Xenova
/

RTMO-t

@@ -21,9 +21,7 @@ import { AutoModel, AutoProcessor, RawImage } from '@xenova/transformers';
 // Load model and processor
 const model_id = 'Xenova/RTMO-t';
-const model = await AutoModel.from_pretrained(model_id, {
-    quantized: false,
-});
 const processor = await AutoProcessor.from_pretrained(model_id);
 // Read image and run processor
@@ -37,8 +35,8 @@ const { dets, keypoints } = await model({ input: pixel_values });
 // Select the first image
 const predicted_boxes = dets.tolist()[0];
 const predicted_points = keypoints.tolist()[0];
-const [width, height] = original_sizes[0];
-const [resized_width, resized_height] = reshaped_input_sizes[0];
 // Compute scale values
 const xScale = width / resized_width;
@@ -48,7 +46,7 @@ const yScale = height / resized_height;
 const point_threshold = 0.3;
 const box_threshold = 0.3;
-// Parse results
 for (let i = 0; i < predicted_boxes.length; ++i) {
     const [xmin, ymin, xmax, ymax, box_score] = predicted_boxes[i];
     if (box_score < box_threshold) continue;
@@ -74,60 +72,66 @@ for (let i = 0; i < predicted_boxes.length; ++i) {
 <summary>See example output</summary>
 ```
-Found person at [275.55, 99.07, 433.03, 753.93] with score 0.989
-  - nose: (348.04, 178.71) with score 0.686
-  - left_eye: (357.65, 166.47) with score 0.347
-  - right_eye: (341.15, 164.56) with score 0.331
-  - left_shoulder: (375.16, 258.75) with score 0.999
-  - right_shoulder: (312.26, 241.00) with score 0.999
-  - left_elbow: (381.83, 360.03) with score 0.999
-  - right_elbow: (291.49, 326.95) with score 0.999
-  - left_wrist: (399.93, 455.04) with score 0.997
-  - right_wrist: (335.69, 327.09) with score 0.999
-  - left_hip: (357.00, 457.75) with score 0.999
-  - right_hip: (317.68, 474.91) with score 0.998
-  - left_knee: (385.42, 547.58) with score 0.998
-  - right_knee: (339.32, 648.62) with score 0.953
-  - left_ankle: (384.14, 699.15) with score 0.990
-  - right_ankle: (357.63, 621.90) with score 0.906
-Found person at [67.16, 23.39, 338.29, 783.70] with score 0.932
-  - left_shoulder: (157.14, 159.59) with score 0.973
-  - right_shoulder: (159.63, 144.00) with score 0.872
-  - left_elbow: (210.02, 242.90) with score 0.982
-  - right_elbow: (201.28, 231.61) with score 0.694
-  - left_wrist: (258.17, 330.94) with score 0.978
-  - right_wrist: (205.45, 305.74) with score 0.654
-  - left_hip: (231.90, 367.39) with score 0.999
-  - right_hip: (240.19, 365.36) with score 1.000
-  - left_knee: (195.22, 574.91) with score 0.999
-  - right_knee: (216.01, 578.60) with score 1.000
-  - left_ankle: (283.08, 528.39) with score 1.000
-  - right_ankle: (300.10, 733.43) with score 0.999
-Found person at [-0.17, 75.70, 109.33, 555.50] with score 0.806
-  - nose: (49.95, 123.09) with score 0.385
-  - left_shoulder: (78.57, 171.93) with score 0.983
-  - right_shoulder: (30.76, 174.85) with score 0.974
-  - left_elbow: (91.19, 248.35) with score 0.859
-  - right_elbow: (19.49, 241.54) with score 0.877
-  - left_wrist: (93.19, 314.57) with score 0.812
-  - right_wrist: (6.06, 301.15) with score 0.899
-  - left_hip: (69.81, 313.63) with score 0.995
-  - right_hip: (41.66, 315.41) with score 0.997
-  - left_knee: (76.36, 416.84) with score 0.999
-  - right_knee: (44.06, 420.83) with score 0.998
-  - left_ankle: (83.66, 514.07) with score 0.992
-  - right_ankle: (44.09, 519.74) with score 0.983
-Found person at [348.03, 53.31, 432.29, 526.36] with score 0.328
-  - left_shoulder: (395.69, 156.16) with score 1.000
-  - right_shoulder: (351.04, 157.42) with score 0.917
-  - left_elbow: (413.08, 225.16) with score 0.995
-  - left_wrist: (418.51, 295.31) with score 0.985
-  - left_hip: (387.03, 287.25) with score 0.995
-  - right_hip: (359.71, 286.18) with score 0.939
-  - left_knee: (389.06, 393.34) with score 0.992
-  - right_knee: (363.29, 393.47) with score 0.922
-  - left_ankle: (391.54, 482.10) with score 0.970
-  - right_ankle: (365.87, 483.47) with score 0.847
 ```
 </details>

