Spaces:
Runtime error
Runtime error
added vid in ference
Browse files- .gitignore +2 -1
- app.py +24 -28
- predict.py +48 -0
.gitignore
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
flagged/
|
|
|
2 |
*.png
|
3 |
-
*.mp4
|
4 |
*.mkv
|
|
|
5 |
gradio_cached_examples/
|
|
|
1 |
flagged/
|
2 |
+
__pycache__/
|
3 |
*.png
|
|
|
4 |
*.mkv
|
5 |
+
*.mp4
|
6 |
gradio_cached_examples/
|
app.py
CHANGED
@@ -1,32 +1,11 @@
|
|
1 |
import gradio as gr
|
2 |
-
import cv2
|
3 |
import requests
|
4 |
-
from
|
|
|
5 |
|
6 |
-
model = YOLO('best.pt')
|
7 |
-
path = [['image.jpg'],]
|
8 |
-
classes = ['ain', 'al', 'aleff','bb','dal','dha','dhad','fa','gaaf','ghain','ha','haa','jeem','kaaf','khaa','la','laam',
|
9 |
-
'meem','nun','ra','saad','seen','sheen','ta','taa','thaa','thal','toot','waw','ya','yaa','zay']
|
10 |
-
TargetMapper = dict(zip(range(32),classes))
|
11 |
-
def show_preds_image(image_path):
|
12 |
-
print(image_path)
|
13 |
-
image = cv2.imread(image_path)
|
14 |
-
outputs = model.predict(source=image_path)
|
15 |
-
results = outputs[0]
|
16 |
-
for i,det in enumerate(results.boxes.xyxy):
|
17 |
-
cls = TargetMapper[results.boxes.cls.numpy()[i]]
|
18 |
-
#det = results.boxes.xyxy[0]
|
19 |
-
cv2.rectangle(
|
20 |
-
image,
|
21 |
-
(int(det[0]), int(det[1])),
|
22 |
-
(int(det[2]), int(det[3])),
|
23 |
-
color=(0, 0, 255),
|
24 |
-
thickness=2,
|
25 |
-
lineType=cv2.LINE_AA
|
26 |
-
)
|
27 |
-
cv2.putText(image, cls, (int(det[0]), int(det[1])-10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (36,255,12), 2)
|
28 |
|
29 |
-
|
|
|
30 |
|
31 |
#image = cv2.imwrite('output.jpg', show_preds_image(path))
|
32 |
inputs_image = [
|
@@ -35,11 +14,28 @@ inputs_image = [
|
|
35 |
outputs_image = [
|
36 |
gr.components.Image(type="numpy", label="Output Image"),
|
37 |
]
|
38 |
-
gr.Interface(
|
39 |
-
fn=
|
40 |
inputs=inputs_image,
|
41 |
outputs=outputs_image,
|
42 |
title="Arab Sign Language Detection app",
|
43 |
examples=path,
|
44 |
cache_examples=False,
|
45 |
-
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
import gradio as gr
|
|
|
2 |
import requests
|
3 |
+
from predict import image_inference,video_inference
|
4 |
+
|
5 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
|
7 |
+
path = [['image.jpg'],]
|
8 |
+
video_path = [['video_.mp4']]
|
9 |
|
10 |
#image = cv2.imwrite('output.jpg', show_preds_image(path))
|
11 |
inputs_image = [
|
|
|
14 |
outputs_image = [
|
15 |
gr.components.Image(type="numpy", label="Output Image"),
|
16 |
]
|
17 |
+
image_interface = gr.Interface(
|
18 |
+
fn=image_inference,
|
19 |
inputs=inputs_image,
|
20 |
outputs=outputs_image,
|
21 |
title="Arab Sign Language Detection app",
|
22 |
examples=path,
|
23 |
cache_examples=False,
|
24 |
+
)#.launch(share=True)
|
25 |
+
inputs_video = [
|
26 |
+
gr.components.Video(type='filepath',label='Input Video'),
|
27 |
+
]
|
28 |
+
outputs_video = [
|
29 |
+
gr.components.Image(type='numpy',label='Output Video')
|
30 |
+
]
|
31 |
+
interface_video = gr.Interface(
|
32 |
+
fn=video_inference,
|
33 |
+
inputs=inputs_video,
|
34 |
+
outputs=outputs_video,
|
35 |
+
title="Arab Sign Language Detection app",
|
36 |
+
examples=video_path
|
37 |
+
)
|
38 |
+
gr.TabbedInterface(
|
39 |
+
[image_interface, interface_video],
|
40 |
+
tab_names=['Image inference', 'Video inference']
|
41 |
+
).queue().launch()
|
predict.py
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import cv2
|
2 |
+
from ultralytics import YOLO
|
3 |
+
|
4 |
+
|
5 |
+
classes = ['ain', 'al', 'aleff','bb','dal','dha','dhad','fa','gaaf','ghain','ha','haa','jeem','kaaf','khaa','la','laam',
|
6 |
+
'meem','nun','ra','saad','seen','sheen','ta','taa','thaa','thal','toot','waw','ya','yaa','zay']
|
7 |
+
TargetMapper = dict(zip(range(32),classes))
|
8 |
+
model = YOLO('best.pt')
|
9 |
+
def image_inference(image_path):
|
10 |
+
print(image_path)
|
11 |
+
image = cv2.imread(image_path)
|
12 |
+
outputs = model.predict(source=image_path)
|
13 |
+
results = outputs[0]
|
14 |
+
for i,det in enumerate(results.boxes.xyxy):
|
15 |
+
cls = TargetMapper[results.boxes.cls.numpy()[i]]
|
16 |
+
#det = results.boxes.xyxy[0]
|
17 |
+
cv2.rectangle(
|
18 |
+
image,
|
19 |
+
(int(det[0]), int(det[1])),
|
20 |
+
(int(det[2]), int(det[3])),
|
21 |
+
color=(0, 0, 255),
|
22 |
+
thickness=2,
|
23 |
+
lineType=cv2.LINE_AA
|
24 |
+
)
|
25 |
+
cv2.putText(image, cls, (int(det[0]), int(det[1])-10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (36,255,12), 2)
|
26 |
+
|
27 |
+
return cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
|
28 |
+
|
29 |
+
def video_inference(video_path) :
|
30 |
+
cap = cv2.VideoCapture(video_path)
|
31 |
+
while(cap.isOpened()):
|
32 |
+
ret, frame = cap.read()
|
33 |
+
if ret:
|
34 |
+
frame_copy = frame.copy()
|
35 |
+
outputs = model.predict(source=frame)
|
36 |
+
results = outputs[0]#.cpu().numpy()
|
37 |
+
for i, det in enumerate(results.boxes.xyxy):
|
38 |
+
cls = TargetMapper[results.boxes.cls.numpy()[i]]
|
39 |
+
cv2.rectangle(
|
40 |
+
frame_copy,
|
41 |
+
(int(det[0]), int(det[1])),
|
42 |
+
(int(det[2]), int(det[3])),
|
43 |
+
color=(0, 0, 255),
|
44 |
+
thickness=2,
|
45 |
+
lineType=cv2.LINE_AA
|
46 |
+
)
|
47 |
+
cv2.putText(frame_copy, cls, (int(det[0]), int(det[1])-10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (36,255,12), 2)
|
48 |
+
yield cv2.cvtColor(frame_copy, cv2.COLOR_BGR2RGB)
|