1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
|
//! SAM: Segment Anything Model
//! https://github.com/facebookresearch/segment-anything
#[cfg(feature = "mkl")]
extern crate intel_mkl_src;
#[cfg(feature = "accelerate")]
extern crate accelerate_src;
use candle::DType;
use candle_nn::VarBuilder;
use candle_transformers::models::segment_anything::sam;
use clap::Parser;
#[derive(Parser)]
struct Args {
#[arg(long)]
model: Option<String>,
#[arg(long)]
image: String,
/// Run on CPU rather than on GPU.
#[arg(long)]
cpu: bool,
#[arg(long)]
generate_masks: bool,
#[arg(long, default_value_t = 0.5)]
point_x: f64,
#[arg(long, default_value_t = 0.5)]
point_y: f64,
/// Enable tracing (generates a trace-timestamp.json file).
#[arg(long)]
tracing: bool,
/// Use the TinyViT based models from MobileSAM
#[arg(long)]
use_tiny: bool,
}
pub fn main() -> anyhow::Result<()> {
use tracing_chrome::ChromeLayerBuilder;
use tracing_subscriber::prelude::*;
let args = Args::parse();
let _guard = if args.tracing {
let (chrome_layer, guard) = ChromeLayerBuilder::new().build();
tracing_subscriber::registry().with(chrome_layer).init();
Some(guard)
} else {
None
};
let device = candle_examples::device(args.cpu)?;
let (image, initial_h, initial_w) = if args.image.ends_with(".safetensors") {
let mut tensors = candle::safetensors::load(&args.image, &device)?;
let image = match tensors.remove("image") {
Some(image) => image,
None => {
if tensors.len() != 1 {
anyhow::bail!("multiple tensors in '{}'", args.image)
}
tensors.into_values().next().unwrap()
}
};
let image = if image.rank() == 4 {
image.get(0)?
} else {
image
};
let (_c, h, w) = image.dims3()?;
(image, h, w)
} else {
let (image, h, w) = candle_examples::load_image(&args.image, Some(sam::IMAGE_SIZE))?;
(image.to_device(&device)?, h, w)
};
println!("loaded image {image:?}");
let model = match args.model {
Some(model) => std::path::PathBuf::from(model),
None => {
let api = hf_hub::api::sync::Api::new()?;
let api = api.model("lmz/candle-sam".to_string());
let filename = if args.use_tiny {
"mobile_sam-tiny-vitt.safetensors"
} else {
"sam_vit_b_01ec64.safetensors"
};
api.get(filename)?
}
};
let weights = unsafe { candle::safetensors::MmapedFile::new(model)? };
let weights = weights.deserialize()?;
let vb = VarBuilder::from_safetensors(vec![weights], DType::F32, &device);
let sam = if args.use_tiny {
sam::Sam::new_tiny(vb)? // tiny vit_t
} else {
sam::Sam::new(768, 12, 12, &[2, 5, 8, 11], vb)? // sam_vit_b
};
if args.generate_masks {
// Default options similar to the Python version.
let bboxes = sam.generate_masks(
&image,
/* points_per_side */ 32,
/* crop_n_layer */ 0,
/* crop_overlap_ratio */ 512. / 1500.,
/* crop_n_points_downscale_factor */ 1,
)?;
for (idx, bbox) in bboxes.iter().enumerate() {
println!("{bbox:?}");
let mask = (&bbox.data.to_dtype(DType::U8)? * 255.)?;
let (h, w) = mask.dims2()?;
let mask = mask.broadcast_as((3, h, w))?;
candle_examples::save_image_resize(
&mask,
format!("sam_mask{idx}.png"),
initial_h,
initial_w,
)?;
}
} else {
let point = Some((args.point_x, args.point_y));
let start_time = std::time::Instant::now();
let (mask, iou_predictions) = sam.forward(&image, point, false)?;
println!(
"mask generated in {:.2}s",
start_time.elapsed().as_secs_f32()
);
println!("mask:\n{mask}");
println!("iou_predictions: {iou_predictions:?}");
// Save the mask as an image.
let mask = (mask.ge(0f32)? * 255.)?;
let (_one, h, w) = mask.dims3()?;
let mask = mask.expand((3, h, w))?;
candle_examples::save_image_resize(&mask, "sam_mask.png", initial_h, initial_w)?;
if !args.image.ends_with(".safetensors") {
let mut img = image::io::Reader::open(&args.image)?
.decode()
.map_err(candle::Error::wrap)?;
let mask_pixels = mask.permute((1, 2, 0))?.flatten_all()?.to_vec1::<u8>()?;
let mask_img: image::ImageBuffer<image::Rgb<u8>, Vec<u8>> =
match image::ImageBuffer::from_raw(w as u32, h as u32, mask_pixels) {
Some(image) => image,
None => anyhow::bail!("error saving merged image"),
};
let mask_img = image::DynamicImage::from(mask_img).resize_to_fill(
img.width(),
img.height(),
image::imageops::FilterType::CatmullRom,
);
for x in 0..img.width() {
for y in 0..img.height() {
let mask_p = imageproc::drawing::Canvas::get_pixel(&mask_img, x, y);
if mask_p.0[0] > 100 {
let mut img_p = imageproc::drawing::Canvas::get_pixel(&img, x, y);
img_p.0[2] = 255 - (255 - img_p.0[2]) / 2;
img_p.0[1] /= 2;
img_p.0[0] /= 2;
imageproc::drawing::Canvas::draw_pixel(&mut img, x, y, img_p)
}
}
}
match point {
Some((x, y)) => {
let (x, y) = (
(x * img.width() as f64) as i32,
(y * img.height() as f64) as i32,
);
imageproc::drawing::draw_filled_circle(
&img,
(x, y),
3,
image::Rgba([255, 0, 0, 200]),
)
.save("sam_merged.jpg")?
}
None => img.save("sam_merged.jpg")?,
};
}
}
Ok(())
}
|
