Hugging Face's logo

idefinity
/
flip-web

ONNX
Model card Files
xet
 Community
zziang commited on
Commit
261d81c
·
verified ·
1 Parent(s): 7e5059d

Upload k2q/report.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. k2q/report.json +375 -0
k2q/report.json ADDED
@@ -0,0 +1,375 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "notes": [
3
+ "$ /usr/bin/python3 -m pip install --no-cache-dir -q huggingface_hub safetensors torchvision tqdm -> rc 0",
4
+ "$ git clone -q https://github.com/VAST-AI-Research/TripoSplat.git /kaggle/working/TripoSplat -> rc 0",
5
+ "$ git -C /kaggle/working/TripoSplat checkout -q d8db9e0 -> rc 0",
6
+ "ckpts 4.461275425 GB",
7
+ "model.safetensors 209.33 MB",
8
+ "dequantised 204 int4 weights + 355 fp16 tensors = 370.5 M params",
9
+ "ckpt parts: {'main': 'triposplat_fp16.safetensors', 'dino': 'dino_v3_vit_h.safetensors', 'flux': 'flux2-vae.safetensors', 'decoder': 'triposplat_vae_decoder_fp16.safetensors', 'rmbg': 'birefnet.safetensors'}",
10
+ "load_state_dict missing 0 unexpected 0",
11
+ "images ['https://datasets-server.huggingface.co/cached-assets/DownFlow/fuliji/--/6f7f7855634f78f64ec4fa51ba84dd528c740216/--/default/train/0/image/image.jpg?Expires=1793150610&Signature=mXWxinokvATupDO06H-9IbZLG~JQoOG5IlEj0bKBTuAuE09g0EwSybPUhUrb4eaRLWuP5k2twgJnsZ~0Z2Joar7Syr-3UZFyN7D~T4Tl82Kj5VuaneXqT4DbRXIQJtVuPeZtKJLH5-HWdG9WBWbG8phjsfCOVORKxQwvKd9KMtCkLE5fYRKuDteXgBwCwlbiyFaf~tllOti2KEYloHLNwXum6lOXt6AtgJaq9VdpFxBIkNtVfg3pYUSNi-7UDk~DVQtukpBL7hqZ0MwL3gBpQ-LCbvg9BSj2I6q~wbjrg39hogN7kFzTrcD~f0HvRW4rhq3Z1dCguMtSpiHxDjaoDA__&Key-Pair-Id=K3C0L9WB6U5DUC', 'https://datasets-server.huggingface.co/cached-assets/DownFlow/fuliji/--/6f7f7855634f78f64ec4fa51ba84dd528c740216/--/default/train/1/image/image.jpg?Expires=1793150611&Signature=KCSeu0fvTNQrX2tux2uLJ6rl6GWUSxFLF8yzPPioROt6qtW~O0Ci2FFY8CeC~me-NQeOQnFdBCv0W3d2IPLdRHXIsJB3X1biqtvk1vNIUESy9K0XvfVuZuhRVu89vGJpuMrnPktxPcexW1jqfkp4kLWjn3diOV~9Yap8oqXciIdTK4oRrs7LF2X9VgueLrrbSTuWrzUF~MEEDxjSkQZNlh92BdBZlgO0JBoVZEfV6QAp6i5SP~NI7FDECbABrTRMSwea1FRb4bo915Tlfcl8ZgOpoYLoTTPeoR0aikOcXuCM94dGELitFsxQrPAePlYukh8zy01~8igKh13XLgRSJQ__&Key-Pair-Id=K3C0L9WB6U5DUC', 'https://datasets-server.huggingface.co/cached-assets/DownFlow/fuliji/--/6f7f7855634f78f64ec4fa51ba84dd528c740216/--/default/train/2/image/image.jpg?Expires=1793150612&Signature=q4NNd2xB2KtWdyrkU93g6jFUBRMPEtbGeEQJ2FbPBDHQU7Izopzb1PllSxFa0yj0HjcG9B085RPYKW74gKTTRK2dIw1eIBVhxRawUor8AggJ~3p5oOotZ5G3VGZqsNfkrzTk3fEgW4ekYYxQNql78ZGPZIo-0S4QRGYi9w0zozPjesZHYKSynF~zH3QJzsnt1HnrOwn-shUe7k7KyCrnn23NCRWIEQWgW5gC30q7uJJ-kKwFt4nEjv21mSkL~v8j6FWJzjQVCn4lTJ3kpz-7mhlg3BagOndH-2QPowQF7Z4bQ6gW6duTDkg9-XAQnc-UKyRYz8TUC8ARMU7xPp6Jfw__&Key-Pair-Id=K3C0L9WB6U5DUC']",
12
