bigger model time

app.py

@@ -5,7 +5,7 @@ import os
 import cv2
 import uuid
 import time
-import spaces
+#import spaces
 import subprocess
 import matplotlib
 matplotlib.use('Agg')
@@ -26,7 +26,7 @@ from huggingface_hub import HfApi
 
 plt.style.use('dark_background')
 
-onnx_file = hf_hub_download(repo_id="dylanplummer/ropenet", filename="model.onnx", repo_type="model", token=os.environ['DATASET_SECRET'])
+onnx_file = hf_hub_download(repo_id="dylanplummer/ropenet", filename="nextjump.onnx", repo_type="model", token=os.environ['DATASET_SECRET'])
 # model_xml = hf_hub_download(repo_id="dylanplummer/ropenet", filename="model.xml", repo_type="model", token=os.environ['DATASET_SECRET'])
 # hf_hub_download(repo_id="dylanplummer/ropenet", filename="model.mapping", repo_type="model", token=os.environ['DATASET_SECRET'])
 #model_xml = "model_ir/model.xml"
@@ -51,9 +51,9 @@ def sigmoid(x):
     return 1 / (1 + np.exp(-x))
 
 
-@spaces.GPU()
+#@spaces.GPU()
 def inference(x, count_only_api, api_key, 
-              img_size=224, seq_len=64, stride_length=32, stride_pad=3, batch_size=4, 
+              img_size=288, seq_len=64, stride_length=32, stride_pad=3, batch_size=4, 
               miss_threshold=0.8, marks_threshold=0.6, median_pred_filter=True, center_crop=True, both_feet=True, 
               api_call=False,
               progress=gr.Progress()):
@@ -138,7 +138,7 @@ def inference(x, count_only_api, api_key,
         idx_list.append(i)
         if len(batch_list) == batch_size:
             batch_X = torch.cat(batch_list)
-            outputs = ort_sess.run(None, {'frames': batch_X.numpy()})
+            outputs = ort_sess.run(None, {'video': batch_X.numpy()})
             y1pred = outputs[0]
             y2pred = outputs[1]
             y3pred = outputs[2]
@@ -162,7 +162,7 @@ def inference(x, count_only_api, api_key,
             batch_list.append(batch_list[-1])
             idx_list.append(idx_list[-1])
         batch_X = torch.cat(batch_list)
-        outputs = ort_sess.run(None, {'frames': batch_X.numpy()})
+        outputs = ort_sess.run(None, {'video': batch_X.numpy()})
         y1pred = outputs[0]
         y2pred = outputs[1]
         y3pred = outputs[2]