updated data link, increased BNN expo
This commit is contained in:
NT committed
1 parent
33ba170d77
commit
8ee86cf058
2 files changed
+109
-94
No files matched your search
+99
-85
@@ -3,7 +3,7 @@
|
||||
"nbformat_minor": 0,
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"name": "bayesian-code-jun25-fromBook.ipynb",
|
||||
"name": "bayesian-code-jul30upload.ipynb",
|
||||
"provenance": [],
|
||||
"collapsed_sections": []
|
||||
},
|
||||
@@ -58,25 +58,27 @@
|
||||
"base_uri": "https://localhost:8080/"
|
||||
},
|
||||
"id": "JwZudtWauiGa",
|
||||
"outputId": "af0a6e19-4762-4787-dbc6-422b73f58ac9"
|
||||
"outputId": "d0f589f8-959e-40e1-d1c8-8fe06c33f36b"
|
||||
},
|
||||
"source": [
|
||||
"import numpy as np\n",
|
||||
"import os.path, random\n",
|
||||
"\n",
|
||||
"# as before, either download or use gdrive\n",
|
||||
"# get training data: as in the previous supervised example, either download or use gdrive\n",
|
||||
"dir = \"./\"\n",
|
||||
"if True:\n",
|
||||
" if not os.path.isfile('data-airfoils.npz'):\n",
|
||||
" import urllib.request\n",
|
||||
" url=\"https://ge.in.tum.de/download/2019-deepFlowPred/data.npz\"\n",
|
||||
" import requests\n",
|
||||
" print(\"Downloading training data (300MB), this can take a few minutes the first time...\")\n",
|
||||
" urllib.request.urlretrieve(url, 'data-airfoils.npz')\n",
|
||||
" npfile=np.load('data-airfoils.npz')\n",
|
||||
" with open(\"data-airfoils.npz\", 'wb') as datafile:\n",
|
||||
" resp = requests.get('https://dataserv.ub.tum.de/s/m1615239/download?path=%2F&files=dfp-data-400.npz', verify=False)\n",
|
||||
" datafile.write(resp.content)\n",
|
||||
"else: # cf supervised airfoil code:\n",
|
||||
" from google.colab import drive\n",
|
||||
" drive.mount('/content/gdrive')\n",
|
||||
" npfile=np.load('gdrive/My Drive/data-airfoils.npz')\n",
|
||||
" dir = \"./gdrive/My Drive/\"\n",
|
||||
"\n",
|
||||
"npfile=np.load(dir+'data-airfoils.npz')\n",
|
||||
"print(\"Loaded data, {} training, {} validation samples\".format(len(npfile[\"inputs\"]),len(npfile[\"vinputs\"])))\n",
|
||||
"print(\"Size of the inputs array: \"+format(npfile[\"inputs\"].shape))\n",
|
||||
"\n",
|
||||
@@ -85,14 +87,28 @@
|
||||
"y_train = np.moveaxis(npfile[\"targets\"],1,-1)\n",
|
||||
"\n",
|
||||
"X_val = np.moveaxis(npfile[\"vinputs\"],1,-1)\n",
|
||||
"y_val = np.moveaxis(npfile[\"vtargets\"],1,-1)\n"
|
||||
"y_val = np.moveaxis(npfile[\"vtargets\"],1,-1)"
|
||||
],
|
||||
"execution_count": 1,
|
||||
"outputs": [
|
||||
{
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Drive already mounted at /content/gdrive; to attempt to forcibly remount, call drive.mount(\"/content/gdrive\", force_remount=True).\n",
|
||||
"Downloading training data (300MB), this can take a few minutes the first time...\n"
|
||||
],
|
||||
"name": "stdout"
|
||||
},
|
||||
{
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"/usr/local/lib/python3.7/dist-packages/urllib3/connectionpool.py:847: InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings\n",
|
||||
" InsecureRequestWarning)\n"
|
||||
],
|
||||
"name": "stderr"
|
||||
},
|
||||
{
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Loaded data, 320 training, 80 validation samples\n",
|
||||
"Size of the inputs array: (320, 3, 128, 128)\n"
|
||||
],
|
||||
@@ -118,7 +134,7 @@
|
||||
"height": 403
|
||||
},
|
||||
"id": "1y1zHmKlAWNs",
|
||||
"outputId": "2735a476-288e-408b-8ec2-81cd778b1106"
|
||||
"outputId": "90ecb091-a733-4c2a-fd56-56447d32d414"
|
||||
},
|
||||
"source": [
|
||||
"import pylab\n",
|
||||
@@ -204,7 +220,7 @@
|
||||
"from tensorflow_probability.python.layers import Convolution2DFlipout\n",
|
||||
"from tensorflow.keras.models import Model\n",
|
||||
"\n",
|
||||
"def tfBlockUnet(filters=3, transposed=False, kernel_size=3, bn=True, relu=True, pad=\"same\", dropout=0., flipout=False,\n",
|
||||
"def tfBlockUnet(filters=3, transposed=False, kernel_size=4, bn=True, relu=True, pad=\"same\", dropout=0., flipout=False,\n",
|
||||
" kdf=None, name=''):\n",
|
||||
" block = Sequential(name=name)\n",
|
||||
" if relu:\n",
|
||||
@@ -231,7 +247,7 @@
|
||||
"\n",
|
||||
" return block"
|
||||
],
|
||||
"execution_count": 3,
|
||||
"execution_count": 35,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
@@ -304,7 +320,7 @@
|
||||
" return Model(inputs=inputs,outputs=dout1)\n",
|
||||
"\n"
|
||||
],
|
||||
"execution_count": 4,
|
||||
"execution_count": 36,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
@@ -346,7 +362,7 @@
|
||||
" f = math.pow(0.5, e)\n",
|
||||
" return minLR + (maxLR - minLR) * f"
|
||||
],
|
||||
"execution_count": 5,
|
||||
"execution_count": 37,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
@@ -366,7 +382,7 @@
|
||||
"height": 316
|
||||
},
|
||||
"id": "tDXZO0FN02do",
|
||||
"outputId": "3f0f63d5-cb2f-405f-e639-a29b4b756ab6"
|
||||
"outputId": "d409105b-4d5e-4064-c2cf-c8a8fe2a6712"
|
||||
},
|
||||
"source": [
|
||||