+ " hf_0000.jpg (853, 1280)",
13
+ " hf_0001.jpg (853, 1280)",
14
+ " hf_0002.jpg (519, 409)",
15
+ "------------------------------------------------------------",
16
+ "hf_0000.jpg",
17
+ " captured initial noise (1, 8192, 16)",
18
+ " captured initial noise (1, 8192, 16)",
19
+ " captured initial noise (1, 8192, 16)",
20
+ " int4 2-step: sample 4.03s decode 0.88s opacity 0.4228 scale 0.00641",
21
+ " latent vs t20: cos 0.6843113957424125 rel_l2 0.746503795884487",
22
+ "------------------------------------------------------------",
23
+ "hf_0001.jpg",
24
+ " captured initial noise (1, 8192, 16)",
25
+ " captured initial noise (1, 8192, 16)",
26
+ " captured initial noise (1, 8192, 16)",
27
+ " int4 2-step: sample 4.03s decode 0.46s opacity 0.4687 scale 0.00506",
28
+ " latent vs t20: cos 0.6605275894860584 rel_l2 0.7676950237454742",
29
+ "------------------------------------------------------------",
30
+ "hf_0002.jpg",
31
+ " captured initial noise (1, 8192, 16)",
32
+ " captured initial noise (1, 8192, 16)",
33
+ " captured initial noise (1, 8192, 16)",
34
+ " int4 2-step: sample 4.01s decode 0.46s opacity 0.3371 scale 0.00649",
35
+ " latent vs t20: cos 0.4955636664316501 rel_l2 0.9132866334680064",
36
+ "uploaded hf_0000.jpg 0.09 MB",
37
+ "uploaded hf_0000_feature1.npy 21.0 MB",
38
+ "uploaded hf_0000_feature2.npy 2.1 MB",
39
+ "uploaded hf_0000_i01_camera.npy 0.0 MB",
40
+ "uploaded hf_0000_i01_latent.npy 0.52 MB",
41
+ "uploaded hf_0000_i01_noise.npy 0.52 MB",
42
+ "uploaded hf_0000_i02.ply 4.46 MB",
43
+ "uploaded hf_0000_i02_camera.npy 0.0 MB",
44
+ "uploaded hf_0000_i02_latent.npy 0.52 MB",
45
+ "uploaded hf_0000_i02_noise.npy 0.52 MB",
46
+ "uploaded hf_0000_t20_camera.npy 0.0 MB",
47
+ "uploaded hf_0000_t20_latent.npy 0.52 MB",
48
+ "uploaded hf_0000_t20_noise.npy 0.52 MB",
49
+ "uploaded hf_0001.jpg 0.08 MB",
50
+ "uploaded hf_0001_feature1.npy 21.0 MB",
51
+ "uploaded hf_0001_feature2.npy 2.1 MB",
52
+ "uploaded hf_0001_i01_camera.npy 0.0 MB",
53
+ "uploaded hf_0001_i01_latent.npy 0.52 MB",
54
+ "uploaded hf_0001_i01_noise.npy 0.52 MB",
55
+ "uploaded hf_0001_i02.ply 4.46 MB",
56
+ "uploaded hf_0001_i02_camera.npy 0.0 MB",
57
+ "uploaded hf_0001_i02_latent.npy 0.52 MB",
58
+ "uploaded hf_0001_i02_noise.npy 0.52 MB",
59
+ "uploaded hf_0001_t20_camera.npy 0.0 MB",
60
+ "uploaded hf_0001_t20_latent.npy 0.52 MB",
61
+ "uploaded hf_0001_t20_noise.npy 0.52 MB",
62
+ "uploaded hf_0002.jpg 0.02 MB",
63
+ "uploaded hf_0002_feature1.npy 21.0 MB",
64
+ "uploaded hf_0002_feature2.npy 2.1 MB",
65
+ "uploaded hf_0002_i01_camera.npy 0.0 MB",
66
+ "uploaded hf_0002_i01_latent.npy 0.52 MB",
67
+ "uploaded hf_0002_i01_noise.npy 0.52 MB",
68
+ "uploaded hf_0002_i02.ply 4.46 MB",
