File size: 44,678 Bytes
612f0be |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 |
python train_ddp_spawn.py --base configs/train-v01.yaml --no-test True --train True --logdir outputs/logs/train-v01
[2024-09-29 13:19:46,460] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect)
[WARNING] async_io requires the dev libaio .so object and headers but these were not found.
[WARNING] async_io: please install the libaio-dev package with apt
[WARNING] If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
[WARNING] Please specify the CUTLASS repo directory as environment variable $CUTLASS_PATH
[WARNING] sparse_attn requires a torch version >= 1.5 and < 2.0 but detected 2.0
[WARNING] using untested triton version (2.0.0), only 1.0.0 is known to be compatible
2024-09-29 13:19:55.519392: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2024-09-29 13:19:55.698222: I external/local_tsl/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.
2024-09-29 13:19:56.301373: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2024-09-29 13:19:58.557393: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
Global seed set to 2300
[09/29 13:20:06 VTDM]: Running on GPUs 7,
[09/29 13:20:06 VTDM]: Use the strategy of deepspeed_stage_2
[09/29 13:20:06 VTDM]: Pytorch lightning trainer config:
{'gpus': '7,', 'logger_refresh_rate': 5, 'check_val_every_n_epoch': 1, 'max_epochs': 50, 'accelerator': 'cuda', 'strategy': 'deepspeed_stage_2', 'precision': 16}
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
Initialized embedder #0: FrozenOpenCLIPImagePredictionEmbedder with 683800065 params. Trainable: False
Initialized embedder #1: AesEmbedder with 343490018 params. Trainable: False
Initialized embedder #2: ConcatTimestepEmbedderND with 0 params. Trainable: False
Initialized embedder #3: VideoPredictionEmbedderWithEncoder with 83653863 params. Trainable: False
Initialized embedder #4: ConcatTimestepEmbedderND with 0 params. Trainable: False
Restored from /mnt/afs_intern/yanghaibo/datas/download_checkpoints/svd_checkpoints/stable-video-diffusion-img2vid-xt/svd_xt_image_decoder.safetensors with 312 missing and 0 unexpected keys
Missing Keys: ['conditioner.embedders.1.aesthetic_model.positional_embedding', 'conditioner.embedders.1.aesthetic_model.text_projection', 'conditioner.embedders.1.aesthetic_model.logit_scale', 'conditioner.embedders.1.aesthetic_model.visual.class_embedding', 'conditioner.embedders.1.aesthetic_model.visual.positional_embedding', 'conditioner.embedders.1.aesthetic_model.visual.proj', 'conditioner.embedders.1.aesthetic_model.visual.conv1.weight', 'conditioner.embedders.1.aesthetic_model.visual.ln_pre.weight', 'conditioner.embedders.1.aesthetic_model.visual.ln_pre.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.0.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.0.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.0.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.0.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.0.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.0.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.0.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.0.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.0.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.0.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.0.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.0.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.1.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.1.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.1.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.1.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.1.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.1.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.1.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.1.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.1.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.1.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.1.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.1.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.2.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.2.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.2.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.2.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.2.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.2.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.2.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.2.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.2.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.2.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.2.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.2.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.3.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.3.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.3.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.3.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.3.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.3.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.3.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.3.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.3.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.3.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.3.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.3.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.4.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.4.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.4.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.4.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.4.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.4.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.4.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.4.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.4.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.4.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.4.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.4.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.5.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.5.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.5.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.5.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.5.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.5.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.5.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.5.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.5.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.5.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.5.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.5.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.6.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.6.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.6.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.6.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.6.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.6.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.6.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.6.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.6.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.6.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.6.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.6.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.7.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.7.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.7.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.7.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.7.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.7.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.7.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.7.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.7.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.7.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.7.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.7.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.8.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.8.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.8.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.8.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.8.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.8.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.8.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.8.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.8.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.8.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.8.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.8.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.9.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.9.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.9.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.9.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.9.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.9.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.9.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.9.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.9.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.9.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.9.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.9.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.10.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.10.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.10.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.10.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.10.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.10.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.10.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.10.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.10.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.10.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.10.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.10.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.11.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.11.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.11.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.11.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.11.