Update app.py
Browse files
app.py
CHANGED
@@ -1,165 +1,71 @@
|
|
1 |
import gradio as gr
|
2 |
-
import numpy as np
|
3 |
-
import random
|
4 |
-
|
5 |
-
# import spaces #[uncomment to use ZeroGPU]
|
6 |
-
from diffusers import DiffusionPipeline
|
7 |
import torch
|
|
|
|
|
|
|
|
|
8 |
|
|
|
9 |
device = "cuda" if torch.cuda.is_available() else "cpu"
|
10 |
-
model_repo_id = "stabilityai/sdxl-turbo" # Replace to the model you would like to use
|
11 |
-
|
12 |
-
if torch.cuda.is_available():
|
13 |
-
torch_dtype = torch.float16
|
14 |
-
else:
|
15 |
-
torch_dtype = torch.float32
|
16 |
-
|
17 |
-
pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
|
18 |
-
pipe = pipe.to(device)
|
19 |
-
|
20 |
-
MAX_SEED = np.iinfo(np.int32).max
|
21 |
-
MAX_IMAGE_SIZE = 1024
|
22 |
-
|
23 |
-
|
24 |
-
# @spaces.GPU #[uncomment to use ZeroGPU]
|
25 |
-
def infer(
|
26 |
-
prompt,
|
27 |
-
negative_prompt,
|
28 |
-
seed,
|
29 |
-
randomize_seed,
|
30 |
-
width,
|
31 |
-
height,
|
32 |
-
guidance_scale,
|
33 |
-
num_inference_steps,
|
34 |
-
progress=gr.Progress(track_tqdm=True),
|
35 |
-
):
|
36 |
-
if randomize_seed:
|
37 |
-
seed = random.randint(0, MAX_SEED)
|
38 |
-
|
39 |
-
generator = torch.Generator().manual_seed(seed)
|
40 |
-
|
41 |
-
image = pipe(
|
42 |
-
prompt=prompt,
|
43 |
-
negative_prompt=negative_prompt,
|
44 |
-
guidance_scale=guidance_scale,
|
45 |
-
num_inference_steps=num_inference_steps,
|
46 |
-
width=width,
|
47 |
-
height=height,
|
48 |
-
generator=generator,
|
49 |
-
).images[0]
|
50 |
-
|
51 |
-
return image, seed
|
52 |
-
|
53 |
-
|
54 |
-
examples = [
|
55 |
-
"Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
|
56 |
-
"An astronaut riding a green horse",
|
57 |
-
"A delicious ceviche cheesecake slice",
|
58 |
-
]
|
59 |
-
|
60 |
-
css = """
|
61 |
-
#col-container {
|
62 |
-
margin: 0 auto;
|
63 |
-
max-width: 640px;
|
64 |
-
}
|
65 |
-
"""
|
66 |
-
|
67 |
-
with gr.Blocks(css=css) as demo:
|
68 |
-
with gr.Column(elem_id="col-container"):
|
69 |
-
gr.Markdown(" # Text-to-Image Gradio Template")
|
70 |
-
|
71 |
-
with gr.Row():
|
72 |
-
prompt = gr.Text(
|
73 |
-
label="Prompt",
|
74 |
-
show_label=False,
|
75 |
-
max_lines=1,
|
76 |
-
placeholder="Enter your prompt",
|
77 |
-
container=False,
|
78 |
-
)
|
79 |
-
|
80 |
-
run_button = gr.Button("Run", scale=0, variant="primary")
|
81 |
-
|
82 |
-
result = gr.Image(label="Result", show_label=False)
|
83 |
-
|
84 |
-
with gr.Accordion("Advanced Settings", open=False):
|
85 |
-
negative_prompt = gr.Text(
|
86 |
-
label="Negative prompt",
|
87 |
-
max_lines=1,
|
88 |
-
placeholder="Enter a negative prompt",
|
89 |
-
visible=False,
|
90 |
-
)
|
91 |
-
|
92 |
-
seed = gr.Slider(
|
93 |
-
label="Seed",
|
94 |
-
minimum=0,
|
95 |
-
maximum=MAX_SEED,
|
96 |
-
step=1,
|
97 |
-
value=0,
|
98 |
-
)
|
99 |
-
|
100 |
-
randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
|
101 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
102 |
with gr.Row():
|
103 |
-
|
104 |
-
|
105 |
-
|
106 |
-
|
107 |
-
step=32,
|
108 |
-
value=1024, # Replace with defaults that work for your model
|
109 |
-
)
|
110 |
|
111 |
-
|
112 |
-
label="Height",
|
113 |
-
minimum=256,
|
114 |
-
maximum=MAX_IMAGE_SIZE,
|
115 |
-
step=32,
|
116 |
-
value=1024, # Replace with defaults that work for your model
|
117 |
-
)
|
118 |
|
119 |
-
|
120 |
-
guidance_scale = gr.Slider(
|
121 |
-
label="Guidance scale",
|
122 |
-
minimum=0.0,
|
123 |
-
maximum=10.0,
|
124 |
-
step=0.1,
|
125 |
-
value=0.0, # Replace with defaults that work for your model
|
126 |
-
)
|
127 |
|
128 |
-
|
129 |
-
|
130 |
-
|
131 |
-
|
132 |
-
|
133 |
-
|
134 |
-
)
|
135 |
-
|
136 |
-
gr.Examples(examples=examples, inputs=[prompt])
|
137 |
-
gr.on(
|
138 |
-
triggers=[run_button.click, prompt.submit],
|
139 |
-
fn=infer,
|
140 |
-
inputs=[
|
141 |
-
prompt,
|
142 |
-
negative_prompt,
|
143 |
-
seed,
|
144 |
-
randomize_seed,
|
145 |
-
width,
|
146 |
-
height,
|
147 |
-
guidance_scale,
