Datasets:

---

ftopal

/

huggingface-models-raw

like 0

ERROR: type should be string, got "\n\nhttps://github.com/open-mmlab/mmpose/tree/main/projects/rtmo with ONNX weights to be compatible with Transformers.js.\n\n## Usage (Transformers.js)\n\nIf you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@xenova/transformers) using:\n```bash\nnpm i @xenova/transformers\n```\n\n**Example:** Perform pose-estimation w/ `Xenova/RTMO-t`.\n\n```js\nimport { AutoModel, AutoProcessor, RawImage } from '@xenova/transformers';\n\n// Load model and processor\nconst model_id = 'Xenova/RTMO-t';\nconst model = await AutoModel.from_pretrained(model_id);\nconst processor = await AutoProcessor.from_pretrained(model_id);\n\n// Read image and run processor\nconst url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/football-match.jpg';\nconst image = await RawImage.read(url);\nconst { pixel_values, original_sizes, reshaped_input_sizes } = await processor(image);\n\n// Predict bounding boxes and keypoints\nconst { dets, keypoints } = await model({ input: pixel_values });\n\n// Select the first image\nconst predicted_boxes = dets.tolist()[0];\nconst predicted_points = keypoints.tolist()[0];\nconst [height, width] = original_sizes[0];\nconst [resized_height, resized_width] = reshaped_input_sizes[0];\n\n// Compute scale values\nconst xScale = width / resized_width;\nconst yScale = height / resized_height;\n\n// Define thresholds\nconst point_threshold = 0.3;\nconst box_threshold = 0.3;\n\n// Display results\nfor (let i = 0; i < predicted_boxes.length; ++i) {\n const [xmin, ymin, xmax, ymax, box_score] = predicted_boxes[i];\n if (box_score < box_threshold) continue;\n\n const x1 = (xmin * xScale).toFixed(2);\n const y1 = (ymin * yScale).toFixed(2);\n const x2 = (xmax * xScale).toFixed(2);\n const y2 = (ymax * yScale).toFixed(2);\n\n console.log(`Found person at [${x1}, ${y1}, ${x2}, ${y2}] with score ${box_score.toFixed(3)}`)\n const points = predicted_points[i]; // of shape [17, 3]\n for (let id = 0; id < points.length; ++id) {\n const label = model.config.id2label[id];\n const [x, y, point_score] = points[id];\n if (point_score < point_threshold) continue;\n console.log(` - ${label}: (${(x * xScale).toFixed(2)}, ${(y * yScale).toFixed(2)}) with score ${point_score.toFixed(3)}`);\n }\n}\n```\n\n<details>\n\n<summary>See example output</summary>\n\n```\nFound person at [411.10, 63.87, 647.68, 505.40] with score 0.986\n - nose: (526.09, 119.83) with score 0.874\n - left_eye: (539.01, 110.39) with score 0.696\n - right_eye: (512.50, 111.08) with score 0.662\n - left_shoulder: (563.59, 171.10) with score 0.999\n - right_shoulder: (467.38, 160.82) with score 0.999\n - left_elbow: (572.72, 240.61) with score 0.999\n - right_elbow: (437.86, 218.20) with score 0.998\n - left_wrist: (603.74, 303.53) with score 0.995\n - right_wrist: (506.01, 218.68) with score 0.992\n - left_hip: (536.00, 306.25) with score 1.000\n - right_hip: (472.79, 311.69) with score 0.999\n - left_knee: (580.82, 366.38) with score 0.996\n - right_knee: (500.25, 449.72) with score 0.954\n - left_ankle: (572.21, 449.52) with score 0.993\n - right_ankle: (541.37, 436.71) with score 0.916\nFound person at [93.58, 19.64, 492.62, 522.45] with score 0.909\n - left_shoulder: (233.76, 109.57) with score 0.971\n - right_shoulder: (229.56, 100.34) with score 0.950\n - left_elbow: (317.31, 162.73) with score 0.950\n - right_elbow: (229.98, 179.31) with score 0.934\n - left_wrist: (385.59, 219.03) with score 0.870\n - right_wrist: (161.31, 230.74) with score 0.952\n - left_hip: (351.23, 243.42) with score 0.998\n - right_hip: (361.94, 240.70) with score 0.999\n - left_knee: (297.77, 382.00) with score 0.998\n - right_knee: (306.07, 393.59) with score 1.000\n - left_ankle: (413.48, 354.16) with score 1.000\n - right_ankle: (445.30, 488.11) with score 0.999\nFound person at [-1.46, 50.68, 160.66, 371.74] with score 0.780\n - nose: (80.17, 81.16) with score 0.570\n - left_eye: (85.17, 75.45) with score 0.383\n - right_eye: (70.20, 77.09) with score 0.382\n - left_shoulder: (121.30, 114.98) with score 0.981\n - right_shoulder: (46.56, 114.41) with score 0.981\n - left_elbow: (144.09, 163.76) with score 0.777\n - right_elbow: (29.69, 159.24) with score 0.886\n - left_wrist: (142.31, 205.64) with score 0.725\n - right_wrist: (6.24, 199.62) with score 0.876\n - left_hip: (108.07, 208.90) with score 0.992\n - right_hip: (64.72, 212.01) with score 0.996\n - left_knee: (115.26, 276.52) with score 0.998\n - right_knee: (65.09, 283.25) with score 0.998\n - left_ankle: (126.09, 340.42) with score 0.991\n - right_ankle: (63.88, 348.88) with score 0.977\nFound person at [526.35, 36.25, 650.42, 280.90] with score 0.328\n - nose: (554.06, 71.87) with score 0.901\n - left_eye: (562.10, 66.30) with score 0.928\n - right_eye: (546.65, 66.36) with score 0.746\n - left_ear: (575.98, 68.17) with score 0.658\n - left_shoulder: (588.04, 102.61) with score 0.999\n - right_shoulder: (526.00, 102.94) with score 0.704\n - left_elbow: (618.11, 149.18) with score 0.984\n - left_wrist: (630.77, 189.42) with score 0.961\n - left_hip: (578.74, 181.42) with score 0.966\n - right_hip: (530.33, 176.46) with score 0.698\n - left_knee: (568.74, 233.01) with score 0.958\n - right_knee: (542.44, 243.87) with score 0.687\n - left_ankle: (585.17, 284.79) with score 0.838\n - right_ankle: (550.07, 292.19) with score 0.435\n```\n\n</details>"

ERROR: type should be string, got "\n\nhttps://github.com/open-mmlab/mmpose/tree/main/projects/rtmo with ONNX weights to be compatible with Transformers.js.\n\n## Usage (Transformers.js)\n\nIf you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@xenova/transformers) using:\n```bash\nnpm i @xenova/transformers\n```\n\n**Example:** Perform pose-estimation w/ `Xenova/RTMO-s`.\n\n```js\nimport { AutoModel, AutoProcessor, RawImage } from '@xenova/transformers';\n\n// Load model and processor\nconst model_id = 'Xenova/RTMO-s';\nconst model = await AutoModel.from_pretrained(model_id);\nconst processor = await AutoProcessor.from_pretrained(model_id);\n\n// Read image and run processor\nconst url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/football-match.jpg';\nconst image = await RawImage.read(url);\nconst { pixel_values, original_sizes, reshaped_input_sizes } = await processor(image);\n\n// Predict bounding boxes and keypoints\nconst { dets, keypoints } = await model({ input: pixel_values });\n\n// Select the first image\nconst predicted_boxes = dets.tolist()[0];\nconst predicted_points = keypoints.tolist()[0];\nconst [height, width] = original_sizes[0];\nconst [resized_height, resized_width] = reshaped_input_sizes[0];\n\n// Compute scale values\nconst xScale = width / resized_width;\nconst yScale = height / resized_height;\n\n// Define thresholds\nconst point_threshold = 0.3;\nconst box_threshold = 0.3;\n\n// Display results\nfor (let i = 0; i < predicted_boxes.length; ++i) {\n const [xmin, ymin, xmax, ymax, box_score] = predicted_boxes[i];\n if (box_score < box_threshold) continue;\n\n const x1 = (xmin * xScale).toFixed(2);\n const y1 = (ymin * yScale).toFixed(2);\n const x2 = (xmax * xScale).toFixed(2);\n const y2 = (ymax * yScale).toFixed(2);\n\n console.log(`Found person at [${x1}, ${y1}, ${x2}, ${y2}] with score ${box_score.toFixed(3)}`)\n const points = predicted_points[i]; // of shape [17, 3]\n for (let id = 0; id < points.length; ++id) {\n const label = model.config.id2label[id];\n const [x, y, point_score] = points[id];\n if (point_score < point_threshold) continue;\n console.log(` - ${label}: (${(x * xScale).toFixed(2)}, ${(y * yScale).toFixed(2)}) with score ${point_score.toFixed(3)}`);\n }\n}\n```\n\n<details>\n\n<summary>See example output</summary>\n\n```\nFound person at [423.33, 55.52, 644.28, 504.13] with score 0.988\n - nose: (527.30, 117.12) with score 0.733\n - left_eye: (541.79, 109.26) with score 0.554\n - right_eye: (515.04, 107.59) with score 0.475\n - left_shoulder: (563.30, 171.75) with score 1.000\n - right_shoulder: (464.21, 159.75) with score 1.000\n - left_elbow: (575.71, 238.04) with score 0.998\n - right_elbow: (436.06, 218.10) with score 0.999\n - left_wrist: (605.86, 303.35) with score 1.000\n - right_wrist: (497.47, 220.82) with score 1.000\n - left_hip: (540.97, 307.31) with score 1.000\n - right_hip: (475.85, 318.78) with score 1.000\n - left_knee: (578.63, 368.63) with score 1.000\n - right_knee: (501.05, 442.49) with score 1.000\n - left_ankle: (572.11, 464.96) with score 0.991\n - right_ankle: (535.75, 441.52) with score 0.981\nFound person at [89.97, 3.96, 517.81, 507.28] with score 0.966\n - left_shoulder: (242.65, 111.06) with score 0.999\n - right_shoulder: (228.79, 112.54) with score 0.999\n - left_elbow: (321.84, 169.07) with score 0.999\n - right_elbow: (225.76, 218.20) with score 1.000\n - left_wrist: (351.73, 220.74) with score 0.999\n - right_wrist: (160.19, 228.03) with score 1.000\n - left_hip: (342.34, 246.81) with score 1.000\n - right_hip: (360.05, 259.35) with score 0.999\n - left_knee: (299.56, 377.97) with score 0.998\n - right_knee: (313.81, 378.83) with score 0.976\n - left_ankle: (443.84, 312.35) with score 0.983\n - right_ankle: (424.74, 433.61) with score 0.823\nFound person at [-0.53, 51.78, 153.65, 371.17] with score 0.769\n - nose: (75.52, 85.67) with score 0.363\n - left_shoulder: (121.54, 113.17) with score 1.000\n - right_shoulder: (49.77, 117.60) with score 1.000\n - left_elbow: (132.90, 147.02) with score 0.932\n - right_elbow: (30.31, 156.42) with score 0.992\n - left_wrist: (154.43, 162.08) with score 0.871\n - right_wrist: (17.20, 196.43) with score 0.943\n - left_hip: (105.61, 204.27) with score 0.999\n - right_hip: (61.99, 203.66) with score 0.999\n - left_knee: (114.70, 270.91) with score 1.000\n - right_knee: (63.75, 275.33) with score 1.000\n - left_ankle: (125.53, 342.00) with score 0.998\n - right_ankle: (63.16, 344.07) with score 0.997\nFound person at [519.40, 34.94, 650.11, 312.07] with score 0.488\n - nose: (554.82, 76.58) with score 0.920\n - left_eye: (563.12, 69.41) with score 0.666\n - right_eye: (544.82, 70.01) with score 0.595\n - left_shoulder: (596.60, 105.61) with score 0.999\n - right_shoulder: (523.29, 107.31) with score 0.969\n - left_elbow: (625.14, 151.30) with score 0.999\n - right_elbow: (515.96, 147.59) with score 0.322\n - left_wrist: (630.90, 196.91) with score 0.998\n - right_wrist: (520.75, 181.83) with score 0.415\n - left_hip: (583.24, 200.84) with score 0.998\n - right_hip: (533.69, 200.01) with score 0.978\n - left_knee: (583.79, 265.14) with score 0.934\n - right_knee: (538.27, 262.98) with score 0.669\n - left_ankle: (584.90, 309.76) with score 0.489\n```\n\n</details>"

