-
Thank you for this great package. I'm trying to use Albumentations for augmenting black and white drawing images like Quickdraw and Fashion MNIST datasets, but most of the examples seem focused on col…
-
It would be great it we have support for meta datasets. Several new research works focus on this benchmark. Do you think this would be added anytime soon?
https://github.com/google-research/meta-da…
mayug updated
3 years ago
-
This link does not work any longer.
https://www.tensorflow.org/tutorials/sequences/recurrent_quickdraw
-
For this year's GSOC, TFDS is going forward with community datasets. However, I had some queries regarding it as I would like to contribute to TFDS as part of this year's GSOC.
1. The [community da…
-
Fail to install l2l via anaconda3 in windows, hope can fix the issue
-
Hi.
When I try to download some datasets (mimgnet, CUB, quickdraw), an error occurs and cannot download them.
```
Traceback (most recent call last):
File "get_data.py", line 37, in
downloa…
-
I’m running a few repeated jobs using Drawing Classifier toolkit to train a model from a random sample of classes from a dataset. All the jobs have the same setup configuration and allocated memory. M…
-
Hi,
I got the following error while trying to pip install the package:
Building wheels for collected packages: learn2learn
Building wheel for learn2learn (setup.py) ... error
ERROR: Comma…
-
There are supposed to be clear subgroups in the teapot drawings from https://console.cloud.google.com/storage/browser/quickdraw_dataset/full/simplified
We should also think about a cover mode that …
-
hi 助教
我目前對於 npg to numpy bitmap 部分的處理方式是將其轉換為
(51, 300, 300, 3) 的格式,但這種方式無法在 load_data 正確執行,
於x = np.concatenate((x, data), axis=0) 會有錯誤,顯示如下訊息:
all the input arrays must have same number of dim…