Update JupyterNB for Visualization

1 year ago · a2138aa6a0
2 changed files with 1675 additions and 0 deletions
--- a/my-FEA-net.ipynb
+++ b/my-FEA-net.ipynb
--- a/test.ipynb
+++ b/test.ipynb
@ -0,0 +1,127 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "aef142c9-a3d0-408c-a87f-695167d49dea",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(61, 181, 2)\n",
+      "(60, 180)\n",
+      "(432, 25)\n",
+      "(432, 4, 2)\n",
+      "(432, 72)\n"
+     ]
+    },
+    {
+     "ename": "RuntimeError",
+     "evalue": "Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mRuntimeError\u001b[0m                              Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[1], line 30\u001b[0m\n\u001b[1;32m     27\u001b[0m loss_function \u001b[38;5;241m=\u001b[39m nn\u001b[38;5;241m.\u001b[39mMSELoss()\n\u001b[1;32m     29\u001b[0m \u001b[38;5;66;03m# Predict \u001b[39;00m\n\u001b[0;32m---> 30\u001b[0m pred \u001b[38;5;241m=\u001b[39m \u001b[43mtest\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mcheckpoints/ANN_\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mpretrained_mod\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43m_opt.pt\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mX\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     32\u001b[0m \u001b[38;5;66;03m# Calculate loss\u001b[39;00m\n\u001b[1;32m     33\u001b[0m pred_loss\u001b[38;5;241m=\u001b[39m[]\n",
+      "File \u001b[0;32m/workspace/EMsFEA-net/test.py:13\u001b[0m, in \u001b[0;36mtest\u001b[0;34m(model_load_path, X, standard, device)\u001b[0m\n\u001b[1;32m     12\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mtest\u001b[39m(model_load_path, X, standard \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m, device \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m0\u001b[39m):\n\u001b[0;32m---> 13\u001b[0m     model \u001b[38;5;241m=\u001b[39m \u001b[43mtorch\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mload\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel_load_path\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     15\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m standard:\n\u001b[1;32m     16\u001b[0m         X \u001b[38;5;241m=\u001b[39m standardization(X)\n",
+      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/serialization.py:1014\u001b[0m, in \u001b[0;36mload\u001b[0;34m(f, map_location, pickle_module, weights_only, mmap, **pickle_load_args)\u001b[0m\n\u001b[1;32m   1012\u001b[0m             \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mRuntimeError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m   1013\u001b[0m                 \u001b[38;5;28;01mraise\u001b[39;00m pickle\u001b[38;5;241m.\u001b[39mUnpicklingError(UNSAFE_MESSAGE \u001b[38;5;241m+\u001b[39m \u001b[38;5;28mstr\u001b[39m(e)) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m-> 1014\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_load\u001b[49m\u001b[43m(\u001b[49m\u001b[43mopened_zipfile\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1015\u001b[0m \u001b[43m                     \u001b[49m\u001b[43mmap_location\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1016\u001b[0m \u001b[43m                     \u001b[49m\u001b[43mpickle_module\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1017\u001b[0m \u001b[43m                     \u001b[49m\u001b[43moverall_storage\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moverall_storage\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1018\u001b[0m \u001b[43m                     \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mpickle_load_args\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1019\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m mmap:\n\u001b[1;32m   1020\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mRuntimeError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmmap can only be used with files saved with \u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m   1021\u001b[0m                        \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m`torch.save(_use_new_zipfile_serialization=True), \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m   1022\u001b[0m                        \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mplease torch.save your checkpoint with this option in order to use mmap.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
