Update app.py

app.py

@@ -11,6 +11,19 @@ chk_point = "kdhht2334/autotrain-diffusion-emotion-facial-expression-recognition
 
 model = AutoModelForImageClassification.from_pretrained(chk_point)
 
+emotion_dict = {
+'neutral': '0',
+'happy': '1',
+'sad' :'2',
+'surprise': '3',
+'fear': '4',
+'disgust': '5',
+'angry': '6',
+'uncertain': '7',
+'nonface': '8',
+}
+
+
 try:
     pipe = pipeline(
         "image-classification",
@@ -24,34 +37,46 @@ except NotImplementedError:
     pipe = pipeline("image-classification", chk_point, device=device)
 
 
-def make_label_folders():
-    folders = model.config.label2id.keys()
-    for folder in folders:
-        folder = Path(folder)
-        if not folder.exists():
-            folder.mkdir()
-    return folders
-
-
-def predictions_into_folders(files):
-    files = [file.name for file in files]
-    files = [
-        file for file in files if not file.startswith(".") and "DS_Store" not in file
-    ]
-    folders = make_label_folders()
-    predictions = pipe(files)
-    for file, prediction in zip(files, predictions):
-        label = prediction[0]["label"]
-        file_name = Path(file).name
-        shutil.copy(file, f"{label}/{file_name}")
-    for folder in folders:
-        shutil.make_archive(folder, "zip", ".", folder)
-    return [f"{folder}.zip" for folder in folders]
-
-demo = gr.Interface(
-    predictions_into_folders,
-    gr.Files(file_count="directory", file_types=["image"]),
-    gr.Files(),
-    cache_examples=True,
-)
-demo.launch(enable_queue=True)
+# def make_label_folders():
+#     folders = model.config.label2id.keys()
+#     for folder in folders:
+#         folder = Path(folder)
+#         if not folder.exists():
+#             folder.mkdir()
+#     return folders
+
+
+# def predictions_into_folders(files):
+#     files = [file.name for file in files]
+#     files = [
+#         file for file in files if not file.startswith(".") and "DS_Store" not in file
+#     ]
+#     folders = make_label_folders()
+#     predictions = pipe(files)
+#     for file, prediction in zip(files, predictions):
+#         label = prediction[0]["label"]
+#         file_name = Path(file).name
+#         shutil.copy(file, f"{label}/{file_name}")
+#     for folder in folders:
+#         shutil.make_archive(folder, "zip", ".", folder)
+#     return [f"{folder}.zip" for folder in folders]
+
+# demo = gr.Interface(
+#     predictions_into_folders,
+#     gr.Files(file_count="directory", file_types=["image"]),
+#     gr.Files(),
+#     cache_examples=True,
+# )
+# demo.launch(enable_queue=True)
+
+
+def predict(image):
+    predictions = pipe(image)
+    return {p["label"]: p["score"] for p in predictions}
+
+gr.Interface(
+    predict,
+    inputs=gr.inputs.Image(label="Upload image", type="filepath"),
+    outputs=gr.outputs.Label(num_top_classes=7),
+    title="FER trained on DiffusionFER dataset",
+).launch()