Update 1.py

1.py

@@ -1,4 +1,4 @@
-#%cd /workspace/tem/florence-sam
+#%cd /workspace/florence-samflorence-sam
 import os
 from typing import Tuple, Optional
 import shutil
@@ -13,8 +13,8 @@ from tqdm import tqdm
 import sys
 import json
 import pickle
-os.chdir("/workspace/florence-sam-tencent")
-sys.path.append('/workspace/florence-sam-tencent')
+os.chdir("/workspace/florence-sam")
+sys.path.append('/workspace/florence-sam')
 from utils.video import generate_unique_name, create_directory, delete_directory
 from utils.florence import load_florence_model, run_florence_inference, \
     FLORENCE_DETAILED_CAPTION_TASK, \
@@ -34,46 +34,33 @@ if torch.cuda.get_device_properties(0).major >= 8:
 FLORENCE_MODEL, FLORENCE_PROCESSOR = load_florence_model(device=DEVICE)
 SAM_IMAGE_MODEL = load_sam_image_model(device=DEVICE)
 
-with open('/workspace/tem/texts.pkl', 'rb') as file:
+with open('/workspace/florence-sam/texts.pkl', 'rb') as file:
     texts = pickle.load(file)
 print(texts)
 
-with open('/workspace/tem/output_video.pkl', 'rb') as file:
+with open('/workspace/florence-sam/output_video.pkl', 'rb') as file:
     output_video = pickle.load(file)
 print(output_video)
 
 VIDEO_SCALE_FACTOR = 1
-VIDEO_TARGET_DIRECTORY = "/workspace/tem/"
+VIDEO_TARGET_DIRECTORY = "/workspace/florence-sam"
 create_directory(directory_path=VIDEO_TARGET_DIRECTORY)
 
 
 video_input= output_video
-texts = ['the table', 'men','ball']
-#VIDEO_TARGET_DIRECTORY = "/workspace/tem/"
+texts = ['men','the table']
+#texts = ['men']
+#VIDEO_TARGET_DIRECTORY = "/workspace/florence-sam"
 if not video_input:
     print("Please upload a video.")
-'''
+
 frame_generator = sv.get_video_frames_generator(video_input)
 frame = next(frame_generator)
 frame = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
-'''
-
 
-frame_generator = sv.get_video_frames_generator(video_input)
 
-# 获取视频的总帧数
-total_frames = int(sv.get_total_frames(video_input))
 
-# 计算中间帧的位置
-middle_frame_index = total_frames // 2
-with open('/workspace/tem//middle_frame_index.pkl', 'wb') as file:
-    pickle.dump(middle_frame_index, file)
-# 读取到中间帧
-for _ in range(middle_frame_index):
-    frame = next(frame_generator)
 
-# 将帧从 BGR 转换为 RGB 并保存到 PIL 图像对象
-frame = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
 
 detections_list = []
 width, height = frame.size
@@ -130,7 +117,7 @@ for text in texts:
             ok_result.append(new_result)
 
 print(ok_result)
-with open('/workspace/tem/all_ok_bboxes.pkl', 'wb') as file:
+with open('/workspace/florence-sam/all_ok_bboxes.pkl', 'wb') as file:
     pickle.dump(all_ok_bboxes, file)
 
 for xyxy in ok_result:
@@ -143,6 +130,6 @@ for xyxy in ok_result:
     detections = run_sam_inference(SAM_IMAGE_MODEL, frame, detections)
     print(detections)
     detections_list.append(detections)
-with open('/workspace/tem/detections_list.pkl', 'wb') as file:
+with open('/workspace/florence-sam/detections_list.pkl', 'wb') as file:
     pickle.dump(detections_list, file)
 print(detections_list)