"lrs=[compute_lr(i, EPOCHS, 0.5*LR,LR) for i in range(EPOCHS)]\n",
|
||||
@@ -374,7 +390,7 @@
|
||||
"plt.xlabel('Iteration')\n",
|
||||
"plt.ylabel('Learning Rate')"
|
||||
],
|
||||
"execution_count": 6,
|
||||
"execution_count": 38,
|
||||
"outputs": [
|
||||
{
|
||||
"output_type": "execute_result",
|
||||
@@ -386,7 +402,7 @@
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"execution_count": 6
|
||||
"execution_count": 38
|
||||
},
|
||||
{
|
||||
"output_type": "display_data",
|
||||
@@ -419,18 +435,18 @@
|
||||
"base_uri": "https://localhost:8080/"
|
||||
},
|
||||
"id": "LGaH2ZW73M1b",
|
||||
"outputId": "e8f02f42-1dec-4db1-e5f0-25cdfd1df374"
|
||||
"outputId": "7c5d2487-88cd-4350-c0bc-b3f477a58cf9"
|
||||
},
|
||||
"source": [
|
||||
"from tensorflow.keras.optimizers import RMSprop, Adam\n",
|
||||
"\n",
|
||||
"model=Bayes_DfpNet(expo=3,flipout=True,kl_scaling=KL_PREF*len(X_train)/BATCH_SIZE)\n",
|
||||
"model=Bayes_DfpNet(expo=4,flipout=True,kl_scaling=KL_PREF*len(X_train)/BATCH_SIZE)\n",
|
||||
"optimizer = Adam(learning_rate=LR, beta_1=0.5,beta_2=0.9999)\n",
|
||||
"\n",
|
||||
"num_params = np.sum([np.prod(v.get_shape().as_list()) for v in model.trainable_variables])\n",
|
||||
"print('The Bayesian U-Net has {} parameters.'.format(num_params))"
|
||||
],
|
||||
"execution_count": 7,
|
||||
"execution_count": 39,
|
||||
"outputs": [
|
||||
{
|
||||
"output_type": "stream",
|
||||
@@ -443,7 +459,7 @@
|
||||
{
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"The Bayesian U-Net has 133475 parameters.\n"
|
||||
"The Bayesian U-Net has 846787 parameters.\n"
|
||||
],
|
||||
"name": "stdout"
|
||||
}
|
||||
@@ -455,13 +471,11 @@
|
||||
"id": "eF4UTqeB6Y4u"
|
||||
},
|
||||
"source": [
|
||||
"Due to some differences in the implementation, the number of parameters is slightly lower than in the conventional neural network (which had 147555), even though we use the same `expo` parameter. \n",
|
||||
"\n",
|
||||
"In general, flipout layers however come with twice as many parameters compared to their conventional counterparts, since instead of a single point estimate one has to learn both mean and variance parameters for the Gaussian posterior of the weights.\n",
|
||||
"In general, flipout layers come with twice as many parameters as their conventional counterparts, since instead of a single point estimate one has to learn both mean and variance parameters for the Gaussian posterior of the weights. As we only have flipout layers for the decoder part here, the resulting model has 846787 parameters, compared to the 585667 of the conventional NN.\n",
|
||||
"\n",
|
||||
"## Training\n",
|
||||
"\n",
|
||||
"Now we are ready to run the training! Note that this might take a while, the flipout layers are significantly slower to train compared to regular layers.\n"
|
||||
"Now we are ready to run the training! Note that this might take a while (typically around 4 hours), as the flipout layers are significantly slower to train compared to regular layers.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -471,7 +485,7 @@
|
||||
"base_uri": "https://localhost:8080/"
|
||||
},
|
||||
"id": "VEQuKBegcd1K",
|
||||
"outputId": "6cec540e-d47f-41db-9463-21e4de6552cd"
|
||||
"outputId": "4030fbb2-04aa-44aa-ff6a-230788669f4f"
|
||||
},
|
||||
"source": [
|
||||
"from tensorflow.keras.losses import mae\n",
|
||||
@@ -519,23 +533,23 @@
|
||||
" mae_losses_vali += [tf.reduce_mean(mae(y_val, outputs))]\n",
|
||||
"\n",
|
||||
" if epoch<3 or epoch%20==0: \n",
|
||||
" print('Epoch {}, total loss: {:.3f}, KL loss: {:.3f}, MAE loss: {:.4f}, MAE loss vali: {:.4f}'.format(epoch, total_losses[-1], kl_losses[-1], mae_losses[-1], mae_losses_vali[-1]))\n",
|
||||
" print('Epoch {}/{}, total loss: {:.3f}, KL loss: {:.3f}, MAE loss: {:.4f}, MAE loss vali: {:.4f}'.format(epoch, EPOCHS, total_losses[-1], kl_losses[-1], mae_losses[-1], mae_losses_vali[-1]))\n",
|
||||
"\n",
|
||||
" "
|
||||
],
|
||||
"execution_count": 8,
|
||||
"execution_count": 40,
|
||||
"outputs": [
|
||||
{
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Epoch 0, total loss: 0.732, KL loss: 0.566, MAE loss: 0.1658, MAE loss vali: 0.0916\n",
|
||||
"Epoch 1, total loss: 0.639, KL loss: 0.563, MAE loss: 0.0758, MAE loss vali: 0.0612\n",
|
||||
"Epoch 2, total loss: 0.624, KL loss: 0.560, MAE loss: 0.0639, MAE loss vali: 0.0552\n",
|
||||
"Epoch 20, total loss: 0.515, KL loss: 0.478, MAE loss: 0.0370, MAE loss vali: 0.0351\n",
|
||||
"Epoch 40, total loss: 0.408, KL loss: 0.378, MAE loss: 0.0295, MAE loss vali: 0.0281\n",
|
||||
"Epoch 60, total loss: 0.309, KL loss: 0.283, MAE loss: 0.0266, MAE loss vali: 0.0257\n",
|
||||
"Epoch 80, total loss: 0.241, KL loss: 0.216, MAE loss: 0.0252, MAE loss vali: 0.0241\n",
|
||||
"Epoch 100, total loss: 0.196, KL loss: 0.172, MAE loss: 0.0240, MAE loss vali: 0.0240\n"
|
||||
"Epoch 0/120, total loss: 4.274, KL loss: 4.118, MAE loss: 0.1559, MAE loss vali: 0.0773\n",
|
||||
