2509

src/sample.ipynb

@@ -281,22 +281,10 @@
    "metadata": {},
    "outputs": [
     {
-     "ename": "OutOfMemoryError",
-     "evalue": "CUDA out of memory. Tried to allocate 20.00 MiB. GPU 0 has a total capacity of 31.36 GiB of which 12.81 MiB is free. Process 1767 has 25.21 GiB memory in use. Including non-PyTorch memory, this process has 6.12 GiB memory in use. Of the allocated memory 5.63 GiB is allocated by PyTorch, and 1.67 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation.  See documentation for Memory Management  (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
-      "\u001b[31mOutOfMemoryError\u001b[39m                          Traceback (most recent call last)",
-      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[2]\u001b[39m\u001b[32m, line 13\u001b[39m\n\u001b[32m      8\u001b[39m dtype = torch.float16\n\u001b[32m      9\u001b[39m device = torch.device(\u001b[33m\"\u001b[39m\u001b[33mcuda\u001b[39m\u001b[33m\"\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m torch.cuda.is_available() \u001b[38;5;28;01melse\u001b[39;00m \u001b[33m\"\u001b[39m\u001b[33mcpu\u001b[39m\u001b[33m\"\u001b[39m)\n\u001b[32m     11\u001b[39m unet = \u001b[43mUNet2DConditionModel\u001b[49m\u001b[43m.\u001b[49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43m/workspace/sdxs3d\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[38;5;66;43;03m#\"AiArtLab/sdxs3d\"\u001b[39;49;00m\n\u001b[32m     12\u001b[39m \u001b[43m                                            \u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msubfolder\u001b[49m\u001b[43m=\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43munet\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtorch_dtype\u001b[49m\u001b[43m=\u001b[49m\u001b[43mdtype\u001b[49m\n\u001b[32m---> \u001b[39m\u001b[32m13\u001b[39m \u001b[43m)\u001b[49m\u001b[43m.\u001b[49m\u001b[43mto\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdevice\u001b[49m\u001b[43m)\u001b[49m.eval()\n\u001b[32m     15\u001b[39m unet.save_pretrained(\u001b[33m\"\u001b[39m\u001b[33m/workspace/sdxs3d/unet\u001b[39m\u001b[33m\"\u001b[39m)\n\u001b[32m     16\u001b[39m \u001b[38;5;28mprint\u001b[39m(\u001b[33m\"\u001b[39m\u001b[33mok\u001b[39m\u001b[33m\"\u001b[39m)\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/usr/local/lib/python3.11/dist-packages/diffusers/models/modeling_utils.py:1424\u001b[39m, in \u001b[36mModelMixin.to\u001b[39m\u001b[34m(self, *args, **kwargs)\u001b[39m\n\u001b[32m   1419\u001b[39m     logger.warning(\n\u001b[32m   1420\u001b[39m         \u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mThe module \u001b[39m\u001b[33m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m.\u001b[34m__class__\u001b[39m.\u001b[34m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m'\u001b[39m\u001b[33m is group offloaded and moving it using `.to()` is not supported.\u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m   1421\u001b[39m     )\n\u001b[32m   1422\u001b[39m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\n\u001b[32m-> \u001b[39m\u001b[32m1424\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m.\u001b[49m\u001b[43mto\u001b[49m\u001b[43m(\u001b[49m\u001b[43m*\u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/usr/local/lib/python3.11/dist-packages/torch/nn/modules/module.py:1369\u001b[39m, in \u001b[36mModule.to\u001b[39m\u001b[34m(self, *args, **kwargs)\u001b[39m\n\u001b[32m   1366\u001b[39m         \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[32m   1367\u001b[39m             \u001b[38;5;28;01mraise\u001b[39;00m\n\u001b[32m-> \u001b[39m\u001b[32m1369\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_apply\u001b[49m\u001b[43m(\u001b[49m\u001b[43mconvert\u001b[49m\u001b[43m)\u001b[49m\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/usr/local/lib/python3.11/dist-packages/torch/nn/modules/module.py:928\u001b[39m, in \u001b[36mModule._apply\u001b[39m\u001b[34m(self, fn, recurse)\u001b[39m\n\u001b[32m    926\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m recurse:\n\u001b[32m    927\u001b[39m     \u001b[38;5;28;01mfor\u001b[39;00m module \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m.children():\n\u001b[32m--> \u001b[39m\u001b[32m928\u001b[39m         \u001b[43mmodule\u001b[49m\u001b[43m.