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.11.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.11.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.11.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.11.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.11.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.11.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.11.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.12.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.12.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.12.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.12.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.12.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.12.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.12.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.12.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.12.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.12.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.12.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.12.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.13.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.13.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.13.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.13.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.13.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.13.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.13.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.13.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.13.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.13.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.13.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.13.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.14.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.14.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.14.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.14.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.14.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.14.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.14.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.14.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.14.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.14.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.14.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.14.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.15.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.15.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.15.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.15.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.15.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.15.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.15.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.15.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.15.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.15.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.15.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.15.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.16.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.16.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.16.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.16.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.16.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.16.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.16.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.16.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.16.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.16.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.16.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.16.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.17.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.17.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.17.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.17.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.17.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.17.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.17.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.17.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.17.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.17.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.17.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.17.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.18.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.18.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.18.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.18.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.18.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.18.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.18.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.18.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.18.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.18.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.18.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.18.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.19.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.19.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.19.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.19.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.19.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.19.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.19.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.19.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.19.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.19.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.19.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.19.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.20.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.20.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.20.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.20.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.20.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.20.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.20.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.20.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.20.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.20.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.20.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.20.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.21.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.21.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.21.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.21.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.21.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.21.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.21.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.21.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.21.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.21.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.21.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.21.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.22.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.22.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.22.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.22.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.22.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.22.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.22.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.22.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.22.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.22.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.22.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.22.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.23.attn.in_proj_weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.23.attn.in_proj_bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.23.attn.out_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.23.attn.out_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.23.ln_1.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.23.ln_1.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.23.mlp.c_fc.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.23.mlp.c_fc.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.23.mlp.c_proj.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.23.mlp.c_proj.bias', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.23.ln_2.weight', 'conditioner.embedders.1.aesthetic_model.visual.transformer.resblocks.23.ln_2.bias', 'conditioner.embedders.1.aesthetic_model.visual.ln_post.weight', 'conditioner.embedders.1.aesthetic_model.visual.ln_post.bias', 'conditioner.embedders.1.aesthetic_model.token_embedding.weight', 'conditioner.embedders.1.aesthetic_model.ln_final.weight', 'conditioner.embedders.1.aesthetic_model.ln_final.bias', 'conditioner.embedders.1.aesthetic_mlp.layers.0.weight', 'conditioner.embedders.1.aesthetic_mlp.layers.0.bias', 'conditioner.embedders.1.aesthetic_mlp.layers.2.weight', 'conditioner.embedders.1.aesthetic_mlp.layers.2.bias', 'conditioner.embedders.1.aesthetic_mlp.layers.4.weight', 'conditioner.embedders.1.aesthetic_mlp.layers.4.bias', 'conditioner.embedders.1.aesthetic_mlp.layers.6.weight', 'conditioner.embedders.1.aesthetic_mlp.layers.6.bias', 'conditioner.embedders.1.aesthetic_mlp.layers.7.weight', 'conditioner.embedders.1.aesthetic_mlp.layers.7.bias']
/mnt/afs_intern/yanghaibo/installed/anaconda3/envs/general/lib/python3.10/site-packages/pytorch_lightning/loggers/test_tube.py:104: LightningDeprecationWarning: The TestTubeLogger is deprecated since v1.5 and will be removed in v1.7. We recommend switching to the `pytorch_lightning.loggers.TensorBoardLogger` as an alternative.
rank_zero_deprecation(
[09/29 13:21:06 VTDM]: Merged modelckpt-cfg:
{'target': 'pytorch_lightning.callbacks.ModelCheckpoint', 'params': {'dirpath': 'outputs/logs/train-v01/2024-09-29T13-20-04_train-v01_00/checkpoints', 'filename': '{epoch:06}', 'verbose': True, 'save_weights_only': True}}
[09/29 13:21:06 VTDM]: Caution: Saving checkpoints every n train steps without deleting. This might require some free space.