"Epoch 1/120, total loss: 4.151, KL loss: 4.086, MAE loss: 0.0655, MAE loss vali: 0.0546\n",
|
||||
"Epoch 2/120, total loss: 4.102, KL loss: 4.050, MAE loss: 0.0526, MAE loss vali: 0.0473\n",
|
||||
"Epoch 20/120, total loss: 3.312, KL loss: 3.284, MAE loss: 0.0285, MAE loss vali: 0.0244\n",
|
||||
"Epoch 40/120, total loss: 2.445, KL loss: 2.421, MAE loss: 0.0246, MAE loss vali: 0.0231\n",
|
||||
"Epoch 60/120, total loss: 1.653, KL loss: 1.629, MAE loss: 0.0237, MAE loss vali: 0.0221\n",
|
||||
"Epoch 80/120, total loss: 1.130, KL loss: 1.108, MAE loss: 0.0224, MAE loss vali: 0.0221\n",
|
||||
"Epoch 100/120, total loss: 0.811, KL loss: 0.789, MAE loss: 0.0222, MAE loss vali: 0.0223\n"
|
||||
],
|
||||
"name": "stdout"
|
||||
}
|
||||
@@ -556,9 +570,9 @@
|
||||
"id": "3niTOL6CcrHo",
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/",
|
||||
"height": 283
|
||||
"height": 261
|
||||
},
|
||||
"outputId": "20c65ee6-0fc4-4416-8571-98616080cd1e"
|
||||
"outputId": "6f499bed-11de-49c5-cb53-2068e5c31849"
|
||||
},
|
||||
"source": [
|
||||
"fig,axs=plt.subplots(ncols=3,nrows=1,figsize=(20,4))\n",
|
||||
@@ -574,24 +588,24 @@
|
||||
"axs[2].plot(mae_losses,label='MAE',color='blue')\n",
|
||||
"axs[2].set_title('Total Train Loss'); axs[2].legend()"
|
||||
],
|
||||
"execution_count": 9,
|
||||
"execution_count": 41,
|
||||
"outputs": [
|
||||
{
|
||||
"output_type": "execute_result",
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"<matplotlib.legend.Legend at 0x7f4716bd8610>"
|
||||
"<matplotlib.legend.Legend at 0x7efd05319e50>"
|
||||
]
|
||||
},
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"execution_count": 9
|
||||
"execution_count": 41
|
||||
},
|
||||
{
|
||||
"output_type": "display_data",
|
||||
"data": {
|
||||
"image/png": "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 truncated
|
||||
"image/png": "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 truncated
|
||||
"text/plain": [
|
||||
"<Figure size 1440x288 with 3 Axes>"
|
||||
]
|
||||
@@ -621,20 +635,20 @@
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/"
|
||||
},
|
||||
"outputId": "bf6689e1-42b0-45eb-80bc-8559fc75afda"
|
||||
"outputId": "dd208675-b851-43ca-ef4f-13f7abc8ffbe"
|
||||
},
|
||||
"source": [
|
||||
"# there should be 6 entries in model.losses since we have 6 blocks with flipout layers in our model\n",
|
||||
"print('There are {} entries in model.losses'.format(len(model.losses)))\n",
|
||||
"print(model.losses)"
|
||||
],
|
||||
"execution_count": 10,
|
||||
"execution_count": 42,
|
||||
"outputs": [
|
||||
{
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"There are 6 entries in model.losses\n",
|
||||
"[<tf.Tensor: shape=(), dtype=float32, numpy=0.014215787>, <tf.Tensor: shape=(), dtype=float32, numpy=0.02402923>, <tf.Tensor: shape=(), dtype=float32, numpy=0.045527037>, <tf.Tensor: shape=(), dtype=float32, numpy=0.02308532>, <tf.Tensor: shape=(), dtype=float32, numpy=0.018481597>, <tf.Tensor: shape=(), dtype=float32, numpy=0.013133749>]\n"
|
||||
"[<tf.Tensor: shape=(), dtype=float32, numpy=0.033721145>, <tf.Tensor: shape=(), dtype=float32, numpy=0.062639065>, <tf.Tensor: shape=(), dtype=float32, numpy=0.26068285>, <tf.Tensor: shape=(), dtype=float32, numpy=0.08385982>, <tf.Tensor: shape=(), dtype=float32, numpy=0.06156125>, <tf.Tensor: shape=(), dtype=float32, numpy=0.056031853>]\n"
|
||||
],
|
||||
"name": "stdout"
|
||||
}
|
||||
@@ -670,7 +684,7 @@
|
||||
"preds_mean=np.mean(preds,axis=0)\n",
|
||||
"preds_std=np.std(preds,axis=0)"
|
||||
],
|
||||
"execution_count": 11,
|
||||
"execution_count": 43,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
@@ -690,19 +704,19 @@
|
||||
"base_uri": "https://localhost:8080/",
|
||||
"height": 341
|
||||
},
|
||||
"outputId": "3b660d02-cb5e-4676-e9ac-962d8576aa64"
|
||||
"outputId": "a517ad8d-ac77-481b-f8c5-8e628143c5f8"
|
||||
},
|
||||
"source": [
|
||||
"NUM=16\n",
|
||||
"# show a single prediction\n",
|
||||
"showSbs(y_val[NUM],preds[0][NUM], top=\"Inputs\", bottom=\"Single forward pass\")\n"
|
||||
],
|
||||
"execution_count": 12,
|
||||
"execution_count": 44,
|
||||
"outputs": [
|
||||
{
|
||||
"output_type": "display_data",
|
||||
"data": {
|
||||
"image/png": "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 truncated
|
||||
"image/png": "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 truncated
|
||||
"text/plain": [
|
||||
"<Figure size 1152x360 with 2 Axes>"
|
||||
]
|
||||
@@ -731,9 +745,9 @@
|
||||
"id": "gAcKTBCGmohC",
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/",
|
||||
"height": 168
|
||||
"height": 157
|
||||
},
|
||||
"outputId": "c5a24006-87c1-4853-e507-44d2eea21a38"
|
||||
"outputId": "6f954e63-68fa-4c29-fefb-a14ec40c16ea"
|
||||
},
|
||||
"source": [
|
||||
"# plot repeated samples from posterior for some observations\n",
|
||||
@@ -759,12 +773,12 @@
|
||||
"OBS_IDX=5\n",
|
||||
"plot_BNN_predictions(y_val[OBS_IDX,...],preds[:,OBS_IDX,:,:,:],preds_mean[OBS_IDX,...],preds_std[OBS_IDX,...])"
