Update app.py

app.py

@@ -1,31 +1,77 @@
-#from transformers import pipeline
-
+import cv2
 import gradio as gr
+import imutils
+import numpy as np
+import torch
+from PIL import Image
+
+def parse_video(video_file):
+    """A utility to parse the input videos.
+    Reference: https://pyimagesearch.com/2018/11/12/yolo-object-detection-with-opencv/
+    """
+    vs = cv2.VideoCapture(video_file)
 
-#asr = pipeline("automatic-speech-recognition", "facebook/wav2vec2-base-960h")
-#classifier = pipeline("text-classification")
+    # try to determine the total number of frames in the video file
+    try:
+        prop = (
+            cv2.cv.CV_CAP_PROP_FRAME_COUNT
+            if imutils.is_cv2()
+            else cv2.CAP_PROP_FRAME_COUNT
+        )
+        total = int(vs.get(prop))
+        print("[INFO] {} total frames in video".format(total))
 
+    # an error occurred while trying to determine the total
+    # number of frames in the video file
+    except:
+        print("[INFO] could not determine # of frames in video")
+        print("[INFO] no approx. completion time can be provided")
+        total = -1
 
-def speech_to_text():
-    text = 'running speech to text'
-    return text
+    frames = []
 
+    # loop over frames from the video file stream
+    while True:
+        # read the next frame from the file
+        (grabbed, frame) = vs.read()
+        if frame is not None:
+            frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+            frames.append(frame)
+        # if the frame was not grabbed, then we have reached the end
+        # of the stream
+        if not grabbed:
+            break
 
-def text_to_sentiment():
-    return 'running text to sentiment'
+    return frames
 
+def pil_parser(frames):
+    X = []
+    frames = np.arange(2,62,2)
+    use_transform : transforms.Compose =transforms.Compose([transforms.Resize([256, 342]),
+                                    transforms.ToTensor(),
+                                    transforms.Normalize(mean=[0.5], std=[0.5])])
 
-demo = gr.Blocks()
+    for i in frames:
+        image = Image.fromarray(dummy_frames[i]).convert('L')
 
-with demo:
-    audio_file = gr.File(file_count='multiple')
-    text = gr.Textbox()
-    label = gr.Label()
+        if use_transform is not None:
+            image = use_transform(image)
+        else:
+            image = transforms.ToTensor()(image)
+        X.append(image)
+    X = torch.stack(X, dim=1).unsqueeze(0)
 
-    b1 = gr.Button("Recognize Speech")
-    b2 = gr.Button("Classify Sentiment")
+    return str(X.shape)
 
-    b1.click(speech_to_text, inputs=audio_file, outputs=text)
-    b2.click(text_to_sentiment, inputs=text, outputs=label)
 
-demo.launch()
+gr.Interface(
+    fn=infer,
+    inputs=gr.Video(),
+    outputs=['text'],
+    title="Viscosity Regression From Video Data",
+    description=(
+        "Gradio demo for Video Regression"
+    ),
+    allow_flagging='never',
+    
+).launch()