69
+ "uploaded hf_0002_i02_camera.npy 0.0 MB",
70
+ "uploaded hf_0002_i02_latent.npy 0.52 MB",
71
+ "uploaded hf_0002_i02_noise.npy 0.52 MB",
72
+ "uploaded hf_0002_t20_camera.npy 0.0 MB",
73
+ "uploaded hf_0002_t20_latent.npy 0.52 MB",
74
+ "uploaded hf_0002_t20_noise.npy 0.52 MB",
75
+ "uploaded prepared_hf_0000.png 0.45 MB",
76
+ "uploaded prepared_hf_0001.png 0.28 MB",
77
+ "uploaded prepared_hf_0002.png 0.38 MB"
78
+ ],
79
+ "images": [
80
+ {
81
+ "image": "hf_0000.jpg",
82
+ "encode_s": 7.11,
83
+ "cond_keys": [
84
+ "feature1",
85
+ "feature2"
86
+ ],
87
+ "cond_shapes": {
88
+ "feature1": [
89
+ 1,
90
+ 4101,
91
+ 1280
92
+ ],
93
+ "feature2": [
94
+ 1,
95
+ 4101,
96
+ 128
97
+ ]
98
+ },
99
+ "runs": {
100
+ "t20": {
101
+ "sample_s": 76.14,
102
+ "latent_shapes": {
103
+ "latent": [
104
+ 1,
105
+ 8192,
106
+ 16
107
+ ],
108
+ "camera": [
109
+ 1,
110
+ 1,
111
+ 5
112
+ ]
113
+ }
114
+ },
115
+ "i01": {
116
+ "sample_s": 2.01,
117
+ "latent_shapes": {
118
+ "latent": [
119
+ 1,
120
+ 8192,
121
+ 16
122
+ ],
123
+ "camera": [
124
+ 1,
125
+ 1,
126
+ 5
127
+ ]
128
+ }
129
+ },
130
+ "i02": {
131
+ "sample_s": 4.03,
132
+ "latent_shapes": {
133
+ "latent": [
134
+ 1,
135
+ 8192,
136
+ 16
137
+ ],
138
+ "camera": [
139
+ 1,
140
+ 1,
141
+ 5
142
+ ]
143
+ }
144
+ }
145
+ },
146
+ "latent": {
147
+ "i01": {
148
+ "n": 131072,
149
+ "mean": 0.0505263498783215,
150
+ "std": 0.7767661075407771,
151
+ "cos": 0.6783716769621494,
152
+ "rel_l2": 0.7383868363961527
153
+ },
154
+ "i02": {
155
+ "n": 131072,
156
+ "mean": 0.05180729646477644,
157
+ "std": 0.8724032044967313,
158
+ "cos": 0.6843113957424125,
159
+ "rel_l2": 0.746503795884487
160
+ },
161
+ "i01_vs_i02": {
162
+ "n": 131072,
163
+ "mean": 0.0505263498783215,
164
+ "std": 0.7767661075407771,
165
+ "cos": 0.9505594992800042,
166
+ "rel_l2": 0.31626140788697676
167
+ }
168
+ },
169
+ "decode_s": 0.88,
170
+ "n_gaussians": 65536,
171
+ "opacity_mean": 0.4228,
172
+ "scale_mean": 0.00641,
173
+ "ply": "hf_0000_i02.ply",
174
+ "ply_mb": 4.46
175
+ },
176
+ {
177
+ "image": "hf_0001.jpg",
178
+ "encode_s": 2.13,
179
+ "cond_keys": [
180
+ "feature1",
181
+ "feature2"
182
+ ],
183
+ "cond_shapes": {
184
+ "feature1": [
185
+ 1,
186
+ 4101,
187
+ 1280
188
+ ],
189
+ "feature2": [
190
+ 1,
191
+ 4101,
192
+ 128
193
+ ]
194
+ },
195
+ "runs": {
196
+ "t20": {
197
+ "sample_s": 79.79,
198
+ "latent_shapes": {
199
+ "latent": [
200
+ 1,
201
+ 8192,
202
+ 16
203
+ ],
204
+ "camera": [
205
+ 1,
206
+ 1,
207
+ 5
208
+ ]
209
+ }
210
+ },
211
+ "i01": {
212
+ "sample_s": 2.0,
213
+ "latent_shapes": {
214
+ "latent": [
215
+ 1,
216
+ 8192,
217
+ 16
218
+ ],
219
+ "camera": [
220
+ 1,
221
+ 1,
222
+ 5
223