ERROR: type should be string, got "\n\nhttps://github.com/open-mmlab/mmpose/tree/main/projects/rtmo with ONNX weights to be compatible with Transformers.js.\n\n## Usage (Transformers.js)\n\nIf you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@xenova/transformers) using:\n```bash\nnpm i @xenova/transformers\n```\n\n**Example:** Perform pose-estimation w/ `Xenova/RTMO-m`.\n\n```js\nimport { AutoModel, AutoProcessor, RawImage } from '@xenova/transformers';\n\n// Load model and processor\nconst model_id = 'Xenova/RTMO-m';\nconst model = await AutoModel.from_pretrained(model_id);\nconst processor = await AutoProcessor.from_pretrained(model_id);\n\n// Read image and run processor\nconst url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/football-match.jpg';\nconst image = await RawImage.read(url);\nconst { pixel_values, original_sizes, reshaped_input_sizes } = await processor(image);\n\n// Predict bounding boxes and keypoints\nconst { dets, keypoints } = await model({ input: pixel_values });\n\n// Select the first image\nconst predicted_boxes = dets.tolist()[0];\nconst predicted_points = keypoints.tolist()[0];\nconst [height, width] = original_sizes[0];\nconst [resized_height, resized_width] = reshaped_input_sizes[0];\n\n// Compute scale values\nconst xScale = width / resized_width;\nconst yScale = height / resized_height;\n\n// Define thresholds\nconst point_threshold = 0.3;\nconst box_threshold = 0.4;\n\n// Display results\nfor (let i = 0; i < predicted_boxes.length; ++i) {\n const [xmin, ymin, xmax, ymax, box_score] = predicted_boxes[i];\n if (box_score < box_threshold) continue;\n\n const x1 = (xmin * xScale).toFixed(2);\n const y1 = (ymin * yScale).toFixed(2);\n const x2 = (xmax * xScale).toFixed(2);\n const y2 = (ymax * yScale).toFixed(2);\n\n console.log(`Found person at [${x1}, ${y1}, ${x2}, ${y2}] with score ${box_score.toFixed(3)}`)\n const points = predicted_points[i]; // of shape [17, 3]\n for (let id = 0; id < points.length; ++id) {\n const label = model.config.id2label[id];\n const [x, y, point_score] = points[id];\n if (point_score < point_threshold) continue;\n console.log(` - ${label}: (${(x * xScale).toFixed(2)}, ${(y * yScale).toFixed(2)}) with score ${point_score.toFixed(3)}`);\n }\n}\n```\n\n<details>\n\n<summary>See example output</summary>\n\n```\nFound person at [394.23, 54.52, 676.59, 509.93] with score 0.977\n - nose: (521.88, 120.59) with score 0.692\n - left_eye: (536.24, 109.29) with score 0.635\n - right_eye: (511.85, 107.62) with score 0.651\n - left_shoulder: (561.11, 171.55) with score 0.993\n - right_shoulder: (471.06, 157.17) with score 0.999\n - left_elbow: (574.33, 240.08) with score 0.993\n - right_elbow: (437.67, 219.04) with score 0.998\n - left_wrist: (605.09, 310.85) with score 0.996\n - right_wrist: (496.67, 218.61) with score 0.993\n - left_hip: (537.65, 305.16) with score 1.000\n - right_hip: (475.64, 313.71) with score 1.000\n - left_knee: (581.28, 366.44) with score 1.000\n - right_knee: (506.58, 432.27) with score 0.996\n - left_ankle: (575.49, 470.17) with score 0.999\n - right_ankle: (534.34, 442.35) with score 0.994\nFound person at [65.64, -3.94, 526.84, 538.72] with score 0.947\n - left_shoulder: (224.52, 111.13) with score 0.996\n - right_shoulder: (212.09, 110.60) with score 0.998\n - left_elbow: (322.33, 170.98) with score 0.998\n - right_elbow: (235.17, 223.79) with score 1.000\n - left_wrist: (389.08, 222.90) with score 0.997\n - right_wrist: (162.75, 228.10) with score 0.998\n - left_hip: (365.58, 