 // Load model and processor
 const model_id = 'Xenova/RTMO-t';
+const model = await AutoModel.from_pretrained(model_id);
 const processor = await AutoProcessor.from_pretrained(model_id);
 // Read image and run processor
 // Select the first image
 const predicted_boxes = dets.tolist()[0];
 const predicted_points = keypoints.tolist()[0];
+const [height, width] = original_sizes[0];
+const [resized_height, resized_width] = reshaped_input_sizes[0];
 // Compute scale values
 const xScale = width / resized_width;
 const point_threshold = 0.3;
 const box_threshold = 0.3;
+// Display results
 for (let i = 0; i < predicted_boxes.length; ++i) {
     const [xmin, ymin, xmax, ymax, box_score] = predicted_boxes[i];
     if (box_score < box_threshold) continue;
 <summary>See example output</summary>
 ```
+Found person at [411.10, 63.87, 647.68, 505.40] with score 0.986
+  - nose: (526.09, 119.83) with score 0.874
+  - left_eye: (539.01, 110.39) with score 0.696
+  - right_eye: (512.50, 111.08) with score 0.662
+  - left_shoulder: (563.59, 171.10) with score 0.999
+  - right_shoulder: (467.38, 160.82) with score 0.999
+  - left_elbow: (572.72, 240.61) with score 0.999
+  - right_elbow: (437.86, 218.20) with score 0.998
+  - left_wrist: (603.74, 303.53) with score 0.995
+  - right_wrist: (506.01, 218.68) with score 0.992
+  - left_hip: (536.00, 306.25) with score 1.000
+  - right_hip: (472.79, 311.69) with score 0.999
+  - left_knee: (580.82, 366.38) with score 0.996
+  - right_knee: (500.25, 449.72) with score 0.954
+  - left_ankle: (572.21, 449.52) with score 0.993
+  - right_ankle: (541.37, 436.71) with score 0.916
+Found person at [93.58, 19.64, 492.62, 522.45] with score 0.909
+  - left_shoulder: (233.76, 109.57) with score 0.971
+  - right_shoulder: (229.56, 100.34) with score 0.950
+  - left_elbow: (317.31, 162.73) with score 0.950
+  - right_elbow: (229.98, 179.31) with score 0.934
+  - left_wrist: (385.59, 219.03) with score 0.870
+  - right_wrist: (161.31, 230.74) with score 0.952
+  - left_hip: (351.23, 243.42) with score 0.998
+  - right_hip: (361.94, 240.70) with score 0.999
+  - left_knee: (297.77, 382.00) with score 0.998
+  - right_knee: (306.07, 393.59) with score 1.000
+  - left_ankle: (413.48, 354.16) with score 1.000
+  - right_ankle: (445.30, 488.11) with score 0.999
+Found person at [-1.46, 50.68, 160.66, 371.74] with score 0.780
+  - nose: (80.17, 81.16) with score 0.570
+  - left_eye: (85.17, 75.45) with score 0.383
+  - right_eye: (70.20, 77.09) with score 0.382
+  - left_shoulder: (121.30, 114.98) with score 0.981
+  - right_shoulder: (46.56, 114.41) with score 0.981
+  - left_elbow: (144.09, 163.76) with score 0.777
+  - right_elbow: (29.69, 159.24) with score 0.886
+  - left_wrist: (142.31, 205.64) with score 0.725
+  - right_wrist: (6.24, 199.62) with score 0.876
+  - left_hip: (108.07, 208.90) with score 0.992
+  - right_hip: (64.72, 212.01) with score 0.996
+  - left_knee: (115.26, 276.52) with score 0.998
+  - right_knee: (65.09, 283.25) with score 0.998
+  - left_ankle: (126.09, 340.42) with score 0.991
+  - right_ankle: (63.88, 348.88) with score 0.977
+Found person at [526.35, 36.25, 650.42, 280.90] with score 0.328
+  - nose: (554.06, 71.87) with score 0.901
+  - left_eye: (562.10, 66.30) with score 0.928
+  - right_eye: (546.65, 66.36) with score 0.746
+  - left_ear: (575.98, 68.17) with score 0.658
+  - left_shoulder: (588.04, 102.61) with score 0.999
+  - right_shoulder: (526.00, 102.94) with score 0.704
+  - left_elbow: (618.11, 149.18) with score 0.984
+  - left_wrist: (630.77, 189.42) with score 0.961
+  - left_hip: (578.74, 181.42) with score 0.966
+  - right_hip: (530.33, 176.46) with score 0.698
+  - left_knee: (568.74, 233.01) with score 0.958
+  - right_knee: (542.44, 243.87) with score 0.687
+  - left_ankle: (585.17, 284.79) with score 0.838
+  - right_ankle: (550.07, 292.19) with score 0.435
 ```
 </details>