Fix error downloading model files.

Author: UPstartDeveloper

app/config.yaml

@@ -1,5 +1,5 @@
 resize_shape: [256, 256]
 targets: ['Fire_Images']
 model_paths: ["fire_classifier_params.h5", "fire_classifier_layers.json"]
-model_file_urls: ["https://github.com/UPstartDeveloper/Fire-Detection-API/releases/download/v0.0.2/fire_classifier_params.h5", "https://github.com/UPstartDeveloper/Fire-Detection-API/releases/download/v0.0.2/fire_classifier_layers.json"]
+base_model_url: "https://github.com/UPstartDeveloper/Fire-Detection-API/releases/download/v0.0.2"
 model_sha256: "26f32ae0666bbb83e11968935db0ec2ab06623d1"

fire_classifier/predictor.py

@@ -3,43 +3,46 @@
 import numpy as np
 from typing import List
 import yaml
-from tensorflow.keras.models import load_model
 
 from fire_classifier.preprocessing_utilities import (
     read_img_from_path,
     read_from_file,
 )
-from fire_classifier.utils import download_model
+from fire_classifier.utils import download_model, load_model
 
 
 class ImagePredictor:
     def __init__(
-        self, model_paths: List[str], resize_size: List[int], targets: List[str]
+        self, model_paths: List[str], resize_size: List[int], 
+        base_download_url: str, targets: List[str]
     ):
         self.model_paths = model_paths
-        self.model = load_model(self.model_paths)
         self.resize_size = resize_size
+        self.model = load_model(base_download_url, self.model_paths)
         self.targets = targets
 
     @classmethod
     def init_from_config_path(cls, config_path):
+        # load details for setting up the model
         with open(config_path, "r") as f:
             config = yaml.load(f, yaml.SafeLoader)
+        # use the config data, to integrate the model into the new object
         predictor = cls(
             model_paths=config["model_paths"],
             resize_size=config["resize_shape"],
+            base_download_url=config["base_model_url"],
             targets=config["targets"],
         )
         return predictor
 
     @classmethod
     def init_from_config_url(cls, config_path):
-        with open(config_path, "r") as f:
-            config = yaml.load(f, yaml.SafeLoader)
+        # with open(config_path, "r") as f:
+        #     config = yaml.load(f, yaml.SafeLoader)
 
-        download_model(
-            config["model_file_urls"], config["model_paths"], config["model_sha256"]
-        )
+        # download_model(
+        #     config["model_file_urls"], config["model_paths"], config["model_sha256"]
+        # )
 
         return cls.init_from_config_path(config_path)
 

fire_classifier/utils.py

@@ -12,19 +12,33 @@ def get_hash(filename):
     return sha256_hash.hexdigest()
 
 
-def download_model(urls, file_paths, file_sha256):
+def download_model(url, file_paths, file_sha256=None):
     params_file, layers_file = file_paths
-    params_url, layers_url = urls
-    if (
-        os.path.exists(params_file)
-        and os.path.exists(layers_file)
-        and get_hash(layers_file) == file_sha256
+    params_url, layers_url = (
+        f"{url}/{params_file}",
+        f"{url}/{layers_file}"
+    )
+    if (os.path.exists(params_file) and os.path.exists(layers_file)
+        # and get_hash(layers_file) == file_sha256
     ):
         print("File already exists")
-    else:
+    else:  # download the model
         keras.utils.get_file(
-            origin=params_url, fname=params_file, cache_subdir=""
+            origin=layers_url, fname=layers_file,
+            cache_dir='.', cache_subdir="./model"
         )
         keras.utils.get_file(
-            origin=layers_url, fname=layers_file, cache_subdir=""
+            origin=params_url, fname=params_file,
+            cache_dir='.', cache_subdir="./model"
         )
+
+def load_model(url, file_paths):
+    '''Model reconstruction using H5 + JSON'''
+    # First download the model, if needed
+    download_model(url, file_paths)
+    params_file, layers_file = file_paths
+    # Model reconstruction
+    with open(f"./model/{layers_file}") as f:
+        model = keras.models.model_from_json(f.read())
+        model.load_weights(f"./model/{params_file}")
+    return model