         raise e_format_latlng_to_pixel_coordinates
 
 
-def get_latlng_to_pixel_coordinates(latlng_origin, latlng_current_point, zoom, k: str):
-    # latlng_origin_list = get_latlng_coords_list(latlng_origin, k)
-    # latlng_current_point_list = get_latlng_coords_list(latlng_current_point, k)
-    app_logger.info(f"latlng_origin - {k}: {type(latlng_origin)}, value:{latlng_origin}.")
+def get_latlng_to_pixel_coordinates(latlng_origin_ne, latlng_origin_sw, latlng_current_point, zoom, k: str):
+    app_logger.info(f"latlng_origin - {k}: {type(latlng_origin_ne)}, value:{latlng_origin_ne}.")
     app_logger.info(f"latlng_current_point - {k}: {type(latlng_current_point)}, value:{latlng_current_point}.")
-    latlng_map_origin = get_point_latlng_to_pixel_coordinates(latlng_origin, zoom)
+    latlng_map_origin_ne = get_point_latlng_to_pixel_coordinates(latlng_origin_ne, zoom)
+    latlng_map_origin_sw = get_point_latlng_to_pixel_coordinates(latlng_origin_sw, zoom)
     latlng_map_current_point = get_point_latlng_to_pixel_coordinates(latlng_current_point, zoom)
-    diff_coord_x = abs(latlng_map_origin["x"] - latlng_map_current_point["x"])
-    diff_coord_y = abs(latlng_map_origin["y"] - latlng_map_current_point["y"])
+    diff_coord_x = abs(latlng_map_origin_sw["x"] - latlng_map_current_point["x"])
+    diff_coord_y = abs(latlng_map_origin_ne["y"] - latlng_map_current_point["y"])
     point = PixelCoordinate(x=diff_coord_x, y=diff_coord_y)
-    app_logger.info(f"point - {k}: {point}.")
+    app_logger.info(f"point type - {k}: {point}.")
     return point
 
 

src/prediction_api/predictors.py

@@ -100,28 +100,27 @@ def samexporter_predict(bbox, prompt: list[dict], zoom: float = ZOOM, model_name
         )
         app_logger.info(f"saved prediction_masks:{prediction_masks_output}.")
 
-        # mask = np.zeros((prediction_masks.shape[2], prediction_masks.shape[3]), dtype=np.uint8)
-        # app_logger.info(f"output mask shape:{mask.shape}, {mask.dtype}.")
-        # ## todo: convert to geojson directly within the loop to avoid merging two objects
-        # for n, m in enumerate(prediction_masks[0, :, :, :]):
-        #     app_logger.info(f"## {n} mask => m shape:{mask.shape}, {mask.dtype}.")
-        #     mask[m > 0.0] = 255
-        prediction_masks0 = prediction_masks[0]
-        app_logger.info(f"prediction_masks0 shape:{prediction_masks0.shape}.")
-
-        try:
-            pmf = np.sum(prediction_masks0, axis=0).astype(np.uint8)
-        except Exception as e_sum_pmf:
-            app_logger.error(f"e_sum_pmf:{e_sum_pmf}.")
-            pmf = prediction_masks0[0]
-        app_logger.info(f"creating pil image from prediction mask with shape {pmf.shape}.")
-        pil_pmf = Image.fromarray(pmf)
-        pil_pmf_output = f"/tmp/pil_pmf_{pmf.shape[0]}_{pmf.shape[1]}.png"
-        pil_pmf.save(pil_pmf_output)
-        app_logger.info(f"saved pil_pmf:{pil_pmf_output}.")
-
-        mask = np.zeros(pmf.shape, dtype=np.uint8)
-        mask[pmf > 0] = 255
+        mask = np.zeros((prediction_masks.shape[2], prediction_masks.shape[3]), dtype=np.uint8)
+        app_logger.info(f"output mask shape:{mask.shape}, {mask.dtype}.")
+        for n, m in enumerate(prediction_masks[0, :, :, :]):
+            app_logger.info(f"## {n} mask => m shape:{mask.shape}, {mask.dtype}.")
+            mask[m > 0.0] = 255
+        # prediction_masks0 = prediction_masks[0]
+        # app_logger.info(f"prediction_masks0 shape:{prediction_masks0.shape}.")
+        #
+        # try:
+        #     pmf = np.sum(prediction_masks0, axis=0).astype(np.uint8)
+        # except Exception as e_sum_pmf:
+        #     app_logger.error(f"e_sum_pmf:{e_sum_pmf}.")
+        #     pmf = prediction_masks0[0]
+        # app_logger.info(f"creating pil image from prediction mask with shape {pmf.shape}.")
+        # pil_pmf = Image.fromarray(pmf)
+        # pil_pmf_output = f"/tmp/pil_pmf_{pmf.shape[0]}_{pmf.shape[1]}.png"
+        # pil_pmf.save(pil_pmf_output)
+        # app_logger.info(f"saved pil_pmf:{pil_pmf_output}.")
+        #
+        # mask = np.zeros(pmf.shape, dtype=np.uint8)
+        # mask[pmf > 0] = 255
 
         # cv2.imwrite(f"/tmp/cv2_mask_predicted_{mask.shape[0]}_{mask.shape[1]}_{mask.shape[2]}.png", mask)
         pil_mask = Image.fromarray(mask)