doing create_a_model method

app.py

@@ -203,7 +203,7 @@ def predict_and_analyze(model_name, num_channels, dim, input_channel, image):
     print("Data loaded")
     
     print("Loading model")
-    model_loading_name = "%s_%i_planet_detection" % (model_name, num_channels)
+    model_loading_name = model_path + "%s_%i_planet_detection" % (model_name, num_channels)
     
     if 'eff' in model_name:
         hparams = effnet_hparams[num_channels]
@@ -220,21 +220,20 @@ def predict_and_analyze(model_name, num_channels, dim, input_channel, image):
                                     depth_mult=hparams.depth_mult,
         )
     
-    config.save_pretrained(model_loading_name)
-    config = EfficientNetConfig.from_pretrained(model_loading_name)
+    config.save_pretrained(save_directory=model_loading_name)
+    # config = EfficientNetConfig.from_pretrained(model_loading_name)
     
-    model = EfficientNetPreTrained(config)
+    model = EfficientNetPreTrained.from_pretrained(model_loading_name + '/config.json')
     
+    # model = EfficientNetPreTrained(config)
     # config.register_for_auto_class()
     # model.register_for_auto_class("AutoModelForImageClassification")
-
-    pretrained_model = timm.create_model(model_loading_name, pretrained=True)
-    model.model.load_state_dict(pretrained_model.state_dict())
-    
+    # pretrained_model = timm.create_model(model_loading_name, pretrained=True)
+    # model.model.load_state_dict(pretrained_model.state_dict())
     # pipeline = pipeline(task="image-classification", model=model_loading_name)
-        
     # model = load_model(model_name, activation=True)
     # model = AutoModel.from_pretrained(model_loading_name)
+    
     print("Model loaded")
     
     print("Looking at activations")