[09/29 13:21:06 VTDM]: Merged trainsteps-cfg:
{'target': 'pytorch_lightning.callbacks.ModelCheckpoint', 'params': {'dirpath': 'outputs/logs/train-v01/2024-09-29T13-20-04_train-v01_00/checkpoints/trainstep_checkpoints', 'filename': '{epoch:06}-{step:09}', 'verbose': True, 'save_top_k': -1, 'every_n_train_steps': 3000, 'save_weights_only': False}}
[09/29 13:21:06 VTDM]: Done in building trainer kwargs.
GPU available: True, used: True
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
============= length of dataset 1 =============
[09/29 13:21:07 VTDM]: Set up dataset.
[09/29 13:21:07 VTDM]: accumulate_grad_batches = 1
[09/29 13:21:07 VTDM]: Setting learning rate to 1.00e-05 = 1 (accumulate_grad_batches) * 1 (num_gpus) * 1 (batchsize) * 1.00e-05 (base_lr)
/mnt/afs_intern/yanghaibo/installed/anaconda3/envs/general/lib/python3.10/site-packages/pytorch_lightning/trainer/configuration_validator.py:116: UserWarning: You passed in a `val_dataloader` but have no `validation_step`. Skipping val loop.
rank_zero_warn("You passed in a `val_dataloader` but have no `validation_step`. Skipping val loop.")
/mnt/afs_intern/yanghaibo/installed/anaconda3/envs/general/lib/python3.10/site-packages/pytorch_lightning/trainer/configuration_validator.py:271: LightningDeprecationWarning: The `on_keyboard_interrupt` callback hook was deprecated in v1.5 and will be removed in v1.7. Please use the `on_exception` callback hook instead.
rank_zero_deprecation(
/mnt/afs_intern/yanghaibo/installed/anaconda3/envs/general/lib/python3.10/site-packages/pytorch_lightning/trainer/configuration_validator.py:287: LightningDeprecationWarning: Base `Callback.on_train_batch_end` hook signature has changed in v1.5. The `dataloader_idx` argument will be removed in v1.7.
rank_zero_deprecation(
Global seed set to 2300
initializing deepspeed distributed: GLOBAL_RANK: 0, MEMBER: 1/1
/mnt/afs_intern/yanghaibo/installed/anaconda3/envs/general/lib/python3.10/site-packages/pytorch_lightning/plugins/training_type/deepspeed.py:625: UserWarning: Inferring the batch size for internal deepspeed logging from the `train_dataloader()`. If you require skipping this, please pass `Trainer(strategy=DeepSpeedPlugin(logging_batch_size_per_gpu=batch_size))`
rank_zero_warn(
Enabling DeepSpeed FP16.
/mnt/afs_intern/yanghaibo/installed/anaconda3/envs/general/lib/python3.10/site-packages/pytorch_lightning/core/datamodule.py:469: LightningDeprecationWarning: DataModule.setup has already been called, so it will not be called again. In v1.6 this behavior will change to always call DataModule.setup.
rank_zero_deprecation(
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1,2,3,4,5,6,7]
You have not specified an optimizer or scheduler within the DeepSpeed config. Using `configure_optimizers` to define optimizer and scheduler.