|
||||
],
|
||||
"execution_count": 13,
|
||||
"execution_count": 45,
|
||||
"outputs": [
|
||||
{
|
||||
"output_type": "display_data",
|
||||
"data": {
|
||||
"image/png": "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 truncated
|
||||
"image/png": "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 truncated
|
||||
"text/plain": [
|
||||
"<Figure size 1440x288 with 8 Axes>"
|
||||
]
|
||||
@@ -796,7 +810,7 @@
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/"
|
||||
},
|
||||
"outputId": "37d11f59-ce5a-4c95-f60d-9dd0131aaf3b"
|
||||
"outputId": "71eaae33-e9a1-4f5a-bdfc-a6bdd8719fed"
|
||||
},
|
||||
"source": [
|
||||
"# Average Prediction with total uncertainty\n",
|
||||
@@ -804,16 +818,16 @@
|
||||
"preds_mean_global = np.mean(np.abs(preds),axis=(0,1,2,3))\n",
|
||||
"print(\"\\nAverage pixel prediction on validation set: \\n pressure: {} +- {}, \\n ux: {} +- {},\\n uy: {} +- {}\".format(np.round(preds_mean_global[0],3),np.round(uncertainty_total[0],3),np.round(preds_mean_global[1],3),np.round(uncertainty_total[1],3),np.round(preds_mean_global[2],3),np.round(uncertainty_total[2],3)))\n"
|
||||
],
|
||||
"execution_count": 14,
|
||||
"execution_count": 46,
|
||||
"outputs": [
|
||||
{
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"Average pixel prediction on validation set: \n",
|
||||
" pressure: 0.023 +- 0.007, \n",
|
||||
" ux: 0.468 +- 0.013,\n",
|
||||
" uy: 0.081 +- 0.013\n"
|
||||
" pressure: 0.025 +- 0.009, \n",
|
||||
" ux: 0.459 +- 0.02,\n",
|
||||
" uy: 0.079 +- 0.016\n"
|
||||
],
|
||||
"name": "stdout"
|
||||
}
|
||||
@@ -848,7 +862,7 @@
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/"
|
||||
},
|
||||
"outputId": "68c0a4ea-9bc0-4512-b087-37ec258ca27c"
|
||||
"outputId": "d0241d6b-c3b5-4fe7-80e4-c6314a028b4a"
|
||||
},
|
||||
"source": [
|
||||
"if not os.path.isfile('data-airfoils-test.npz'):\n",
|
||||
@@ -860,7 +874,7 @@
|
||||
"nptfile=np.load('data-airfoils-test.npz')\n",
|
||||
"print(\"Loaded {}/{} test samples\".format(len(nptfile[\"test_inputs\"]),len(nptfile[\"test_targets\"])))"
|
||||
],
|
||||
"execution_count": 15,
|
||||
"execution_count": 47,
|
||||
"outputs": [
|
||||
{
|
||||
"output_type": "stream",
|
||||
@@ -887,7 +901,7 @@
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/"
|
||||
},
|
||||
"outputId": "828733bc-d7ad-4f47-83d0-d437a70ca8d4"
|
||||
"outputId": "dd20559d-3980-444a-f79e-0dfb6af798fd"
|
||||
},
|
||||
"source": [
|
||||
"X_test = np.moveaxis(nptfile[\"test_inputs\"],1,-1)\n",
|
||||
@@ -903,13 +917,13 @@
|
||||
"\n",
|
||||
"print(\"\\nAverage test error: {}\".format(test_loss))\n"
|
||||
],
|
||||
"execution_count": 16,
|
||||
"execution_count": 48,
|
||||
"outputs": [
|
||||
{
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"Average test error: 0.029007223264529137\n"
|
||||
"Average test error: 0.02462211523168565\n"
|
||||
],
|
||||
"name": "stdout"
|
||||
}
|
||||
@@ -922,7 +936,7 @@
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/"
|
||||
},
|
||||
"outputId": "3de9b2fa-a039-4be3-c6ef-348569063272"
|
||||
"outputId": "b6a110a4-1e3e-4e26-859f-a1cd67398b48"
|
||||
},
|
||||
"source": [
|
||||
"# Average Prediction with total uncertainty\n",
|
||||
@@ -930,16 +944,16 @@
|
||||
"preds_test_mean_global = np.mean(np.abs(preds_test),axis=(0,1,2,3))\n",
|
||||
"print(\"\\nAverage pixel prediction on test set: \\n pressure: {} +- {}, \\n ux: {} +- {},\\n uy: {} +- {}\".format(np.round(preds_test_mean_global[0],3),np.round(uncertainty_test_total[0],3),np.round(preds_test_mean_global[1],3),np.round(uncertainty_test_total[1],3),np.round(preds_test_mean_global[2],3),np.round(uncertainty_test_total[2],3)))\n"
|
||||
],
|
||||
"execution_count": 17,
|
||||
"execution_count": 49,
|
||||
"outputs": [
|
||||
{
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"Average pixel prediction on test set: \n",
|
||||