+      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/serialization.py:1422\u001b[0m, in \u001b[0;36m_load\u001b[0;34m(zip_file, map_location, pickle_module, pickle_file, overall_storage, **pickle_load_args)\u001b[0m\n\u001b[1;32m   1420\u001b[0m unpickler \u001b[38;5;241m=\u001b[39m UnpicklerWrapper(data_file, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mpickle_load_args)\n\u001b[1;32m   1421\u001b[0m unpickler\u001b[38;5;241m.\u001b[39mpersistent_load \u001b[38;5;241m=\u001b[39m persistent_load\n\u001b[0;32m-> 1422\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[43munpickler\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mload\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1424\u001b[0m torch\u001b[38;5;241m.\u001b[39m_utils\u001b[38;5;241m.\u001b[39m_validate_loaded_sparse_tensors()\n\u001b[1;32m   1425\u001b[0m torch\u001b[38;5;241m.\u001b[39m_C\u001b[38;5;241m.\u001b[39m_log_api_usage_metadata(\n\u001b[1;32m   1426\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtorch.load.metadata\u001b[39m\u001b[38;5;124m\"\u001b[39m, {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mserialization_id\u001b[39m\u001b[38;5;124m\"\u001b[39m: zip_file\u001b[38;5;241m.\u001b[39mserialization_id()}\n\u001b[1;32m   1427\u001b[0m )\n",
+      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/serialization.py:1392\u001b[0m, in \u001b[0;36m_load.<locals>.persistent_load\u001b[0;34m(saved_id)\u001b[0m\n\u001b[1;32m   1390\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m   1391\u001b[0m     nbytes \u001b[38;5;241m=\u001b[39m numel \u001b[38;5;241m*\u001b[39m torch\u001b[38;5;241m.\u001b[39m_utils\u001b[38;5;241m.\u001b[39m_element_size(dtype)\n\u001b[0;32m-> 1392\u001b[0m     typed_storage \u001b[38;5;241m=\u001b[39m \u001b[43mload_tensor\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdtype\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnbytes\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkey\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m_maybe_decode_ascii\u001b[49m\u001b[43m(\u001b[49m\u001b[43mlocation\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1394\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m typed_storage\n",
+      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/serialization.py:1366\u001b[0m, in \u001b[0;36m_load.<locals>.load_tensor\u001b[0;34m(dtype, numel, key, location)\u001b[0m\n\u001b[1;32m   1361\u001b[0m         storage\u001b[38;5;241m.\u001b[39mbyteswap(dtype)\n\u001b[1;32m   1363\u001b[0m \u001b[38;5;66;03m# TODO: Once we decide to break serialization FC, we can\u001b[39;00m\n\u001b[1;32m   1364\u001b[0m \u001b[38;5;66;03m# stop wrapping with TypedStorage\u001b[39;00m\n\u001b[1;32m   1365\u001b[0m typed_storage \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mstorage\u001b[38;5;241m.\u001b[39mTypedStorage(\n\u001b[0;32m-> 1366\u001b[0m     wrap_storage\u001b[38;5;241m=\u001b[39m\u001b[43mrestore_location\u001b[49m\u001b[43m(\u001b[49m\u001b[43mstorage\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlocation\u001b[49m\u001b[43m)\u001b[49m,\n\u001b[1;32m   1367\u001b[0m     dtype\u001b[38;5;241m=\u001b[39mdtype,\n\u001b[1;32m   1368\u001b[0m     _internal\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m   1370\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m typed_storage\u001b[38;5;241m.\u001b[39m_data_ptr() \u001b[38;5;241m!=\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[1;32m   1371\u001b[0m     loaded_storages[key] \u001b[38;5;241m=\u001b[39m typed_storage\n",
+      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/serialization.py:381\u001b[0m, in \u001b[0;36mdefault_restore_location\u001b[0;34m(storage, location)\u001b[0m\n\u001b[1;32m    379\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdefault_restore_location\u001b[39m(storage, location):\n\u001b[1;32m    380\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m _, _, fn \u001b[38;5;129;01min\u001b[39;00m _package_registry:\n\u001b[0;32m--> 381\u001b[0m         result \u001b[38;5;241m=\u001b[39m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[43mstorage\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlocation\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    382\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m result \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m    383\u001b[0m             \u001b[38;5;28;01mreturn\u001b[39;00m result\n",
+      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/serialization.py:274\u001b[0m, in \u001b[0;36m_cuda_deserialize\u001b[0;34m(obj, location)\u001b[0m\n\u001b[1;32m    272\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_cuda_deserialize\u001b[39m(obj, location):\n\u001b[1;32m    273\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m location\u001b[38;5;241m.\u001b[39mstartswith(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mcuda\u001b[39m\u001b[38;5;124m'\u001b[39m):\n\u001b[0;32m--> 274\u001b[0m         device \u001b[38;5;241m=\u001b[39m \u001b[43mvalidate_cuda_device\u001b[49m\u001b[43m(\u001b[49m\u001b[43mlocation\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    275\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mgetattr\u001b[39m(obj, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_torch_load_uninitialized\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mFalse\u001b[39;00m):\n\u001b[1;32m    276\u001b[0m             \u001b[38;5;28;01mwith\u001b[39;00m torch\u001b[38;5;241m.\u001b[39mcuda\u001b[38;5;241m.\u001b[39mdevice(device):\n",
