Daniel Bourke comments

Results 107 comments of


                                            Daniel Bourke

Clean/remove duplicate images with `fastdup`

Next will be to turn the notebook version of this into a script

Start breaking down `class_names` into more easily understandable foods

Label style: `[HIGHER_FOOD_NAME]_[SPECIFIC_TYPE]` For example: * "Red onion" -> `onion_red` * "Banana bread" -> `bread_banana` * "Brown potato" -> `potato_brown` * "Green apple" -> `apple_green` I could also have a...

Malicious content

Yo @ShivanS93 thank you for all the great suggestions, I’ll be working on all of these in the next stream/coding session.

Go through `all_images` on Google Storage and resize them to take up less space

Doesn't look like I need to do this... Experiments show that it doesn't change much. **Without resizing:** ```python Min load time: 6.175041198730469e-05 Max load time: 0.0051898956298828125 Mean load time: 7.927996739415816e-05...

Here is the ultimate test

Hahahah! The ultimate test and it's both: food & not food! That might break the model.

Here is the ultimate test

Well... looks like it's "food". Just cleaned up a bunch of code/trying to make it reproducible. The new model is trained on about ~40k images of food + ~25k images...

Clarification for discussion of shared memory in `torch.from_numpy(ndarray)` and `torch.Tensor.numpy()`

> Just found the corrections page for the video here where this point has already been acknowledged: #98 > > But leaving this open for now as the book description...

Omg!

Feel free! I'm gonna update this over the next few weeks/months with resources I find :) Happy to add those from the community too

`coremltools` docs - Xcode Model Preview Type for Object Detection?

Thank you! @Y-T-G

problems with setting up dataloader

Hey @lazyman001 , Where are you getting this issue? What's the code you're trying to run? Have you tried putting all your code into a `main()` function? And then calling...