" pressure: 0.025 +- 0.008, \n",
|
||||
" ux: 0.465 +- 0.015,\n",
|
||||
" uy: 0.085 +- 0.016\n"
|
||||
" pressure: 0.029 +- 0.01, \n",
|
||||
" ux: 0.452 +- 0.026,\n",
|
||||
" uy: 0.084 +- 0.02\n"
|
||||
],
|
||||
"name": "stdout"
|
||||
}
|
||||
@@ -951,9 +965,9 @@
|
||||
"id": "Sn8g_ACGsVgo",
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/",
|
||||
"height": 358
|
||||
"height": 361
|
||||
},
|
||||
"outputId": "0b86eaf0-3974-42d3-85fd-da250cffc5f1"
|
||||
"outputId": "fd7015b9-457d-4235-a326-26436474050f"
|
||||
},
|
||||
"source": [
|
||||
"# plot average pixel predictions with uncertainty\n",
|
||||
@@ -973,24 +987,24 @@
|
||||
" axs[channel].set_ylim(preds_mean_global[channel]-1.5*max_unc,preds_mean_global[channel]+1.5*max_unc)\n",
|
||||
"axs[2].legend(loc='center')"
|
||||
],
|
||||
"execution_count": 18,
|
||||
"execution_count": 50,
|
||||
"outputs": [
|
||||
{
|
||||
"output_type": "execute_result",
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"<matplotlib.legend.Legend at 0x7f4716b2bfd0>"
|
||||
"<matplotlib.legend.Legend at 0x7efcf8c54150>"
|
||||
]
|
||||
},
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"execution_count": 18
|
||||
"execution_count": 50
|
||||
},
|
||||
{
|
||||
"output_type": "display_data",
|
||||
"data": {
|
||||
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAiEAAAEwCAYAAABhdaEkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nO3df5TedX3n/eeL/ACRiJrEpZDEiSVsy68ijKh3pUo5aLBIuiss4I+N53g39d4bl+Wm1ODtjSy6XW17g/aU1nJWWIpW4KS15khc8FYsbquYgUJjYNEY0UwQCQEiiDEJvO8/rmviMM5MJpOZ+c5c1/Nxzhy/38/3872u93XO1/jy++udqkKSJGmqHdR0AZIkqTsZQiRJUiMMIZIkqRGGEEmS1AhDiCRJaoQhRJIkNcIQIkmSGmEImWGSPJzkZ0meSfLjJP89yWFN1yVJ0v4yhMxMb6uqw4CTgV7gQw3XI0nSfjOEzGBVtRX4EnB807VIUidJUkmOHrT+35N8dB/7fDvJ2watz0nyeJJXT2atM5khZAZLshh4K/DPTdciDTbOf8A/kOTuJLPb6/9Hko1JDpnseqUJ8tfAuwatvxX4UVX5b/QIDCEz098neQr4n8A/AH/UcD3SRPgT4OfAh5Iso3Vcv6uqdjZbljRmnwHemuQl7fV3Azc1WM+0N7vpAjQuv1tV/1/TRUgTqaqeT/LvgXuB84E/9v9BaiapqkeS/CPw9iSfB84CLm64rGnNMyGSpo2qehi4E+gBrm20GHW7Z4FDB60fMcb9bqR1SeY84Bvte/c0AkOIpMkwrn/Ak/wO8HrgK7Quz0hNuQ94R5JZSZYDbxzjfn9P68nFi2ndI6JRGEIkTYb9/gc8yQLgvwH/O7ASeFuSt05umdKILgbeBjwFvJNWuNinqvoZ8LfAUuDvJq26DpGqaroGSR0mSS+t09JLaP3jPRv4XlWN+E6bJH8HPFZV72uvnwV8GjihqrZPftXSxEhyBXBMVb1rn5O7nCFEkqQJkuTltF6b8O6quqvpeqY7L8dIkjRGST7Ybpsx9O9LSX4P2AJ8yQAyNp4JkTRlknwQ+OAwm75eVWdNdT2SmmUIkSRJjfByjCRJasS0e2PqggULqqenp+ky1CHuueeex6tq4VR/r8exJorHsDrBSMfxtAshPT099PX1NV2GOkSSHzTxvR7Hmigew+oEIx3HXo6RJEmNMIRIkqRGGEIkSVIjDCGSJKkRhhBJktQIQ4i6QpLlSR5KsinJ6lHmvT1JtRuwkWRukhuSbEhyf5I3TVnRktThpt0jutJESzILuBY4E+gH1idZW1UPDJk3j1b77rsHDf8eQFWdkOQVwJeSvKaqnp+a6iWpc3kmRN3gVGBTVW2uql3AzcCKYeZ9BPg4sHPQ2LHAVwGq6jHgKaB3csuVpO5gCFE3OIpWZ8sB/e2xvZKcDCyuqtuG7Hs/cE6S2UmWAqcAi4f7kiSrkvQl6du2bdvEVS9JHcrLMep6SQ4CrgbeM8zm64FfB/qAHwD/BDw33OdU1XXAdQC9vb12hpSkfTCEqBts5YVnLxa1xwbMA44HvpYE4AhgbZJzqqoPuGRgYpJ/Ar4z6RVLUhfwcoy6wXpgWZKlSeYCFwBrBzZW1Y6qWlBVPVXVA3wTOKeq+pIcmuTFAEnOBPYMvaFVkjQ+nglRx6uqPUkuAm4HZgHXV9XGJFcBfVW1dpTdXwHcnuR5WmdP3j35FUtSdzCEqCtU1Tpg3ZCxK0aY+6ZByw8D/3oya5OkbuXlGEmS1AhDiCRJaoQhRJIkNcIQIkmSGmEIkSRJjTCESNIMsK9O0El+K8m9SfYkOXfItpVJvtv+Wzl1VUuj8xFdSZrmxtgJ+oe0Wg/8wZB9Xw58mFbjxQLuae/75FTUri5x53/9xfLpl495N0OIJE1/eztBAyQZ6AS9N4S032lD+8V6g70F+HJVPdHe/mVgOfC5yS9bXeMfPvaL5f0IIV6OkaTpb5+doCdpX2lSGUIkSQAkWZWkL0nftm3bmi5HXcAQIknT3746QU/IvlV1XVX1VlXvwoULx1WotD8MIZI0/Y3aCXofbgfenORlSV4GvLk9JjXOECJJ01xV7QEGOkE/CNw60Ak6yTkASV6TpB84D/irJBvb+z4BfIRWkFkPXDVwk6rUNJ+OkaQZYF+doKtqPa1LLcPtez1w/aQWKI2DZ0IkSVIjDCGSJKkRhhBJktQIQ4gkSWqEIUSSJDXCECJJkhphCJEkSY0YUwhJsjzJQ0k2JVk9zPaDk9zS3n53kp4h25ckeSbJHwzdV5Ikdad9hpAks4BrgbOAY4ELkxw7ZNp7gSer6mjgGuDjQ7ZfDXzpwMuVJEmdYixnQk4FNlXV5qraBdwMrBgyZwVwY3t5DXBGkgAk+V3g+8DGiSlZkiR1grGEkKOALYPW+9tjw85p9zjYAcxPchjwAeA/j/YFto+WJKn7TPaNqVcC11TVM6NNsn20JEndZywN7LYCiwetL2qPDTenP8ls4HBgO/Ba4Nwkfwy8FHg+yc6q+vMDrlySJM1oYwkh64FlSZbSChsXAO8YMmctsBL4BnAu8NWqKuC0gQlJrgSeMYBIkiQYQwipqj1JLgJuB2YB11fVxiRXAX1VtRb