I suggest that we could participate individually and keep a friendly competition amongst ourselves on the leaderboard first.
I did move it to the Folder with the Test,Train and Valid and uploaded to https://transfer.sh/EhyAz/dataset.zip .
You can just to Wget to get the dataset with the preprocessing. Hope this helps
Yep. Looks like that is the choice.
Hey Thanks that worked well.
I just realized the Test folder was empty . Will upload a new dataset folder shortly
@jamesrequa I see you started submitting, did you build upon Jeremy’s notebook demo in class ?
If so, how did you move from training to actual prediction & submit with the fastai library ?
Yep I just built on the lesson 1 notebook with a couple of differences, outlined below:
from_pathssince this dataset isn’t provided in sub-folders by class. Jeremy covers all of this in Lesson 2, but its pretty much just a matter of passing in the train csv file name and paths to image folders. You also need to assign the validation set. Make sure you also provide the path to the test images here as the
test_nameargument otherwise it won’t be able to find the test images when you run predictions after training.
When you are finished training and ready to run predictions on the test set you just need to use
learn.predict(is_test=True). You can also do TTA the same way as you normally would just making sure to pass in
is_test=Truesince you are using the test set not the validation set.
You’ll also need to convert the raw predictions to probabilities i.e.
test_preds = np.exp(test_preds).
From there you just create the submission file using the probabilities. It should already be in the correct shape. One last thing to be careful about is the sorting/ordering of the predictions. When I first submitted to Kaggle, in fact, I had the wrong sorting (I used the default ordering in the sample submission file) and got really bad scores as a result. You can be sure its correct just by using
data.test_dl.dataset.fnamesas your test image
That’s basically it!
I’ve tried to duplicate your notebook, as shown in last night second-half.
It works fine when I use “regular” model names in Cell #3 as
arch=resnet50 (or resnet101), though with lower accuracy (0.89 vs 0.92)
But if I enter
arch=resnext101_64, when I run the first
learn = ConvLearner.pretrained(arch, data, precompute=True), it generates an error as:
Preformatted text`FileNotFoundError: [Errno 2] No such file or directory: ‘/media/eric/SSD500/fastai-master2/courses/dl1/fastai/weights/resnext_101_64x4d.pth’
I did a
git pull a few minutes ago, no fix.
Dog Breed Challenge Precompute Error
Downloading now (without the ‘4’ at the end of the url :-))
Oops just edited the link, thanks!
One night works and first ever submission got me top15 in the competition!
You can use arch = resnext101 without the 64, I assume resnext101_64 is another model. That works for me without having to download the weights.
Hi Guys, Did you resized the images to 224 or 299. I resaw the video and Jeremy didn’t mention to resize. But there is code block which does the resize. Just want to know how you are handling that
@satish860 It’s sz parameter. Try different values to see which is better. Jeremy gave a hint to look at sizes distribution.
@jakcycsl Congrats! I assume 10-th place is a group of students from some other dl course )
@jeremy explains why he used the resize trick, from 224 to 299, here.
It’s cutting-edge SOTA secret sauce, don’t tell anyone
I got this error when I tried to make predictions for test set.
Does anybody help me solve this issue?
Thanks in advance