+ ]
224
+ }
225
+ },
226
+ "i02": {
227
+ "sample_s": 4.03,
228
+ "latent_shapes": {
229
+ "latent": [
230
+ 1,
231
+ 8192,
232
+ 16
233
+ ],
234
+ "camera": [
235
+ 1,
236
+ 1,
237
+ 5
238
+ ]
239
+ }
240
+ }
241
+ },
242
+ "latent": {
243
+ "i01": {
244
+ "n": 131072,
245
+ "mean": 0.04488432699798395,
246
+ "std": 0.7509480489413876,
247
+ "cos": 0.6695273612660281,
248
+ "rel_l2": 0.7452937108996273
249
+ },
250
+ "i02": {
251
+ "n": 131072,
252
+ "mean": 0.0457351031184281,
253
+ "std": 0.8438176966687934,
254
+ "cos": 0.6605275894860584,
255
+ "rel_l2": 0.7676950237454742
256
+ },
257
+ "i01_vs_i02": {
258
+ "n": 131072,
259
+ "mean": 0.04488432699798395,
260
+ "std": 0.7509480489413876,
261
+ "cos": 0.9438339836404723,
262
+ "rel_l2": 0.3347410654009287
263
+ }
264
+ },
265
+ "decode_s": 0.46,
266
+ "n_gaussians": 65536,
267
+ "opacity_mean": 0.4687,
268
+ "scale_mean": 0.00506,
269
+ "ply": "hf_0001_i02.ply",
270
+ "ply_mb": 4.46
271
+ },
272
+ {
273
+ "image": "hf_0002.jpg",
274
+ "encode_s": 2.13,
275
+ "cond_keys": [
276
+ "feature1",
277
+ "feature2"
278
+ ],
279
+ "cond_shapes": {
280
+ "feature1": [
281
+ 1,
282
+ 4101,
283
+ 1280
284
+ ],
285
+ "feature2": [
286
+ 1,
287
+ 4101,
288
+ 128
289
+ ]
290
+ },
291
+ "runs": {
292
+ "t20": {
293
+ "sample_s": 79.76,
294
+ "latent_shapes": {
295
+ "latent": [
296
+ 1,
297
+ 8192,
298
+ 16
299
+ ],
300
+ "camera": [
301
+ 1,
302
+ 1,
303
+ 5
304
+ ]
305
+ }
306
+ },
307
+ "i01": {
308
+ "sample_s": 2.0,
309
+ "latent_shapes": {
310
+ "latent": [
311
+ 1,
312
+ 8192,
313
+ 16
314
+ ],
315
+ "camera": [
316
+ 1,
317
+ 1,
318
+ 5
319
+ ]
320
+ }
321
+ },
322
+ "i02": {
323
+ "sample_s": 4.01,
324
+ "latent_shapes": {
325
+ "latent": [
326
+ 1,
327
+ 8192,
328
+ 16
329
+ ],
330
+ "camera": [
331
+ 1,
332
+ 1,
333
+ 5
334
+ ]
335
+ }
336
+ }
337
+ },
338
+ "latent": {
339
+ "i01": {
340
+ "n": 131072,
341
+ "mean": 0.08820080588443435,
342
+ "std": 0.7130690546315626,
343
+ "cos": 0.49191200521890865,
344
+ "rel_l2": 0.8926177090524836
345
+ },
346
+ "i02": {
347
+ "n": 131072,
348
+ "mean": 0.08802460038560866,
349
+ "std": 0.8066498263304474,
350
+ "cos": 0.4955636664316501,
351
+ "rel_l2": 0.9132866334680064
352
+ },
353
+ "i01_vs_i02": {
354
+ "n": 131072,
355
+ "mean": 0.08820080588443435,
356
+ "std": 0.7130690546315626,
357
+ "cos": 0.9383341927677059,
358
+ "rel_l2": 0.34974807426970267
359
+ }
360
+ },
361
+ "decode_s": 0.46,
362
+ "n_gaussians": 65536,
363
+ "opacity_mean": 0.3371,
364
+ "scale_mean": 0.00649,
365
+ "ply": "hf_0002_i02.ply",
366
+ "ply_mb": 4.46
367
+ }
368
+ ],
369
+ "model": {
370
+ "params_M": 370.5,
371
+ "tensors": 559,
372
+ "missing": [],
373
+ "unexpected": []
374
+ }
375
+ }