4NHBTkk3AE7SCiiRJ0ojGciaEqloHrBsydsWg5Z3Aefv4jCvHUZ8kSepQvjFVkiQ1whAiSZIaYQiRJEmNMIRIkqRGGEIkSVIjDCGSJKkRhhBJktQIQ4gkSWqEIUSSJDXCECJJkhphCJEkSY0whEiSpEYYQiRJUiMMIZIkqRGzmy5AkjRzXPPl7+xdvuTMYxqsRJ3AECJJGrNPfuW7e5cNITpQXo6RJEmNMISoKyRZnuShJJuSrB5l3tuTVJLe9vqcJDcm2ZDkwSSXj7eGa778nb1/kiQvx6gLJJkFXAucCfQD65OsraoHhsybB1wM3D1o+Dzg4Ko6IcmhwANJPldVD+9vHZ7GlqQX8kyIusGpwKaq2lxVu4CbgRXDzPsI8HFg56CxAl6cZDbwImAX8JNJrleSuoIhRN3gKGDLoPX+9theSU4GFlfVbUP2XQP8FPgR8EPgT6vqiUmsVZK6hiFEXS/JQcDVwKXDbD4VeA44ElgKXJrkVSN8zqokfUn6tm3bNmn1SlKnMISoG2wFFg9aX9QeGzAPOB74WpKHgdcBa9s3p74D+B9VtbuqHgP+Eegd7kuq6rqq6q2q3oULF07Cz5CkzmIIUTdYDyxLsjTJXOACYO3AxqraUVULqqqnqnqAbwLnVFUfrUswvw2Q5MW0Asr/muofIEmdyKdj1PGqak+Si4DbgVnA9VW1MclVQF9VrR1l92uBG5JsBALcUFX/MvlVq6vc+V9/sXz6uJ8Cl2YcQ4i6QlWtA9YNGbtihLlvGrT8DK3HdKXJ8w8f+8WyIURdxMsxkiSpEYYQSZLUCEOIJElqhCFEkiQ1whAiSZIaYQiRJEmNMIRI0gyQZHmSh5JsSrJ6mO0HJ7mlvf3uJD3t8blJbkiyIcn9Sd40xaVLIzKESNI0l2QWrRfnnQUcC1yY5Ngh094LPFlVRwPX0OoIDfB7AFV1AnAm8P+2+yVJjfNAlKTp71RgU1VtrqpdwM3AiiFzVgA3tpfXAGckCa3Q8lWAdv+jpxih/5E01QwhkjT9HQVsGbTe3x4bdk5V7QF2APOB+4FzksxOshQ4hRc2dJQa42vbNbPZc0Pal+uBXwf6gB8A/wQ8N9zEJKuAVQBLliyZqvrUxQwhmtnsuaHusJUXnr1Y1B4bbk5/ktnA4cD2qirgkoFJSf4J+M5wX1JV1wHXAfT29taEVS+NwMsxkjT9rQeWJVmaZC5wATC0+/NaYGV7+Vzgq1VVSQ5N8mKAJGcCe6rqgakqXBqNZ0IkaZqrqj1JLgJuB2YB11fVxiRXAX1VtRb4NHBTkk3AE7SCCsArgNuTPE/rbMm7p/4XSMMzhEjSDFBV64B1Q8auGLS8EzhvmP0eBv71ZNcnjYeXYyRJUiMMIZIkqRGGEEmS1AhDiCRJaoQhRJIkNcIQIkmSGmEIkSRJjRhTCEmyPMlDSTYlWT3M9oOT3NLefneSnvb4qUnua//dn+TfTGz5kiRpptpnCEkyC7gWOItWS+gLkxw7ZNp7gSer6mjgGuDj7fFvA71VdRKwHPirdk8DSZLU5cZyJuRUYFNVba6qXcDNwIohc1YAN7aX1wBnJElVPdtuKQ1wCGBDJEmSBIztte1HAVsGrfcDrx1pTrvHwQ5gPvB4ktfSaiX9SuDdg0LJXmNpH33Nl3/R9PGSM48ZQ9mSJGk6m/RLI1V1N3Bckl8HbkzypXaPg8Fz9tk++pNf+e7eZUOIJEkz31gux2wFFg9aX9QeG3ZO+56Pw4HtgydU1YPAM8Dx4y1WkiR1jrGEkPXAsiRLk8yl1R567ZA5a4GV7eVzga9WVbX3mQ2Q5JXArwEPT0jlkiRpRtvn5Zj2PR4XAbcDs4Drq2pjkquAvqpaC3wauCnJJuAJWkEF4A3A6iS7geeB/1BVj0/GD5EkSTPLmO4Jqap1wLohY1cMWt4JnDfMfjcBNx1gjZIkqQP5xlRJktQIQ4gkSWqEIUSSJDXCECJJkhphCJEkSY0whEiSpPHpvwc+9YYXjn3qDa3xMTCESJKk/dd/D9x4Njy64YXjj25ojY8hiBhCJEnS/vvixbD72eG37X4Wvvif9vkRhhBJkrR/ntgMj3939DmPfwee+P6oUwwhkiRp/zz9KMyaO/qcWXNb80ZhCJEkSftn3hHw3K7R5zy3qzVvFIYQSZK0f17+KliwbPQ5C46Bly8ddYohRJIk7b+zPwlzDh1+25xD4exP7PMjDCGSJGn/LToFVn4RjjjxheNHnNgaX3TKPj/CECJJksZn0Snwvq+/cOx9Xx9TAAFDiCRJasjspguQJGmi7N69m/7+fnbu3Nl0KRPqkEMOYdGiRLine truncated
|
||||
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAioAAAEzCAYAAAAfASh9AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nO3dfZQU9Z3v8fdHHiQGghEwRIEMibi5PHgRZ9WcNYmGoOg1EFcJqMmSc9wl3r1mWdcY0XWN0SQbs7s+nBOzhrOSJZpEveRprpBVVyFxs0oYCAbRGBFJGHxgAEXRIA9+7x9VA03TM9NM13TX9Hxe58yh61e/6v7OOUXxobqqvooIzMzMzPLosFoXYGZmZtYeBxUzMzPLLQcVMzMzyy0HFTMzM8stBxUzMzPLLQcVMzMzyy0HFTMzM8stB5U6I2mDpD9K2iHpZUn/LmlgresyMzPrCgeV+vSJiBgITAIagWtrXI+ZmVmXOKjUsYjYBPwMGF/rWszM6o2kkHRcwfK/S/pKJ9s8KekTBcv9JG2RdGJ31tqTOajUMUkjgXOAX9e6FrNCXTzAXyVpuaS+6fL/lrRW0oDurtcsQ98FPl2wfA7wYkT4ON0OB5X69BNJrwL/Bfwc+FqN6zHLwj8BbwHXShpDsl9/OiJ21rYss0NyN3COpHely58B7qphPbnXt9YFWLf4ZET8Z62LMMtSRLwt6S+AVcBM4Bv+X6j1NBHxgqRfAudL+jFwNjC3xmXlms+omFmPEREbgKVAA3B7TYsxgzeBIwqWh5e53UKSr39mAI+l1xNaOxxUzKwWunSAl/S/gA8BD5N8FWRWS6uBiyT1kTQV+GiZ2/2E5K7MuSTXrFgHHFTMrBYO+QAvaSjwb8BfArOBT0g6p3vLNOvQXOATwKvAxSQBpFMR8Ufgh8Bo4EfdVl2dUETUugYz62UkNZKc/h5FcnDvCzwXEe0+80fSj4DNEXFpunw2cCcwISK2dn/VZtmRdB1wfER8utPJvZyDipmZWRVJOorksRGfiYhf1LqevPNXP2ZmZhmSdE3axqT452eS/grYCPzMIaU8PqNiZrkh6RrgmhKrHo2Is6tdj5nVnoOKmZmZ5VaPfODb0KFDo6GhodZlWB1YuXLllogYVu3P9T5sWarFfux92LLU0T7cI4NKQ0MDzc3NtS7D6oCk39fic70PW5ZqsR97H7YsdbQP+2JaMzMzyy0HFTMzM8stBxUzMzPLLQcVMzMzyy0HFTMzM8stBxUzMzPLLQcVMzMzyy0HFTMzM8stBxUzMzPLLQcVMzMzyy0HFTMzM8utTIKKpKmSnpG0TtK8EusPl3Rvun65pIaCdSdIekzSWklrJA3IoiYzMzPr+SoOKpL6ALcDZwNjgQsljS2adgnwSkQcB9wC3JRu2xe4G7g0IsYBpwO7K63JzMzM6kMWZ1ROBtZFxPqI2AXcA0wvmjMdWJi+XgRMliTgTOA3EfEEQERsjYi9GdRkZmZmdSCLoHIssLFguSUdKzknIvYA24EhwPFASHpA0ipJX2zvQyTNkdQsqbm1tTWDss3MzCzvan0xbV/gNODi9M/