Project config
data:
target: sgm.data.video_dataset.VideoDataset
params:
base_folder: datas/OBJAVERSE-LVIS-example/images
eval_folder: validation_set_example
width: 512
height: 512
sample_frames: 16
batch_size: 1
num_workers: 1
model:
target: vtdm.vtdm_gen_v01.VideoLDM
base_learning_rate: 1.0e-05
params:
input_key: video
scale_factor: 0.18215
log_keys: caption
num_samples: 16
trained_param_keys:
- all
en_and_decode_n_samples_a_time: 16
disable_first_stage_autocast: true
ckpt_path: /mnt/afs_intern/yanghaibo/datas/download_checkpoints/svd_checkpoints/stable-video-diffusion-img2vid-xt/svd_xt_image_decoder.safetensors
denoiser_config:
target: sgm.modules.diffusionmodules.denoiser.Denoiser
params:
scaling_config:
target: sgm.modules.diffusionmodules.denoiser_scaling.VScalingWithEDMcNoise
network_config:
target: sgm.modules.diffusionmodules.video_model.VideoUNet
params:
adm_in_channels: 768
num_classes: sequential
use_checkpoint: true
in_channels: 8
out_channels: 4
model_channels: 320
attention_resolutions:
- 4
- 2
- 1
num_res_blocks: 2
channel_mult:
- 1
- 2
- 4
- 4
num_head_channels: 64
use_linear_in_transformer: true
transformer_depth: 1
context_dim: 1024
spatial_transformer_attn_type: softmax-xformers
extra_ff_mix_layer: true
use_spatial_context: true
merge_strategy: learned_with_images
video_kernel_size:
- 3
- 1
- 1
conditioner_config:
target: sgm.modules.GeneralConditioner
params:
emb_models:
- is_trainable: false
input_key: cond_frames_without_noise
ucg_rate: 0.1
target: sgm.modules.encoders.modules.FrozenOpenCLIPImagePredictionEmbedder
params:
n_cond_frames: 1
n_copies: 1
open_clip_embedding_config:
target: sgm.modules.encoders.modules.FrozenOpenCLIPImageEmbedder
params:
version: ckpts/open_clip_pytorch_model.bin
freeze: true
- is_trainable: false
input_key: video
ucg_rate: 0.0
target: vtdm.encoders.AesEmbedder
- is_trainable: false
input_key: elevation
target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
params:
outdim: 256
- input_key: cond_frames
is_trainable: false
ucg_rate: 0.1
target: sgm.modules.encoders.modules.VideoPredictionEmbedderWithEncoder
params:
disable_encoder_autocast: true
n_cond_frames: 1
n_copies: 16
is_ae: true
encoder_config:
target: sgm.models.autoencoder.AutoencoderKLModeOnly
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
attn_type: vanilla-xformers
double_z: true
z_channels: 4
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult:
- 1
- 2
- 4
- 4
num_res_blocks: 2
attn_resolutions: []
dropout: 0.0
lossconfig:
target: torch.nn.Identity
- input_key: cond_aug
is_trainable: false
target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
params:
outdim: 256
first_stage_config:
target: sgm.models.autoencoder.AutoencoderKL
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
attn_type: vanilla-xformers
double_z: true
z_channels: 4
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult:
- 1
- 2
- 4
- 4
num_res_blocks: 2
attn_resolutions: []
dropout: 0.0
lossconfig:
target: torch.nn.Identity
loss_fn_config:
target: sgm.modules.diffusionmodules.loss.StandardDiffusionLoss
params:
num_frames: 16
batch2model_keys:
- num_video_frames
- image_only_indicator
sigma_sampler_config:
target: sgm.modules.diffusionmodules.sigma_sampling.EDMSampling
params:
p_mean: 1.0
p_std: 1.6
loss_weighting_config:
target: sgm.modules.diffusionmodules.loss_weighting.VWeighting
sampler_config:
target: sgm.modules.diffusionmodules.sampling.EulerEDMSampler
params:
num_steps: 25
verbose: true
discretization_config:
target: sgm.modules.diffusionmodules.discretizer.EDMDiscretization
params:
sigma_max: 700.0
guider_config:
target: sgm.modules.diffusionmodules.guiders.LinearPredictionGuider
params:
num_frames: 16
max_scale: 2.5
min_scale: 1.0
Lightning config
trainer:
gpus: 7,
logger_refresh_rate: 5
check_val_every_n_epoch: 1
max_epochs: 50
accelerator: cuda
strategy: deepspeed_stage_2
precision: 16
callbacks:
image_logger:
target: vtdm.callbacks.ImageLogger
params:
log_on_batch_idx: true
increase_log_steps: false
log_first_step: true
batch_frequency: 200
max_images: 8
clamp: true
log_images_kwargs:
'N': 8
sample: true
ucg_keys:
- cond_frames
- cond_frames_without_noise
metrics_over_trainsteps_checkpoint:
target: pytorch_lightning.callbacks.ModelCheckpoint
params:
every_n_train_steps: 3000
save_weights_only: false
| Name | Type | Params
------------------------------------------------------------
0 | model | OpenAIWrapper | 1.5 B
1 | denoiser | Denoiser | 0
2 | conditioner | GeneralConditioner | 1.1 B
3 | first_stage_model | AutoencoderKL | 83.7 M
4 | loss_fn | StandardDiffusionLoss | 0
------------------------------------------------------------
1.5 B Trainable params
1.2 B Non-trainable params
2.7 B Total params
5,438.442 Total estimated model params size (MB)
/mnt/afs_intern/yanghaibo/installed/anaconda3/envs/general/lib/python3.10/site-packages/pytorch_lightning/callbacks/model_checkpoint.py:617: UserWarning: Checkpoint directory outputs/logs/train-v01/2024-09-29T13-20-04_train-v01_00/checkpoints exists and is not empty.
