Update

app/app_utils.py

@@ -42,9 +42,9 @@ def preprocess_image_and_predict(inp):
             for fl in results.multi_face_landmarks:
                 startX, startY, endX, endY = get_box(fl, w, h)
                 cur_face = inp[startY:endY, startX:endX]
-                cur_face_n = pth_processing(Image.fromarray(cur_face)).to(config_data.DEVICE)
+                cur_face_n = pth_processing(Image.fromarray(cur_face))
                 prediction = (
-                    torch.nn.functional.softmax(pth_model_static(cur_face_n), dim=1).cpu()
+                    torch.nn.functional.softmax(pth_model_static(cur_face_n), dim=1)
                     .detach()
                     .numpy()[0]
                 )
@@ -91,8 +91,8 @@ def preprocess_video_and_predict(video):
                     cur_face = frame_copy[startY:endY, startX: endX]
 
                     if (count_frame-1)%config_data.FRAME_DOWNSAMPLING == 0:
-                        cur_face_copy = pth_processing(Image.fromarray(cur_face)).to(config_data.DEVICE)
-                        features = torch.nn.functional.relu(pth_model_static.extract_features(cur_face_copy)).cpu().detach().numpy()
+                        cur_face_copy = pth_processing(Image.fromarray(cur_face))
+                        features = torch.nn.functional.relu(pth_model_static.extract_features(cur_face_copy)).detach().numpy()
         
                         if len(lstm_features) == 0:
                             lstm_features = [features]*10
@@ -100,8 +100,8 @@ def preprocess_video_and_predict(video):
                             lstm_features = lstm_features[1:] + [features]
 
                         lstm_f = torch.from_numpy(np.vstack(lstm_features))
-                        lstm_f = torch.unsqueeze(lstm_f, 0).to(config_data.DEVICE)
-                        output = pth_model_dynamic(lstm_f).cpu().detach().numpy()
+                        lstm_f = torch.unsqueeze(lstm_f, 0)
+                        output = pth_model_dynamic(lstm_f).detach().numpy()
                         last_output = output
                     else:
                         if last_output is not None:

app/model.py

@@ -27,9 +27,9 @@ def load_model(model_url, model_path):
         return None
 
 
-pth_model_static = load_model(config_data.model_static_url, config_data.model_static_path).to(config_data.DEVICE)
+pth_model_static = load_model(config_data.model_static_url, config_data.model_static_path)
 
-pth_model_dynamic = load_model(config_data.model_dynamic_url, config_data.model_dynamic_path).to(config_data.DEVICE)
+pth_model_dynamic = load_model(config_data.model_dynamic_url, config_data.model_dynamic_path)
 
 
 

config.toml

@@ -1,5 +1,4 @@
 APP_VERSION = "0.2.0"
-DEVICE = "cpu"
 FRAME_DOWNSAMPLING = 5
 
 [model_static]