242.19) with score 1.000\n - right_hip: (327.40, 255.20) with score 1.000\n - left_knee: (313.14, 376.06) with score 1.000\n - right_knee: (336.28, 393.63) with score 1.000\n - left_ankle: (428.03, 347.03) with score 1.000\n - right_ankle: (434.31, 510.29) with score 0.992\nFound person at [-0.88, 48.03, 182.29, 381.19] with score 0.787\n - nose: (72.50, 83.26) with score 0.606\n - left_eye: (81.11, 76.66) with score 0.627\n - right_eye: (64.49, 77.73) with score 0.641\n - left_ear: (95.29, 78.63) with score 0.513\n - left_shoulder: (114.15, 109.26) with score 0.918\n - right_shoulder: (46.66, 115.12) with score 0.988\n - left_elbow: (131.40, 160.25) with score 0.351\n - right_elbow: (26.67, 159.11) with score 0.934\n - right_wrist: (6.60, 201.80) with score 0.681\n - left_hip: (110.48, 206.96) with score 0.998\n - right_hip: (60.89, 199.41) with score 0.997\n - left_knee: (118.23, 272.23) with score 0.999\n - right_knee: (66.52, 273.32) with score 0.994\n - left_ankle: (129.82, 346.46) with score 0.999\n - right_ankle: (60.40, 349.13) with score 0.995\nFound person at [512.82, 31.30, 662.28, 314.57] with score 0.451\n - nose: (550.07, 74.26) with score 0.766\n - left_eye: (558.96, 67.14) with score 0.955\n - right_eye: (541.52, 68.23) with score 0.783\n - left_ear: (575.04, 67.61) with score 0.952\n - left_shoulder: (589.39, 102.33) with score 0.996\n - right_shoulder: (511.02, 103.00) with score 0.699\n - left_elbow: (626.71, 148.71) with score 0.997\n - left_wrist: (633.15, 200.33) with score 0.982\n - left_hip: (580.00, 181.21) with score 0.994\n - right_hip: (524.41, 184.62) with score 0.849\n - left_knee: (594.99, 244.95) with score 0.977\n - right_knee: (533.72, 246.37) with score 0.504\n - left_ankle: (598.47, 294.18) with score 0.844\n```\n\n</details>"

ERROR: type should be string, got "\n\nhttps://github.com/open-mmlab/mmpose/tree/main/projects/rtmo with ONNX weights to be compatible with Transformers.js.\n\n## Usage (Transformers.js)\n\nIf you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@xenova/transformers) using:\n```bash\nnpm i @xenova/transformers\n```\n\n**Example:** Perform pose-estimation w/ `Xenova/RTMO-l`.\n\n```js\nimport { AutoModel, AutoProcessor, RawImage } from '@xenova/transformers';\n\n// Load model and processor\nconst model_id = 'Xenova/RTMO-l';\nconst model = await AutoModel.from_pretrained(model_id);\nconst processor = await AutoProcessor.from_pretrained(model_id);\n\n// Read image and run processor\nconst url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/football-match.jpg';\nconst image = await RawImage.read(url);\nconst { pixel_values, original_sizes, reshaped_input_sizes } = await processor(image);\n\n// Predict bounding boxes and keypoints\nconst { dets, keypoints } = await model({ input: pixel_values });\n\n// Select the first image\nconst predicted_boxes = dets.tolist()[0];\nconst predicted_points = keypoints.tolist()[0];\nconst [height, width] = original_sizes[0];\nconst [resized_height, resized_width] = reshaped_input_sizes[0];\n\n// Compute scale values\nconst xScale = width / resized_width;\nconst yScale = height / resized_height;\n\n// Define thresholds\nconst point_threshold = 0.3;\nconst box_threshold = 0.3;\n\n// Display results\nfor (let i = 0; i < predicted_boxes.length; ++i) {\n const [xmin, ymin, xmax, ymax, box_score] = predicted_boxes[i];\n if (box_score < box_threshold) continue;\n\n const x1 = (xmin * xScale).toFixed(2);\n const y1 = (ymin * yScale).toFixed(2);\n const x2 = (xmax * xScale).toFixed(2);\n const y2 = (ymax * yScale).toFixed(2);\n\n console.log(`Found person at [${x1}, ${y1}, ${x2}, ${y2}] with score ${box_score.toFixed(3)}`)\n const points = predicted_points[i]; // of shape [17, 3]\n for (let id = 0; id < points.length; ++id) {\n const label = model.config.id2label[id];\n const [x, y, point_score] = points[id];\n if (point_score < point_threshold) continue;\n console.log(` - ${label}: (${(x * xScale).toFixed(2)}, ${(y * yScale).toFixed(2)}) with score ${point_score.toFixed(3)}`);\n }\n}\n```\n\n<details>\n\n<summary>See example output</summary>\n\n```\nFound person at [400.13, 66.05, 657.48, 496.67] with score 0.978\n - nose: (520.40, 118.17) with score 0.445\n - left_eye: (531.83, 111.10) with score 0.350\n - left_shoulder: (559.65, 168.66) with score 0.999\n - right_shoulder: (469.70, 160.04) with score 0.999\n - left_elbow: (573.20, 237.82) with score 1.000\n - right_elbow: (438.51, 218.06) with score 0.999\n - left_wrist: (604.74, 308.75) with score 0.999\n - right_wrist: (495.52, 219.24) with score 0.999\n - left_hip: (537.36, 306.24) with score 1.000\n - right_hip: (477.61, 314.79) with score 0.998\n - left_knee: (576.44, 360.67) with score 1.000\n - right_knee: (500.26, 448.33) with score 0.997\n - left_ankle: (575.94, 461.43) with score 0.998\n - right_ankle: (525.18, 436.10) with score 0.996\nFound person at [84.74, 11.57, 524.53, 535.62] with score 0.970\n - left_shoulder: (240.00, 106.15) with score 0.998\n - right_shoulder: (230.72, 131.27) with score 0.999\n - left_elbow: (319.58, 164.42) with score 0.999\n - right_elbow: (232.16, 226.10) with score 1.000\n - left_wrist: (390.95, 220.65) with score 0.999\n - right_wrist: (157.61, 227.93) with score 0.999\n - left_hip: (363.29, 249.14) with score 1.000\n - right_hip: (337.65, 250.50) with score 1.000\n - left_knee: (297.35, 368.55) with score 1.000\n - right_knee: (328.29, 390.84) with score 1.000\n - left_ankle: (433.81, 343.83) with score 0.999\n - right_ankle: (452.74, 504.60) with score 0.995\nFound person at [-4.11, 53.42, 174.91, 372.64] with score 0.644\n - nose: (74.67, 84.38) with score 0.375\n - left_shoulder: (114.29, 113.60) with score 0.991\n - right_shoulder: (44.21, 117.73) with score 0.989\n - left_elbow: (124.69, 159.42) with score 0.978\n - right_elbow: (26.54, 154.78) with score 0.995\n - left_wrist: (132.86, 168.78) with score 0.957\n - right_wrist: (6.44, 195.67) with score 0.986\n - left_hip: (98.90, 199.49) with score 0.978\n - right_hip: (62.77, 200.49) with score 0.976\n - left_knee: (111.91, 277.06) with score 0.998\n - right_knee: (65.08, 276.40) with score 0.999\n - left_ankle: (128.95, 344.65) with score 0.973\n - right_ankle: (63.55, 345.60) with score 0.992\nFound person at [511.40, 32.53, 658.71, 345.63] with score 0.384\n - nose: (554.88, 74.25) with score 0.796\n - left_eye: (563.64, 68.39) with score 0.716\n - right_eye: (547.38, 68.22) with score 0.542\n - left_ear: (575.42, 72.40) with score 0.324\n - left_shoulder: (576.47, 105.27) with score 0.999\n - right_shoulder: (531.19, 105.55) with score 0.956\n - left_elbow: (623.35, 151.54) with score 0.999\n - right_elbow: (549.79, 144.36) with score 0.387\n - left_wrist: (631.33, 198.37) with score 0.991\n - right_wrist: (547.36, 162.58) with score 0.486\n - left_hip: (578.36, 192.67) with score 0.989\n - right_hip: (555.21, 188.00) with score 0.925\n - left_knee: (604.56, 239.95) with score 0.977\n - right_knee: (545.23, 221.37) with score 0.952\n - left_ankle: (587.82, 323.26) with score 0.401\n - right_ankle: (546.77, 322.69) with score 0.846\n```\n\n</details>"