zJE0uNTEi5kdEY0Q0Dhs2rJo1mpmZWY1kEVQ2ASMLlkekYyXnpNelDAa2kpx9+UVEbImIN4ElwKQMajIzM7M6kEVQWQGMkTRaUn9gFtBUNKcJmJ2+vgB4JCICeACYIOmINMB8FHgqg5rMzMysDvSt9A0iYo+ky0hCRx9gQUSslXQD0BwRTcCdwF2S1gHbSMIMEfGKpJtJwk4ASyJicaU1mZmZWX2oOKgARMQSkq9tCseuK3i9E5jRzrZ3k9yibGZmZnaAWl9Ma2ZmZtYuBxUzMzPLLQcVMzMzyy0HFTM671dVMO98SSGpMV3uL+k7aZ+qJySdXrWizYqU0XftI+nDNfdIuqBo3X9IelXS/dWr2KxzDirW65XZrwpJg4C5wPKC4b8CiIgJwBTgXyT575VVXZn78R+AzwLfL/EW/wR8pjtrNOsKH1DNyutXBXAjSUPNnQVjY4FHACJiM/Aq0Ni95ZqV1Ol+HBEbIuI3wNvFG0fEw8DrVanU7BA4qJiV0a9K0iRgZInn/DwBTJPUV9Jo4CQOfFKzWbWU03etIu65ZrXgoGLWifSrnJuBK0qsXkDyD0IzcCvw30DJDuA+yFtP555rVgsOKmad96saBIwHlknaAJwKNElqjIg9EXF5REyMiOnAkcDvSn2ID/LWzcrpu2bW4ziomHXSryoitkfE0IhoiIgG4HFgWkQ0p32q3gkgaQqwJyLcr8pqoZy+a2Y9joOK9XoRsQdo61f1NHBfW78qSdM62fxoYJWkp4Gr8F0TViPl7MeS/lRSC0lLk29LWtu2vaRHgf8LTJbUIums6v8WZgfLpNePWU/XWb+qovHTC15vAP6kO2szK1cZfddWkHwlVGrbD3dvdWZd4zMqZmZmllsOKmZmZpZbDipmZmaWWw4qZmZmllsOKmZmZpZbDipmZmaWWw4qZmZmllsOKmZmZpZbDipmZmaWWw4qZmZmllsOKmZmZpZbDipmZmaWWw4qZmZmlluZBBVJUyU9I2mdpHkl1h8u6d50/XJJDel4g6Q/Slqd/tyRRT1mZmZWH/pW+gaS+gC3A1OAFmCFpKaIeKpg2iXAKxFxnKRZwE3AzHTdcxExsdI6zMzMrP5kcUblZGBdRKyPiF3APcD0ojnTgYXp60XAZEnK4LPNzMysjlV8RgU4FthYsNwCnNLenIjYI2k7MCRdN1rSr4HXgGsj4tEMajIzM7O8WPqP+1+fcfUhbZpFUKnEi8CoiNgq6STgJ5LGRcRrxRMlzQHmAIwaNarKZZqZmVmX/fzr+18fYlDJ4qufTcDIguUR6VjJOZL6AoOBrRHxVkRsBYiIlcBzwPGlPiQi5kdEY0Q0Dhs2LIOyzczMLO+yCCorgDGSRkvqD8wCmormNAGz09cXAI9EREgall6Mi6T3A2OA9RnUZGZmZnWg4q9+0mtOLgMeAPoACyJiraQbgOaIaALuBO6StA7YRhJmAD4C3CBpN/A2cGlEbKu0JjMzM6sPmVyjEhFLgCVFY9cVvN4JzCix3Q+BH2ZRg5mZmdUfP5nWzMzMcstBxczMzHLLQcXMzMxyy0HFzKxOlNF37SOSVknaI+mConWzJT2b/swu3tasVhxUzFKdHeQL5p0vKSQ1psv9JC2UtEbS05IO7WlGZhko6Lt2NjAWuFDS2KJpfwA+C3y/aNujgC+RPFX8ZOBLkt7d3TWblcNBxYyyD/JIGgTMBZYXDM8ADo+ICcBJwOfaOoSbVVGnfdciYkNE/IbkcRCFzgIeiohtEfEK8BAwtRpFm3XGQcUsUU5zTYAbSbp/7ywYC+Cd6VOX3wHsIuldZVZNpfquHVuFbc26lYOKWaLTA7WkScDIiFhctO0i4A2S3lV/AP651IMLJc2R1CypubW1NdPizarB+7DVgoOKWRkkHQbcDFxRYvXJwF7gGGA0cEXaEuIA7ldl3aycvmsVbet92Gqh1t2TzfKiswP1IGA8sEwSwHCgSdI04CLgPyJiN7BZ0i+BRrrQt+qWh3637/XlU0r25zRrz76+ayT77iySfbMcDwBfK7iA9kzAF4VbLviMilmiw+aaEbE9IoZGRENENACPA9Miopnk656PAUh6J3Aq8NuuFHHbw8/u+zE7FBGxB2jru/Y0cF9b37U0UCPpTyW1kFwA/m1Ja9Ntt5Fcf7Ui/bnBfdcsL3xGxYyym2u253bgO+lBX8B30jsrzKqqjL5rK0jOFpbadgGwoFsLNOsCBxWzVGcH+aLx0wte76BE000zM6ucv/oxMzOz3HJQMTMzs9zyVz9mZnm39B/3vz7DN+NY7+KgYmaWdz//+v7XDirWy/irHzMzM8stBxUzMzPLLQcVMzMzyy0HFTMzM8stBxUzMzPLLQcVMzMzyy0HFTMzM8stBxUzMzPLLQcVMzMzy61MgoqkqZKekbRO0rwS6w+XdG+6frmkhqL1oyTtkPSFLOoxM7PauOWh3+37MctCxY/Ql9QHuB2YArQAKyQ1RcRTBdMuAV6JiOMkzQJuAmYWrL8Z+FmltZiZWW3d9vCz+15fPuX4GlZi9SKLMyonA+siYn1E7ALuAaYXzZkOLExfLwImSxKApE8CzwNrM6jFzMzM6kgWQeVYYGPBcks6VnJOROwBtgNDJA0ErgK+3NmHSJojqVlSc2trawZlm5mZWd7V+mLa64FbImJHZxMjYn5ENEZE47Bhw7q/MjMzM6u5iq9RATYBIwuWR6Rjpea0SOoLDAa2AqcAF0j6BnAk8LaknRHxzQzqMjMzsx4ui6CyAhgjaTRJIJkFXFQ0pwmYDTwGXAA8EhEBfLhtgqTrgR0OKWZmZtam4qASEXskXQY8APQBFkTEWkk3AM0R0QTcCdwlaR2wjSTMmFXH0n/c//qMq2tXh5mZHbIszqgQEUuAJUVj1xW83gnM6OQ9rs+iFrOD/Pzr+187qJiZ9Si1vpjWzMzMrF0OKmZmZpZbDipmZmaWWw4qZmZ1oqt91yT1l/QdSWskPSHp9CqXbtYuBxUzOj/AF8w7X1JIakyXL5a0uuDnbUkTq1e5WaKg79rZwFjgQklji6bt67sG3ELSdw3grwAiYgJJ37Z/keR/HywXvCNar1fmAR5Jg4C5wPK2sYj4XkRMjIiJwGeA5yNidXUqNztAJX3XxgKPAETEZuBVoLEqVZt1wkHFrLwDPMCNJP8D3dnO+1yYbmtWC13uuwY8AUyT1Dd9eOdJHPjEccA916w2HFTMyjjAS5oEjIyIxR28z0zgB+2t9EHecmwByX7fDNwK/Dewt3iSe65ZLTiomHUi/a7+ZuCKDuacArwZEU+2N8cHeetmh9J3jcK+axGxJyIuT7/GnE7Se+13VajZrFMOKmadH+AHAeOBZZI2AKcCTW0X1KZm0cHZFLMq2Nd3TLine truncated
|
||||
"text/plain": [
|
||||
"<Figure size 648x360 with 3 Axes>"
|
||||
]
|
||||
@@ -1008,7 +1022,7 @@
|
||||
"id": "icgfvAIqoMpE"
|
||||
},
|
||||
"source": [
|
||||
"This is reassuring: The uncertainties on the OOD test set with new shapes are higher than on the validation set. The mean error is also larger for most cases.\n",
|
||||
"This is reassuring: The uncertainties on the OOD test set with new shapes are at least slightly higher than on the validation set. The mean error is also larger for most cases.\n",
