add/edit some videos

.gitattributes

@@ -38,5 +38,10 @@ test/1.mp4 filter=lfs diff=lfs merge=lfs -text
 test/2.mp4 filter=lfs diff=lfs merge=lfs -text
 test/3.mp4 filter=lfs diff=lfs merge=lfs -text
 test/4.mp4 filter=lfs diff=lfs merge=lfs -text
-test/cat[[:space:]]bird[[:space:]]dog.mp4 filter=lfs diff=lfs merge=lfs -text
+test/bicycles.mp4 filter=lfs diff=lfs merge=lfs -text
+test/cat[[:space:]]dog.mp4 filter=lfs diff=lfs merge=lfs -text
 test/horse[[:space:]]cow[[:space:]]people.mp4 filter=lfs diff=lfs merge=lfs -text
+test/motorbikes.mp4 filter=lfs diff=lfs merge=lfs -text
+test/output.mp4 filter=lfs diff=lfs merge=lfs -text
+test/planes.mp4 filter=lfs diff=lfs merge=lfs -text
+test/trains.mp4 filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,2 @@
+# 忽略 tmp 文件夹下的所有 mp4 文件
+tmp/*.mp4

app.py

@@ -8,29 +8,30 @@ import shutil
 import os
 import skvideo.io
 
+# 全局设置
+DEFAULT_CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair",
+                                   "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
+COLORS = np.random.uniform(0, 255, size=(len(DEFAULT_CLASSES), 3))
+DISPLAY_INTERVAL = 30
+CONFIDENCE_LEVEL = 0.5
+
+
 # 定义视频处理函数
-def process_video(input_video_path):
+def process_video(input_video_path, selected_classes):
+    print(selected_classes)
+    
     use_gpu = False
-
-    frame_display_interval = 30
-    frame_display_counter = frame_display_interval
-    confidence_level = 0.5
     writer = None
+    display_counter = DISPLAY_INTERVAL
 
-    CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
-            "bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
-            "dog", "horse", "motorbike", "person", "pottedplant", "sheep",
-            "sofa", "train", "tvmonitor"]
-
-    COLORS = np.random.uniform(0, 255, size=(len(CLASSES), 3))
-
-    net = cv2.dnn.readNetFromCaffe('ssd_files/MobileNetSSD_deploy.prototxt', 'ssd_files/MobileNetSSD_deploy.caffemodel')
+    net = cv2.dnn.readNetFromCaffe(
+        'ssd_files/MobileNetSSD_deploy.prototxt', 'ssd_files/MobileNetSSD_deploy.caffemodel')
 
     if use_gpu:
         print("[INFO] setting preferable backend and target to CUDA...")
         net.setPreferableBackend(cv2.dnn.DNN_BACKEND_CUDA)
         net.setPreferableTarget(cv2.dnn.DNN_TARGET_CUDA)
-    
+
     print("[INFO] accessing video stream...")
     vs = cv2.VideoCapture(input_video_path)
 
@@ -49,7 +50,7 @@ def process_video(input_video_path):
 
         for i in np.arange(0, detections.shape[2]):
             confidence = detections[0, 0, i, 2]
-            if confidence > confidence_level:
+            if confidence > CONFIDENCE_LEVEL:
                 idx = int(detections[0, 0, i, 1])
                 box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
                 (startX, startY, endX, endY) = box.astype("int")
@@ -58,56 +59,57 @@ def process_video(input_video_path):
                 originEndX = int(endX*origin_w/w)
                 originEndY = int(endY*origin_h/h)
 
-                label = "{}: {:.2f}%".format(CLASSES[idx], confidence * 100)
-                cv2.rectangle(origin_frame, (originStartX, originStartY), (originEndX, originEndY), COLORS[idx], 2)
+                if DEFAULT_CLASSES[idx] in selected_classes:
+                    label = "{}: {:.2f}%".format(DEFAULT_CLASSES[idx], confidence * 100)
+                    cv2.rectangle(origin_frame, (originStartX, originStartY),
+                                (originEndX, originEndY), COLORS[idx], 2)
 