\u001b[49m\u001b[43m_apply\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfn\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    930\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34mcompute_should_use_set_data\u001b[39m(tensor, tensor_applied):\n\u001b[32m    931\u001b[39m     \u001b[38;5;28;01mif\u001b[39;00m torch._has_compatible_shallow_copy_type(tensor, tensor_applied):\n\u001b[32m    932\u001b[39m         \u001b[38;5;66;03m# If the new tensor has compatible tensor type as the existing tensor,\u001b[39;00m\n\u001b[32m    933\u001b[39m         \u001b[38;5;66;03m# the current behavior is to change the tensor in-place using `.data =`,\u001b[39;00m\n\u001b[32m   (...)\u001b[39m\u001b[32m    938\u001b[39m         \u001b[38;5;66;03m# global flag to let the user control whether they want the future\u001b[39;00m\n\u001b[32m    939\u001b[39m         \u001b[38;5;66;03m# behavior of overwriting the existing tensor or not.\u001b[39;00m\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/usr/local/lib/python3.11/dist-packages/torch/nn/modules/module.py:928\u001b[39m, in \u001b[36mModule._apply\u001b[39m\u001b[34m(self, fn, recurse)\u001b[39m\n\u001b[32m    926\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m recurse:\n\u001b[32m    927\u001b[39m     \u001b[38;5;28;01mfor\u001b[39;00m module \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m.children():\n\u001b[32m--> \u001b[39m\u001b[32m928\u001b[39m         \u001b[43mmodule\u001b[49m\u001b[43m.\u001b[49m\u001b[43m_apply\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfn\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    930\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34mcompute_should_use_set_data\u001b[39m(tensor, tensor_applied):\n\u001b[32m    931\u001b[39m     \u001b[38;5;28;01mif\u001b[39;00m torch._has_compatible_shallow_copy_type(tensor, tensor_applied):\n\u001b[32m    932\u001b[39m         \u001b[38;5;66;03m# If the new tensor has compatible tensor type as the existing tensor,\u001b[39;00m\n\u001b[32m    933\u001b[39m         \u001b[38;5;66;03m# the current behavior is to change the tensor in-place using `.data =`,\u001b[39;00m\n\u001b[32m   (...)\u001b[39m\u001b[32m    938\u001b[39m         \u001b[38;5;66;03m# global flag to let the user control whether they want the future\u001b[39;00m\n\u001b[32m    939\u001b[39m         \u001b[38;5;66;03m# behavior of overwriting the existing tensor or not.\u001b[39;00m\n",
-      "    \u001b[31m[... skipping similar frames: Module._apply at line 928 (4 times)]\u001b[39m\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/usr/local/lib/python3.11/dist-packages/torch/nn/modules/module.py:928\u001b[39m, in \u001b[36mModule._apply\u001b[39m\u001b[34m(self, fn, recurse)\u001b[39m\n\u001b[32m    926\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m recurse:\n\u001b[32m    927\u001b[39m     \u001b[38;5;28;01mfor\u001b[39;00m module \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m.children():\n\u001b[32m--> \u001b[39m\u001b[32m928\u001b[39m         \u001b[43mmodule\u001b[49m\u001b[43m.\u001b[49m\u001b[43m_apply\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfn\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    930\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34mcompute_should_use_set_data\u001b[39m(tensor, tensor_applied):\n\u001b[32m    931\u001b[39m     \u001b[38;5;28;01mif\u001b[39;00m torch._has_compatible_shallow_copy_type(tensor, tensor_applied):\n\u001b[32m    932\u001b[39m         \u001b[38;5;66;03m# If the new tensor has compatible tensor type as the existing tensor,\u001b[39;00m\n\u001b[32m    933\u001b[39m         \u001b[38;5;66;03m# the current behavior is to change the tensor in-place using `.data =`,\u001b[39;00m\n\u001b[32m   (...)\u001b[39m\u001b[32m    938\u001b[39m         \u001b[38;5;66;03m# global flag to let the user control whether they want the future\u001b[39;00m\n\u001b[32m    939\u001b[39m         \u001b[38;5;66;03m# behavior of overwriting the existing tensor or not.