added automodelimage

app.py

@@ -253,22 +253,23 @@ def predict_and_analyze(model_name, num_channels, dim, input_channel, image):
     # model = EfficientNetPreTrained.from_pretrained(model_loading_name)
     # model = AutoModel.from_pretrained(model_loading_name, trust_remote_code=True)
     
-    model = EfficientNet(dropout=hparams.dropout,
-                                    num_channels=hparams.num_channels,
-                                    num_classes=hparams.num_classes,
-                                    size=hparams.size,
-                                    stochastic_depth_prob=hparams.stochastic_depth_prob,
-                                    width_mult=hparams.width_mult,
-                                    depth_mult=hparams.depth_mult,)
-    
-    model_url = cached_download(hf_hub_url(model_loading_name, filename="pytorch_model.bin"))
-    print(model_url)
-    
-    loaded = torch.load(model_url, map_location='cpu')
-    print(loaded)
-    
-    model.load_state_dict(loaded)
-    print(model)
+    model = AutoModelForImageClassification.from_pretrained(model_loading_name)
+    
+    # model = EfficientNet(dropout=hparams.dropout,
+    #                                 num_channels=hparams.num_channels,
+    #                                 num_classes=hparams.num_classes,
+    #                                 size=hparams.size,
+    #                                 stochastic_depth_prob=hparams.stochastic_depth_prob,
+    #                                 width_mult=hparams.width_mult,
+    #                                 depth_mult=hparams.depth_mult,)
+    # model_url = cached_download(hf_hub_url(model_loading_name, filename="pytorch_model.bin"))
+    # print(model_url)
+    
+    # loaded = torch.load(model_url, map_location='cpu')
+    # print(loaded)
+    
+    # model.load_state_dict(loaded)
+    # print(model)
     
     # model = EfficientNetPreTrained(config)
     # config.register_for_auto_class()