Tree with Lichen

Tree with Lichen

SONY ILCE-7C 20mm f22.0 1/30s ISO250

A tree with lichen at Echo Summit on Highway 50 in the Sierra Nevada mountains.

Add your comment...

Related Posts

(Recent Photos)

(Published to the Fediverse as: Tree with Lichen #photo #trees Photo of a lichen covered tree at Echo Summit on Highway 50 in the Sierra Nevada Mountains, California. )

Surf Scooter

Surf Scooter

SONY DSC-RX10M4 220mm f4.0 1/1,000s ISO100

I think a Surf Scooter, surfing a wave just off Fort Funston in San Francisco.

Add your comment...

Related Posts

(Recent Photos)

(Published to the Fediverse as: Surf Scooter #photo #fortfunston #sanfrancisco Photo of a Surf Scooter riding the crest of a wave off Fort Funston beach in San Francisco. )

Reviews for April 2023

By Robert Ellison. Updated on Sunday, April 30, 2023.

Spoilers!

Movies

The Thing

I caught the 2011 prequel on Netflix which I completely missed when it came out. The setup was pretty great and then it all got fairly boring once the killing started. As a prequel it's set in the 80's and it's really hard to tell that this is true. There are no cell phones, but then you probably don't have any signal in Antarctica. The vehicles are old, but how often does a Norwegian research station swap out its snow-cats anyway? And everyone is wearing what you'd probably always wear to such a cold destination. It was pretty average horror and I wish I hadn't bothered.

Music

Raw Raw

Nice new K.Flay track.

Podcasts

A Very British Cult

Review:Podcasts:A Very British Cult

A Very British Cult investigates a life coaching outfit called Lighthouse which seems to be very very expensive and for some reason brings some sort of cheap UK Scientology to mind.

Any Questions

Review:Podcasts:Any Questions

Every so often I'll review a podcast that is a regular listen rather than a series. It feels odd to call Any Questions a podcast as I grew up with it on the radio, but that's what it is to me now.

Any Questions is a long-running comedy panel show in the mold of Just a Minute. Politicians have one minute to talk about a subject without answering the question. As with many BBC panel shows there are many long running gags and in-jokes, like asking for more houses (just not in the community where the program is being hosted this week!), or any question involving HS2.

I went to see it live once but didn't get my question picked. There is a companion program called Any Answers which is less comedy and more care-in-the-community for people who decide to phone in.

I'm Not a Monster Series 2

Review:Podcasts: I'm Not a Monster Series 2

Series 2 of I'm Not a Monster is The Shamima Begum Story. Begum was stripped of British citizenship after joining IS in Syria as a teenager. The Home Office believes that she is a terrorist and others that she is a victim of child trafficking. Regardless of the truth this didn't turn out well for her and it's hard not to feel some sympathy.

TV

Euphoria Seasons 1 and 2

Euphoria season 1 answers the question: what if Bret Easton Ellis had written Beverly Hills 90210? It's unflinching and hard to watch, a crazy mix of every horrible story about what the teens are up to these days. It makes me want to move my kids to Norway and home school, although I can't due to Brexit. Season 2 answers the question: what if Bret Easton Ellis quit and they had to go with a committee instead. It's initially gratuitous and then gradually becomes boring and self referential. I don't think I'm up for Season 3.

I downloaded this to watch on a flight and all things considered it's probably good that it didn't work. But HBO, really. I've been paying you for years and using the same phone and account for years and the second you don't like the look of my IP address you bail on me? For travel only Netflix really gets this right and works pretty consistently. Every other streaming provider seems to fail horribly at the slightest sign of travel.

(All images included with ITHCWY reviews are the property of their respective owners and are used to illustrate reviews only.)

Add your comment...

Related Posts

(All Reviews)

Links for April 2023

By Robert Ellison. Updated on Thursday, April 27, 2023.

Bangalore and Back, a Time Lapse

Bangalore and Back, a Time Lapse

The latest installment in my series of Bangalore time lapses. This one is about the interminable journey and all of the airports.