rank_zero_warn(f"Checkpoint directory {dirpath} exists and is not empty.")
[09/29 13:21:13 VTDM]: Epoch: 0, batch_num: inf
/mnt/afs_intern/yanghaibo/installed/anaconda3/envs/general/lib/python3.10/site-packages/pytorch_lightning/utilities/data.py:56: UserWarning: Trying to infer the `batch_size` from an ambiguous collection. The batch size we found is 1. To avoid any miscalculations, use `self.log(..., batch_size=batch_size)`.
warning_cache.warn(
############################## Sampling setting ##############################
Sampler: EulerEDMSampler
Discretization: EDMDiscretization
Guider: LinearPredictionGuider
Sampling with EulerEDMSampler for 26 steps: 0%| | 0/26 [00:00<?, ?it/s]/mnt/afs_intern/yanghaibo/installed/anaconda3/envs/general/lib/python3.10/site-packages/torch/utils/checkpoint.py:31: UserWarning: None of the inputs have requires_grad=True. Gradients will be None
warnings.warn("None of the inputs have requires_grad=True. Gradients will be None")
Sampling with EulerEDMSampler for 26 steps: 96%|██████████████████████████████████████████████████████████████████████████████████████████▍ | 25/26 [00:36<00:01, 1.48s/it]
[09/29 13:22:36 VTDM]: [Epoch 0] [Batch 5/inf 16.49 s/batch] => loss: 0.025749
[09/29 13:22:48 VTDM]: [Epoch 0] [Batch 10/inf 9.47 s/batch] => loss: 0.034793
Average Epoch time: 94.71 seconds
Average Peak memory 43059.05 MiB
[09/29 13:23:36 VTDM]: Epoch: 1, batch_num: inf
############################## Sampling setting ##############################
Sampler: EulerEDMSampler
Discretization: EDMDiscretization
Guider: LinearPredictionGuider
Sampling with EulerEDMSampler for 26 steps: 96%|██████████████████████████████████████████████████████████████████████████████████████████▍ | 25/26 [00:25<00:01, 1.02s/it]
[09/29 13:24:19 VTDM]: [Epoch 1] [Batch 5/inf 8.63 s/batch] => loss: 0.030595
[09/29 13:24:31 VTDM]: [Epoch 1] [Batch 10/inf 5.54 s/batch] => loss: 0.113596
Average Epoch time: 55.36 seconds
Average Peak memory 43059.05 MiB
[09/29 13:25:18 VTDM]: Epoch: 2, batch_num: inf
############################## Sampling setting ##############################
Sampler: EulerEDMSampler
Discretization: EDMDiscretization
Guider: LinearPredictionGuider
Sampling with EulerEDMSampler for 26 steps: 96%|██████████████████████████████████████████████████████████████████████████████████████████▍ | 25/26 [00:25<00:01, 1.02s/it]
[09/29 13:26:01 VTDM]: [Epoch 2] [Batch 5/inf 8.58 s/batch] => loss: 0.127297
[09/29 13:26:13 VTDM]: [Epoch 2] [Batch 10/inf 5.51 s/batch] => loss: 0.039552
Average Epoch time: 55.14 seconds
Average Peak memory 43059.05 MiB
[09/29 13:26:59 VTDM]: Epoch: 3, batch_num: inf
############################## Sampling setting ##############################
|