Update app.py

app.py

@@ -103,7 +103,7 @@ model = AutoModel.from_pretrained(
 
 tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
 # set the max number of tiles in `max_num`
-pixel_values = load_image('./examples/image1.jpg', max_num=6).to(torch.bfloat16).cuda()
+pixel_values = load_image('./examples/Screenshot 2024-05-15 212157.png', max_num=6).to(torch.bfloat16).cuda()
 
 generation_config = dict(
     num_beams=1,
@@ -126,8 +126,8 @@ response, history = model.chat(tokenizer, pixel_values, question, generation_con
 print(question, response)
 
 # multi-round multi-image conversation
-pixel_values1 = load_image('./examples/image1.jpg', max_num=6).to(torch.bfloat16).cuda()
-pixel_values2 = load_image('./examples/image2.jpg', max_num=6).to(torch.bfloat16).cuda()
+pixel_values1 = load_image('./examples/Screenshot 2024-05-15 212157.png', max_num=6).to(torch.bfloat16).cuda()
+pixel_values2 = load_image('./examples/Screenshot 2024-05-15 222516.png', max_num=6).to(torch.bfloat16).cuda()
 pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)
 
 question = "详细描述这两张图片" # Describe the two pictures in detail
@@ -139,8 +139,8 @@ response, history = model.chat(tokenizer, pixel_values, question, generation_con
 print(question, response)
 
 # batch inference (single image per sample)
-pixel_values1 = load_image('./examples/image1.jpg', max_num=6).to(torch.bfloat16).cuda()
-pixel_values2 = load_image('./examples/image2.jpg', max_num=6).to(torch.bfloat16).cuda()
+pixel_values1 = load_image('./examples/Screenshot 2024-05-15 212157.png', max_num=6).to(torch.bfloat16).cuda()
+pixel_values2 = load_image('./examples/Screenshot 2024-05-15 222516.png', max_num=6).to(torch.bfloat16).cuda()
 image_counts = [pixel_values1.size(0), pixel_values2.size(0)]
 pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)