Add your comment...

Related Posts

(More Timelapses)

(Published to the Fediverse as: Bangalore and Back, a Time Lapse #timelapse #video #bangalore #india Time lapse video showing a trip to Bangalore, India and back. That's a lot of 747s and airports. )

Reviews for March 2023

Spoilers!

Movies

Noise

This was a random preflight download for me from Netflix. It's about a Belgian influencer who loses his mind after the arrival of a child (and the soundtrack nearly made me lose my own mind - the baby screams for most of the film and is only interrupted by things like eating soft fruit loudly). It was OK.

TV

Mythic Quest Season 3

Review:TV:Mythic Quest Season 3

It's not quite as good as the first couple of seasons but still worth watching. I think this time around moving Ian and Poppy into their own studio was a mistake, but not as big as consummating the unconsumatable.

Poker Face Season 1

This is mostly talked about as a Colombo remake but I think Natasha Lyonne is channelling the Hoff because this really reminds me more of Knight Rider. Stranger comes to town, gets people out of jam, leaves. It's more about that vibe than the solving of any particular muder. Loved it.

The Last of Us Season 1

Review:TV:The Last of Us Season 1

Having just complained bitterly about Dark Summer skipping the apocalypse foreplay I was happy to see The Last of Us revel in it. This is what a high concept zombie show looks like. I'm sorry, it's fungus rather than zombies of course. I never played the game it's based on but it seems like zombies? They bite you and you get infected. As bored as I am with zombies this was really good.

(All images included with ITHCWY reviews are the property of their respective owners and are used to illustrate reviews only.)

Add your comment...

Related Posts

(All Reviews)

Vernal (Spring) Equinox 2023

Vernal (Spring) Equinox 2023

Spring for the Northern Hemisphere, and Autumn south of the Equator, starts right now - 21:25 UTC on March 20, 2023. The image above shows the exact moment of the equinox in Catfood Earth.

Add your comment...

Related Posts

(All Code Posts)

(Published to the Fediverse as: Vernal (Spring) Equinox 2023 #code #earth #equinox #spring #autumn #vernal Catfood Earth render of the exact moment of the Spring Equinox for 2023 (21:25 UTC on March 20, 2023). )

More Colors

For a long time this blog has been black with some splashes of International Orange. The favorite icon and logo was some weird grid of dots (and yes, I give Google crap for Material Design). Now that Google has brought icons to the desktop search results as well as mobile I wanted a rounder favicon. Their direction is round icons all the way, and my weird dots don't look great in this format.

The new logo and favorite icon is a dynamic pie chart. This updates daily (the favorite icon will lag a bit due to caching) and shows the category distribution of posts over the last two years. The logo text is just a random permutation of the category colors. This is stupidly precise and geeky and also a lot more cheerful. I may add a few more splashes over time.

I started with some online tool for the palette and used International Orange as a starting point and its color wheel complement to pin the other end of the range. This looks terrible. I then had a long conversation with ChatGPT 4 and told it what I liked and didn't like about each palette it came up with. I was pretty high maintenance but the AI was patient and I'm pretty happy with the color scheme we ended up with.

ITHCWY Logo

Add your comment...

Related Posts

(All Etc Posts)

(Published to the Fediverse as: More Colors #etc #ithcwy ITHCWY has a new 8 color palette, logo and favorite icon generated via a conversation with ChatGPT. )

Predicting when fog will flow through the Golden Gate using ML.NET

Predicting when fog will flow through the Golden Gate using ML.NET

I'd like to make a time lapse of the moment when fog enters the Golden Gate and flows under the Golden Gate Bridge. It's surprisingly hard to know when conditions will be just right though. Often the weather is pleasant at my house while the fog is sneaking through and there is very little chance of me checking a webcam or satellite image. I decided to fix this about a year ago and started collecting data. The best bet seemed to be GOES-West CONUS - Band 2 which is a high resolution daylight satellite image that shows clouds and fog. I put together a Google Apps Script project to save an hourly snapshot and left if running. Here's a video of the data so far, zoomed in for a HD aspect ratio and scaled up a bit:

It's pretty obvious to me when conditions are just right. Could an ML model learn that this was about to happen from an image that was three hours older?

