Update app.py

app.py

@@ -3,14 +3,19 @@ import torch
 import numpy as np
 from transformers import DPTForDepthEstimation, DPTImageProcessor
 import gradio as gr
+import torch.quantization
 
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-model = DPTForDepthEstimation.from_pretrained("Intel/dpt-swinv2-tiny-256", torch_dtype=torch.float16).to(device)
+model = DPTForDepthEstimation.from_pretrained("Intel/dpt-swinv2-tiny-256", torch_dtype=torch.float32)
+model.eval()
+model = torch.quantization.quantize_dynamic(
+    model, {torch.nn.Linear, torch.nn.Conv2d}, dtype=torch.qint8
+).to(device)
 processor = DPTImageProcessor.from_pretrained("Intel/dpt-swinv2-tiny-256")
 
 color_map = cv2.applyColorMap(np.arange(256, dtype=np.uint8), cv2.COLORMAP_INFERNO)
 
-input_tensor = torch.zeros((1, 3, 128, 128), dtype=torch.float16, device=device)
+input_tensor = torch.zeros((1, 3, 128, 128), dtype=torch.float32, device=device)
 depth_map = np.zeros((128, 128), dtype=np.float32)
 depth_map_colored = np.zeros((128, 128, 3), dtype=np.uint8)