I’ve made a Notebook to classify Alien vs. Predator images using Google Colab, more info here:
Yes that’s right. Let me know if you see anything you think could be improved.
The link is missing the “s” at the end of http. Should be:
!curl https://course-v3.fast.ai/setup/colab | bash
Made a PR to fix the issue https://github.com/fastai/course-v3/pull/56
Done!
1 Like
as asked in the opening markdown cell it asks to create a duplicate by clicking on a tick in a box.
there is no box to click
i tried saving the notebook to my drive but the cell
" Image.open(‘images/notebook_tutorial/cat_example.jpg’) " is showing an error as there is no images directory in my drive.
what is the solution? do i have to compulsarily create an images folder in my drive or download it locally or is there another solution ?
The widge from fastai does not work well.
you have to upload it with colab and copy the path to see where the image is.
For example, you can see the copy path word selection in below, and the image location is at /content/11111.jpg: I was using the fastbook lesson5 notebook
So you’re saying ill have to upload the images folder to my drive too ?
You can also upload it to your google drive or just upload it to the colab. See the bottom upload and mount drive in above? You should try it on your own.
I’m unsure if this is a colab issue or a lesson question, I’m basically running through lesson 1 on colab and the learn.lr_find portion seems to work up to around 66% on the progress bar but then displays the LR_find complete output while leaving the progress bar stuck at 61/92 (~66%).
Is this behavior expected?
The plots and subsequent parts of lesson one come out fine from what I can tell, but its unclear at this early stage whether lr_find is working properly.