The first step was dividing thousands of images into two classes - frames where the fog would be perfect in three hours and frames where this was not going to happen. I built a little WPF tool to label the data (I don't use this often these days and every time I do I marvel at how the Image control has defaults that won't show the image FFS). This had the potential to be tedious so I built in some heuristics to flag likely candidates and then knocked out the false positives. Because the satellite images include clouds there is often white in the Golden Gate that is cloud cover rather than fog. At the end of the process I had two subfolders full of images to work with.

My goal this weekend was to get something working, and then refine every few months as I get more data. Right now I have 18 images that are in the Fog class and 7,539 that are NoFog. I also wanted this running on my blog, which is .NET 4.8 and will stay that way until I get a couple of weeks of forced bed rest. ML.NET says that it's based on .NET Standard and so should run anywhere.

Having local automl is very cool once you get it working. For large datasets this might not be a great option, but not having to wrangle with the cloud was also very appealing for this project.

Getting GPU training configured involved many gigabytes of installs. Get the latest Visual Studio 2022. Get the latest ML.NET model builder. Sign up for an NVIDIA developer account and install terrifyingly old and specific versions of CUDA and cuDNN. This last part was the worst because the CUDA installer wanted to downgrade my graphics driver, warned directly that this would cause problems and then claimed that it couldn't find a supported version of Visual Studio. I nervously unchecked everything that was already installed, and so far model builder has run fine and I don't seem to have caused any driver problems.

For image classification settings you can choose micro-accuracy (the default), macro-accuracy, logarithmic loss, or logarithmic loss reduction. Micro-accuracy is based on the contribution of all classes and unsurprisingly it's useless in this case as just predicting 'no' works very well overall. Maco-accuracy is the average of the accuracy of each class and this produced reasonable results for me. Possibly too good, I probably have some overfitting and will spend some time on that soon.

After training the model builder has an evaluate tab which is pretty worthless, at least for this model/case. You can spot check the prediction for specific images, and then there is one overall number for the performance of the model. I'm used to looking at precision and recall and it looks like I'll have to spend some time building separate tooling to do this. Hopefully this will improve in future versions.

At this point I have a .NET 6 console application that can make plausible looking predictions. Overall I'm very impressed with how easy it was to get this far.

Integrating with my blog though was very sad. After a lot of NuGet'ing and Googling I came to realize that ML.NET will not play nice with .NET 4.8, at least for image classification. Having dared to anger the NuGet gods I did a git reset --hard and called out to a new .NET 6 process to handle the classification. For my application I'm only running the prediction once per hour so I'm not bothered by performance. That .NET Standard claim proved to be unhelpful and I could have used just about anything.

The model is now running hourly. I have put up a dedicated page, Golden Gate Fog Prediction, with the latest forecast and plan to improve this over time. If this would be a useful tool for you please leave a comment below (right now it emails me when there is a positive prediction, it could potentially email a list of people).

Updated 2023-03-12 23:24:

After building some tooling to quantify this first model I have some hard metrics to add. Precision is 23%. This means there is a high rate of false positives. Recall is 78%. This means that when there really is fog the model does a pretty good job of predicting it. Overall the f1 score is 35% which is not great. In practice the model doesn't miss the condition I'm trying to detect often but it will send you out only to be disappointed most of the time. I'm not that surprised given how few positive cases I had to work with so far. My next steps are collecting more training data and looking more carefully at the labeling process to make sure I'm not missing some reasonable positive cases.

Add your comment...

Related Posts

(All Code Posts)

(Published to the Fediverse as: Predicting when fog will flow through the Golden Gate using ML.NET #code #video #ml #fog Using Microsoft's AutoML in ML.NET to build an image classifier that predicts fog flowing under the Golden Gate Bridge. )

Links for March 2023