\u001b[39;00m\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/usr/local/lib/python3.11/dist-packages/torch/nn/modules/module.py:955\u001b[39m, in \u001b[36mModule._apply\u001b[39m\u001b[34m(self, fn, recurse)\u001b[39m\n\u001b[32m    951\u001b[39m \u001b[38;5;66;03m# Tensors stored in modules are graph leaves, and we don't want to\u001b[39;00m\n\u001b[32m    952\u001b[39m \u001b[38;5;66;03m# track autograd history of `param_applied`, so we have to use\u001b[39;00m\n\u001b[32m    953\u001b[39m \u001b[38;5;66;03m# `with torch.no_grad():`\u001b[39;00m\n\u001b[32m    954\u001b[39m \u001b[38;5;28;01mwith\u001b[39;00m torch.no_grad():\n\u001b[32m--> \u001b[39m\u001b[32m955\u001b[39m     param_applied = \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[43mparam\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    956\u001b[39m p_should_use_set_data = compute_should_use_set_data(param, param_applied)\n\u001b[32m    958\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mtorch\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01m_subclasses\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mfake_tensor\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m FakeTensor\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/usr/local/lib/python3.11/dist-packages/torch/nn/modules/module.py:1355\u001b[39m, in \u001b[36mModule.to.<locals>.convert\u001b[39m\u001b[34m(t)\u001b[39m\n\u001b[32m   1348\u001b[39m     \u001b[38;5;28;01mif\u001b[39;00m convert_to_format \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m t.dim() \u001b[38;5;129;01min\u001b[39;00m (\u001b[32m4\u001b[39m, \u001b[32m5\u001b[39m):\n\u001b[32m   1349\u001b[39m         \u001b[38;5;28;01mreturn\u001b[39;00m t.to(\n\u001b[32m   1350\u001b[39m             device,\n\u001b[32m   1351\u001b[39m             dtype \u001b[38;5;28;01mif\u001b[39;00m t.is_floating_point() \u001b[38;5;129;01mor\u001b[39;00m t.is_complex() \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[32m   1352\u001b[39m             non_blocking,\n\u001b[32m   1353\u001b[39m             memory_format=convert_to_format,\n\u001b[32m   1354\u001b[39m         )\n\u001b[32m-> \u001b[39m\u001b[32m1355\u001b[39m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mt\u001b[49m\u001b[43m.\u001b[49m\u001b[43mto\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m   1356\u001b[39m \u001b[43m        \u001b[49m\u001b[43mdevice\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m   1357\u001b[39m \u001b[43m        \u001b[49m\u001b[43mdtype\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mt\u001b[49m\u001b[43m.\u001b[49m\u001b[43mis_floating_point\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mt\u001b[49m\u001b[43m.\u001b[49m\u001b[43mis_complex\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[32m   1358\u001b[39m \u001b[43m        \u001b[49m\u001b[43mnon_blocking\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m   1359\u001b[39m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m   1360\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mNotImplementedError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[32m   1361\u001b[39m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mstr\u001b[39m(e) == \u001b[33m\"\u001b[39m\u001b[33mCannot copy out of meta tensor; no data!\u001b[39m\u001b[33m\"\u001b[39m:\n",
-      "\u001b[31mOutOfMemoryError\u001b[39m: CUDA out of memory. Tried to allocate 20.00 MiB. GPU 0 has a total capacity of 31.36 GiB of which 12.81 MiB is free. Process 1767 has 25.21 GiB memory in use. Including non-PyTorch memory, this process has 6.12 GiB memory in use. Of the allocated memory 5.63 GiB is allocated by PyTorch, and 1.67 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation.  See documentation for Memory Management  (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ok\n"
      ]
     }
    ],

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a5f30e9b12b0278761340b15f4daf2fcfe69ab45f3884276d8f220c0d064530
+oid sha256:88a4685341dba55274c8ae3991144a18be96dd6257c81612e749a408e934544f
 size 3092571208