Fix dependencies and kernel crash in captumyt.py (#2408)

* Update captum dependencies (matplotlib and flask-compress)
* Use resnet18 due to RAM limitation
Google Colab crashes due to insufficient RAM (more than 12 GB is required) if resnet101 or resnet50 are used. Thus, resnet18 is used instead (approximately 6 GB is used).

beginner_source/introyt/captumyt.py

@@ -98,21 +98,24 @@
 Before you get started, you need to have a Python environment with:
 
 -  Python version 3.6 or higher
--  For the Captum Insights example, Flask 1.1 or higher
+-  For the Captum Insights example, Flask 1.1 or higher and Flask-Compress
+   (the latest version is recommended)
 -  PyTorch version 1.2 or higher (the latest version is recommended)
 -  TorchVision version 0.6 or higher (the latest version is recommended)
 -  Captum (the latest version is recommended)
+-  Matplotlib version 3.3.4, since Captum currently uses a Matplotlib
+   function whose arguments have been renamed in later versions
 
 To install Captum in an Anaconda or pip virtual environment, use the
 appropriate command for your environment below:
 
 With ``conda``::
 
-    conda install pytorch torchvision captum -c pytorch
+    conda install pytorch torchvision captum flask-compress matplotlib=3.3.4 -c pytorch
 
 With ``pip``::
 
-    pip install torch torchvision captum
+    pip install torch torchvision captum matplotlib==3.3.4 Flask-Compress
 
 Restart this notebook in the environment you set up, and you’re ready to
 go!
@@ -155,7 +158,7 @@
 # now.
 # 
 
-model = models.resnet101(weights='IMAGENET1K_V1')
+model = models.resnet18(weights='IMAGENET1K_V1')
 model = model.eval()