Positional Encoding Shape Mismatch in Clay Encoder

.gitignore

@@ -71,3 +71,5 @@ datadisk/
 # pip
 .venv
 *.ckpt
+data*/
+cubes/

Untitled.ipynb

@@ -0,0 +1,97 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "daf2ce7c-fef0-464a-8ca7-9a457890f245",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Add the repo root to the sys path for the model import below\n",
+    "import sys\n",
+    "\n",
+    "sys.path.append(\"../..\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "b943e3ee-55bf-4b07-a03e-baed01838982",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# from torchvision.transformers import v2\n",
+    "# from claymodule.module import ClayMAEModule"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "0c4d59de-4818-4bfb-84af-aa43bf6e24e8",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "False\n"
+     ]
+    }
+   ],
+   "source": [
+    "from torchvision import transforms\n",
+    "\n",
+    "print(hasattr(transforms, \"v2\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "ba499594-4a04-4263-8e74-b2944fdc08bb",
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "ModuleNotFoundError",
+     "evalue": "No module named 'torchvision.transformers'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
+      "\u001b[31mModuleNotFoundError\u001b[39m                       Traceback (most recent call last)",
+      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[7]\u001b[39m\u001b[32m, line 1\u001b[39m\n\u001b[32m----> \u001b[39m\u001b[32m1\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mtorchvision\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mtransformers\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m v2\n",
+      "\u001b[31mModuleNotFoundError\u001b[39m: No module named 'torchvision.transformers'"
+     ]
+    }
+   ],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6d200a02-2e9f-449b-bb8f-ab595d1e5126",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}