-                y = originStartY - 15 if originStartY - 15 > 15 else originStartY + 15
-                cv2.putText(origin_frame, label, (originStartX, y), cv2.FONT_HERSHEY_DUPLEX, 0.5, COLORS[idx], 1)
+                    y = originStartY - 15 if originStartY - 15 > 15 else originStartY + 15
+                    cv2.putText(origin_frame, label, (originStartX, y),
+                                cv2.FONT_HERSHEY_DUPLEX, 0.5, COLORS[idx], 1)
 
         # 如果没有创建视频编写器，请创建它
         if writer is None:
             random_filename = "./tmp/" + str(uuid.uuid4()) + ".mp4"
-            fourcc = cv2.VideoWriter_fourcc(*'avc1')  # 可以根据需要选择适当的编解码器
+            # fourcc = cv2.VideoWriter_fourcc(*'avc1')  # 可以根据需要选择适当的编解码器
             # writer = cv2.VideoWriter(random_filename, fourcc, 30, (origin_frame.shape[1], origin_frame.shape[0]), True)
-            writer = skvideo.io.FFmpegWriter(random_filename, outputdict={'-vcodec': 'libx264', '-pix_fmt': 'yuv420p'})
+            writer = skvideo.io.FFmpegWriter(random_filename, outputdict={
+                                             '-vcodec': 'libx264', '-pix_fmt': 'yuv420p'})
         # 将帧写入输出视频
         # writer.write(origin_frame)
         writer.writeFrame(cv2.cvtColor(origin_frame, cv2.COLOR_BGR2RGB))
 
-        display_frame = cv2.cvtColor(origin_frame, cv2.COLOR_BGR2RGB)  # 将图像从BGR转换为RGB
-        if frame_display_counter:
-            frame_display_counter -= 1
+        display_frame = cv2.cvtColor(
+            origin_frame, cv2.COLOR_BGR2RGB)  # 将图像从BGR转换为RGB
+        if display_counter:
+            display_counter -= 1
         else:
             yield display_frame, None
-            frame_display_counter = frame_display_interval
+            display_counter = DISPLAY_INTERVAL
 
     vs.release()
     # 在循环结束后释放视频编写器
     # if writer is not None:
     #     writer.release()
     writer.close()
-    
-    # 将相对路径转换为绝对路径
-    absolute_path = os.path.abspath(random_filename)
-    print(absolute_path)
-    
+
     # 指定根目录路径
     root_directory = "./tmp"
     # 调用函数打印根目录的文件树
     print_directory_tree(root_directory)
 
-    yield display_frame, absolute_path
+    yield display_frame, random_filename
 
 
 def print_directory_tree(directory):
     for root, dirs, files in os.walk(directory):
         # 打印当前目录路径
         print(f"Directory: {root}")
-        
+
         # 打印当前目录下的所有文件
         for file in files:
             print(f"  File: {os.path.join(root, file)}")
-        
+
         # 打印当前目录下的所有子目录
         for dir in dirs:
             print(f"  Subdirectory: {os.path.join(root, dir)}")
@@ -124,26 +126,34 @@ def cleanup_tmp_folder():
     except Exception as e:
         print(f"Error cleaning up .mp4 files in tmp folder: {str(e)}")
 
+
 def main():
     # 定义Gradio界面
     with gr.Blocks() as demo:
         with gr.Row():
-            input_video = gr.Video(label="input")
-            processed_frames = gr.Image(label="live preview")
-            output_video = gr.Video(label="output")
+            input_video = gr.Video(label="Video Input")
+            processed_frames = gr.Image(label="Live Preview")
+            output_video = gr.Video(label="Video Output")
 
         with gr.Row():
-            examples = gr.Examples([f"test/{file.name}" for file in os.scandir('./test')], inputs=input_video)
+            with gr.Column():
+                input_classes = gr.Dropdown(
+                    DEFAULT_CLASSES, value=DEFAULT_CLASSES, multiselect=True, label="Detection Classes", info="Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed auctor, nisl eget ultricies aliquam, nunc nisl aliquet nunc, eget aliquam nisl nunc vel nisl."
+                )
+                examples = gr.Examples(
+                    [f"test/{file.name}" for file in os.scandir('./test')], inputs=input_video)
             process_video_btn = gr.Button("process video")
 
