diff --git a/02_Noise2Void/exercise.ipynb b/02_Noise2Void/exercise.ipynb
index 990a397..6a92097 100644
--- a/02_Noise2Void/exercise.ipynb
+++ b/02_Noise2Void/exercise.ipynb
@@ -231,7 +231,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "
Checkpoint 1: What is N2V really doing?
\n",
+ "
Checkpoint 1: N2V masking
\n",
""
]
},
@@ -389,16 +389,6 @@
"careamist = CAREamist(source=training_config)"
]
},
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "%load_ext tensorboard\n",
- "%tensorboard --logdir logs/lightning_logs"
- ]
- },
{
"attachments": {},
"cell_type": "markdown",
diff --git a/03_COSDD/exercise.ipynb b/03_COSDD/exercise.ipynb
index b8ef461..b781074 100644
--- a/03_COSDD/exercise.ipynb
+++ b/03_COSDD/exercise.ipynb
@@ -340,7 +340,7 @@
"source": [
"
\n",
"\n",
- "COSDD is a Variational Autoencoder~\\cite{chenvariational} (solid arrows) trained to model the distribution of noisy images $\\mathbf{x}$. \n",
+ "COSDD is a Variational Autoencoder (solid arrows) trained to model the distribution of noisy images $\\mathbf{x}$. \n",
"The autoregressive (AR) decoder models the noise component of the images, while the latent variable models only the clean signal component $\\mathbf{s}$.\n",
"In a second step (dashed arrows), the \\emph{signal decoder} is trained to map latent variables into image space, producing an estimate of the signal underlying $\\mathbf{x}$.\n",
"{\\bf b):}\n",
@@ -603,7 +603,7 @@
"outputs": [],
"source": [
"lowsnr_path = \"./../data/mito-confocal-lowsnr.tif\"\n",
- "n_test_images = 10\n",
+ "n_test_images = 5\n",
"# load the data\n",
"test_set = tifffile.imread(lowsnr_path)\n",
"test_set = test_set[:n_test_images, np.newaxis]\n",
diff --git a/04_DenoiSplit/exercise.ipynb b/04_DenoiSplit/exercise.ipynb
index 16ec2ae..85eaeda 100644
--- a/04_DenoiSplit/exercise.ipynb
+++ b/04_DenoiSplit/exercise.ipynb
@@ -796,7 +796,7 @@
},
{
"cell_type": "markdown",
- "id": "4d103864",
+ "id": "fc2ed8e0",
"metadata": {},
"source": [
"
End of the exercise
\n",