|
148 |
-
num_inference_steps,
|
149 |
-
],
|
150 |
-
outputs=[result, seed],
|
151 |
-
)
|
152 |
-
|
153 |
-
import os
|
154 |
-
|
155 |
-
# Danh sách thư mục cần tạo
|
156 |
-
folders = ["model", "data", "outputs", "logs"]
|
157 |
-
|
158 |
-
for folder in folders:
|
159 |
-
os.makedirs(folder, exist_ok=True) # exist_ok=True để tránh lỗi nếu thư mục đã tồn tại
|
160 |
|
161 |
-
|
162 |
|
|
|
163 |
|
164 |
-
if __name__ == "__main__":
|
165 |
demo.launch()
|
|
|
1 |
import gradio as gr
|
|
|
|
|
|
|
|
|
|
|
2 |
import torch
|
3 |
+
from transformers import pipeline
|
4 |
+
from moviepy.editor import VideoFileClip
|
5 |
+
from PIL import Image
|
6 |
+
import os
|
7 |
|
8 |
+
# Kiểm tra thiết bị sử dụng GPU hay CPU
|
9 |
device = "cuda" if torch.cuda.is_available() else "cpu"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
|
11 |
+
# Tải các mô hình phân loại ảnh và video từ Hugging Face
|
12 |
+
image_classifier = pipeline("image-classification", model="google/vit-base-patch16-224-in21k", device=0 if device == "cuda" else -1)
|
13 |
+
video_classifier = pipeline("video-classification", model="google/vit-base-patch16-224-in21k", device=0 if device == "cuda" else -1)
|
14 |
+
|
15 |
+
# Hàm phân loại ảnh
|
16 |
+
def classify_image(image, model_name):
|
17 |
+
# Tùy chọn chọn model ảnh khác nếu người dùng yêu cầu
|
18 |
+
if model_name == "ViT":
|
19 |
+
classifier = image_classifier
|
20 |
+
else:
|
21 |
+
classifier = image_classifier # Chỉnh sửa ở đây nếu muốn hỗ trợ thêm các mô hình khác
|
22 |
+
|
23 |
+
# Phân loại ảnh
|
24 |
+
result = classifier(image)
|
25 |
+
return result[0]['label'], result[0]['score']
|
26 |
+
|
27 |
+
# Hàm phân loại video
|
28 |
+
def classify_video(video, model_name):
|
29 |
+
# Tùy chọn chọn model video khác nếu người dùng yêu cầu
|
30 |
+
if model_name == "ViT":
|
31 |
+
classifier = video_classifier
|
32 |
+
else:
|
33 |
+
classifier = video_classifier # Chỉnh sửa ở đây nếu muốn hỗ trợ thêm các mô hình khác
|
34 |
+
|
35 |
+
# Đọc video và trích xuất các frame (ở đây đơn giản là lấy 1 frame đầu tiên)
|
36 |
+
clip = VideoFileClip(video.name)
|
37 |
+
frame = clip.get_frame(0)
|
38 |
+
image = Image.fromarray(frame)
|
39 |
+
|
40 |
+
# Phân loại frame đầu tiên của video
|
41 |
+
result = classifier(image)
|
42 |
+
return result[0]['label'], result[0]['score']
|
43 |
+
|
44 |
+
# Giao diện Gradio
|
45 |
+
with gr.Blocks() as demo:
|
46 |
+
with gr.TabbedInterface() as tabs:
|
47 |
+
with gr.TabItem("Image Classification"):
|
48 |
+
gr.Markdown("### Upload an image for classification")
|
49 |
with gr.Row():
|
50 |
+
model_choice_image = gr.Dropdown(choices=["ViT", "ResNet"], label="Choose a Model", value="ViT")
|
51 |
+
image_input = gr.Image(type="pil", label="Upload Image")
|
52 |
+
image_output_label = gr.Textbox(label="Prediction")
|
53 |
+
image_output_score = gr.Textbox(label="Confidence Score")
|
|
|
|
|
|
|
54 |
|
55 |
+
classify_image_button = gr.Button("Classify Image")
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
|
57 |
+
classify_image_button.click(classify_image, inputs=[image_input, model_choice_image], outputs=[image_output_label, image_output_score])
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
|
59 |
+
with gr.TabItem("Video Classification"):
|
60 |
+
gr.Markdown("### Upload a video for classification")
|
61 |
+
with gr.Row():
|
62 |
+
model_choice_video = gr.Dropdown(choices=["ViT", "ResNet"], label="Choose a Model", value="ViT")
|
63 |
+
video_input = gr.Video(label="Upload Video")
|
64 |
+
video_output_label = gr.Textbox(label="Prediction")
|
65 |
+
video_output_score = gr.Textbox(label="Confidence Score")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
|
67 |
+
classify_video_button = gr.Button("Classify Video")
|
68 |
|
69 |
+
classify_video_button.click(classify_video, inputs=[video_input, model_choice_video], outputs=[video_output_label, video_output_score])
|
70 |
|
|
|
71 |
demo.launch()
|