+      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/serialization.py:258\u001b[0m, in \u001b[0;36mvalidate_cuda_device\u001b[0;34m(location)\u001b[0m\n\u001b[1;32m    255\u001b[0m device \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mcuda\u001b[38;5;241m.\u001b[39m_utils\u001b[38;5;241m.\u001b[39m_get_device_index(location, \u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m    257\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m torch\u001b[38;5;241m.\u001b[39mcuda\u001b[38;5;241m.\u001b[39mis_available():\n\u001b[0;32m--> 258\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mRuntimeError\u001b[39;00m(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mAttempting to deserialize object on a CUDA \u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[1;32m    259\u001b[0m                        \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdevice but torch.cuda.is_available() is False. \u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[1;32m    260\u001b[0m                        \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mIf you are running on a CPU-only machine, \u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[1;32m    261\u001b[0m                        \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mplease use torch.load with map_location=torch.device(\u001b[39m\u001b[38;5;130;01m\\'\u001b[39;00m\u001b[38;5;124mcpu\u001b[39m\u001b[38;5;130;01m\\'\u001b[39;00m\u001b[38;5;124m) \u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[1;32m    262\u001b[0m                        \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mto map your storages to the CPU.\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m    263\u001b[0m device_count \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mcuda\u001b[38;5;241m.\u001b[39mdevice_count()\n\u001b[1;32m    264\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m device \u001b[38;5;241m>\u001b[39m\u001b[38;5;241m=\u001b[39m device_count:\n",
+      "\u001b[0;31mRuntimeError\u001b[0m: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU."
+     ]
+    }
+   ],
+   "source": [
+    "from test import test\n",
+    "\n",
+    "import numpy as np\n",
+    "\n",
+    "import torch\n",
+    "import torch.nn as nn\n",
+    "import torch.nn.functional as F\n",
+    "\n",
+    "from utils.data_standardizer import standardization\n",
+    "from utils.data_loader import data_loader\n",
+    "\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "# Load datasets\n",
+    "# test data select:\n",
+    "dataload_mod='mod3' # opt: mod1 mod2 mod3\n",
+    "# pretrained model select:\n",
+    "pretrained_mod='mod3' # opt: mod1 mod2 mod3\n",
+    "\n",
+    "dst_path='datasets/top88_'+ dataload_mod + '_xPhys_180_60.npy'\n",
+    "U_path='datasets/top88_'+ dataload_mod + '_u_180_60.npy'\n",
+    "global_density, global_displace, coarse_density, coarse_displace, fine_displace = data_loader(dst_path, U_path)\n",
+    "X = np.hstack((coarse_density[:,:] , coarse_displace[:,:,0] , coarse_displace[:,:,1]))\n",
+    "Y = fine_displace[:,:]\n",
+    "\n",
+    "# Set loss function\n",
+    "loss_function = nn.MSELoss()\n",
+    "\n",
+    "# Predict \n",
+    "pred = test('checkpoints/ANN_' + pretrained_mod + '_opt.pt', X)\n",
+    "\n",
+    "# Calculate loss\n",
+    "pred_loss=[]\n",
+    "device = f'cuda:{0}' if torch.cuda.is_available() else 'cpu'\n",
+    "Y = torch.from_numpy(Y).type(torch.float32).to(device)\n",
+    "for i in range(pred.shape[0]):\n",
+    "    pred_loss.append(loss_function(pred[i,:],Y[i,:]).item())\n",
+    "\n",
+    "print('Total loss: '+ str(loss_function(pred,Y).item()))\n",
+    "\n",
+    "# Plot \n",
+    "plt.plot(range(pred.shape[0]),pred_loss)\n",
+    "plt.ylabel('Loss')\n",
+    "plt.xlabel('Coarse mesh id')\n",
+    "plt.title(\"Linear graph\") \n",
+    "plt.show()\n",
+    "\n",
+    "loss_metrix = np.asarray(pred_loss)\n",
+    "loss_metrix = loss_metrix.reshape(int(60/5), int(180/5))\n",
+    "plt.matshow(loss_metrix)\n",
+    "plt.title(\"Show loss value in grid\") \n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a2946a86-77ac-466f-8869-aa91f5e2602c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "language": "python",
+   "name": "base"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}