|
||||
"In general it is hard to obtain a calibrated uncertainty estimate, but since we are dealing with a fairly simple problem here, it seems that the BNN is able to estimate it reasonably well."
|
||||
]
|
||||
},
|
||||
@@ -1018,20 +1032,20 @@
|
||||
"id": "oP1HOciVjh-o",
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/",
|
||||
"height": 168
|
||||
"height": 157
|
||||
},
|
||||
"outputId": "9cac6c60-96c5-496b-fc4c-0f9cb1ca476e"
|
||||
"outputId": "f3486c62-7641-47c5-d95f-575d53329607"
|
||||
},
|
||||
"source": [
|
||||
"OBS_IDX=5\n",
|
||||
"plot_BNN_predictions(y_test[OBS_IDX,...],preds_test[:,OBS_IDX,:,:,:],preds_test_mean[OBS_IDX,...],preds_test_std[OBS_IDX,...])"
|
||||
],
|
||||
"execution_count": 19,
|
||||
"execution_count": 51,
|
||||
"outputs": [
|
||||
{
|
||||
"output_type": "display_data",
|
||||
"data": {
|
||||
"image/png": "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 truncated
|
||||
"image/png": "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 truncated
|
||||
"text/plain": [
|
||||
"<Figure size 1440x288 with 8 Axes>"
|
||||
]
|
||||
@@ -1060,7 +1074,7 @@
|
||||
"base_uri": "https://localhost:8080/",
|
||||
"height": 590
|
||||
},
|
||||
"outputId": "97cd26a5-7030-4e40-968b-123839ca1edd"
|
||||
"outputId": "a54e614a-a338-4075-be5e-d86bbf2f020e"
|
||||
},
|
||||
"source": [
|
||||
"IDXS = [1,3,8]\n",
|
||||
@@ -1074,7 +1088,7 @@
|
||||
"axs[0][1].set_title('Avg Pred')\n",
|
||||
"axs[0][2].set_title('Std. Dev')\n"
|
||||
],
|
||||
"execution_count": 20,
|
||||
"execution_count": 52,
|
||||
"outputs": [
|
||||
{
|
||||
"output_type": "execute_result",
|
||||
@@ -1086,12 +1100,12 @@
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"execution_count": 20
|
||||
"execution_count": 52
|
||||
},
|
||||
{
|
||||
"output_type": "display_data",
|
||||
"data": {
|
||||
"image/png": "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 truncated
|
||||
"image/png": "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 truncated
|
||||
"text/plain": [
|
||||
"<Figure size 648x648 with 9 Axes>"
|
||||
]
|
||||
@@ -1138,4 +1152,4 @@
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
@@ -95,25 +95,26 @@
|
||||
"print(\"Torch version {}\".format(torch.__version__))\n",
|
||||
"\n",
|
||||
"# get training data\n",
|
||||
"dir = \"./\"\n",
|
||||
"if True:\n",
|
||||
" # download\n",
|
||||
" if not os.path.isfile('data-airfoils.npz'):\n",
|
||||
" import urllib.request\n",
|
||||
" url=\"https://ge.in.tum.de/download/2019-deepFlowPred/data.npz\"\n",
|
||||
" import requests\n",
|
||||
" print(\"Downloading training data (300MB), this can take a few minutes the first time...\")\n",
|
||||
" urllib.request.urlretrieve(url, 'data-airfoils.npz')\n",
|
||||
" npfile=np.load('data-airfoils.npz')\n",
|
||||
"\n",
|
||||
"else:\n",
|
||||
" with open(\"data-airfoils.npz\", 'wb') as datafile:\n",
|
||||
" resp = requests.get('https://dataserv.ub.tum.de/s/m1615239/download?path=%2F&files=dfp-data-400.npz', verify=False)\n",
|
||||
" datafile.write(resp.content)\n",
|
||||
"else: \n",
|
||||
" # alternative: load from google drive (upload there beforehand):\n",
|
||||
" from google.colab import drive\n",
|
||||
" drive.mount('/content/gdrive')\n",
|
||||
" npfile=np.load('gdrive/My Drive/data-airfoils.npz')\n",
|
||||
"\n",
|
||||
" dir = \"./gdrive/My Drive/\"\n",
|
||||
"\n",
|
||||
"npfile=np.load(dir+'data-airfoils.npz')\n",
|
||||
" \n",
|
||||
"print(\"Loaded data, {} training, {} validation samples\".format(len(npfile[\"inputs\"]),len(npfile[\"vinputs\"])))\n",
|
||||
"\n",
|
||||
"print(\"Size of the inputs array: \"+format(npfile[\"inputs\"].shape))\n"
|
||||
"print(\"Size of the inputs array: \"+format(npfile[\"inputs\"].shape))"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
||||
Reference in new issue
Block a user