-        process_video_btn.click(process_video, input_video, [processed_frames, output_video])
+        process_video_btn.click(process_video, inputs=[
+                                input_video, input_classes], outputs=[processed_frames, output_video])
+
+    demo.queue().launch(share=False, debug=True, server_name="0.0.0.0", server_port=7860)
 
-    demo.queue().launch(share=False,debug=True,server_name="0.0.0.0",server_port=7860)
 
 if __name__ == "__main__":
     # 注册清理函数，确保在程序退出时执行
     atexit.register(cleanup_tmp_folder)
-    
+
     # 根目录路径
     root_directory = "./"
     # tmp文件夹路径
@@ -153,4 +163,4 @@ if __name__ == "__main__":
         os.makedirs(tmp_directory)
 
     # 执行main()
-    main()
+    main()

test.py

@@ -0,0 +1,32 @@
+import gradio as gr
+
+
+def sentence_builder(quantity, animal, countries, place, activity_list, morning):
+    return f"""The {quantity} {animal}s from {" and ".join(countries)} went to the {place} where they {" and ".join(activity_list)} until the {"morning" if morning else "night"}"""
+
+
+demo = gr.Interface(
+    sentence_builder,
+    [
+        gr.Slider(2, 20, value=4, label="Count", info="Choose between 2 and 20"),
+        gr.Dropdown(
+            ["cat", "dog", "bird"], label="Animal", info="Will add more animals later!"
+        ),
+        gr.CheckboxGroup(["USA", "Japan", "Pakistan"], label="Countries", info="Where are they from?"),
+        gr.Radio(["park", "zoo", "road"], label="Location", info="Where did they go?"),
+        gr.Dropdown(
+            ["ran", "swam", "ate", "slept"], value=["swam", "slept"], multiselect=True, label="Activity", info="Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed auctor, nisl eget ultricies aliquam, nunc nisl aliquet nunc, eget aliquam nisl nunc vel nisl."
+        ),
+        gr.Checkbox(label="Morning", info="Did they do it in the morning?"),
+    ],
+    "text",
+    examples=[
+        [2, "cat", ["Japan", "Pakistan"], "park", ["ate", "swam"], True],
+        [4, "dog", ["Japan"], "zoo", ["ate", "swam"], False],
+        [10, "bird", ["USA", "Pakistan"], "road", ["ran"], False],
+        [8, "cat", ["Pakistan"], "zoo", ["ate"], True],
+    ]
+)
+
+if __name__ == "__main__":
+    demo.launch()

test/{cat bird dog.mp4 → bicycles.mp4}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d73e8c7dbf12a35bf7d82ef881a46d58e33fa0058a72414b53ce5cfcaec78ab
-size 6629220
+oid sha256:2d4077002a5d0627599091ed8c204a149e354433a764baeb50ce3747ddcf3844
+size 5031955

test/cat dog.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a08b4bae4486c30d8af2b8f4e2e736e5d7bf6789934f38615ec9208453508957
+size 9481934

test/motorbikes.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a3ee65ea65d844baef575d966aa76ad5780af97cb3d56b1e855c1784a6fefaf
+size 8739256

test/output.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:332483edafc4761b39f3ec5eeb1f58baa7a1fd9635f12db02f96871bc79ff04f
+size 28810171

test/planes.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:848fe543a4653a4d224d1fed284f50e6c69332aa2f0f05f9fc06b89c2e278425
+size 13107364

test/trains.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e94002af4a980959103201b58b3200f2980b5c9bf2a202e66832a8f9d3966730
+size 10075560