Skip to content

Instantly share code, notes, and snippets.

View Eshan-Agarwal's full-sized avatar
🏠
Work From Home

Eshan Agarwal Eshan-Agarwal

🏠
Work From Home
View GitHub Profile
{
"citation": "@article{recht2018cifar10.1,\n author = {Benjamin Recht and Rebecca Roelofs and Ludwig Schmidt and Vaishaal Shankar},\n title = {Do CIFAR-10 Classifiers Generalize to CIFAR-10?},\n year = {2018},\n note = {\\url{https://arxiv.org/abs/1806.00451}},\n}\n\n@article{torralba2008tinyimages, \n author = {Antonio Torralba and Rob Fergus and William T. Freeman}, \n journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, \n title = {80 Million Tiny Images: A Large Data Set for Nonparametric Object and Scene Recognition}, \n year = {2008}, \n volume = {30}, \n number = {11}, \n pages = {1958-1970}\n}",
"description": "The CIFAR-10.1 dataset is a new test set for CIFAR-10. CIFAR-10.1 contains roughly 2,000 new test images \nthat were sampled after multiple years of research on the original CIFAR-10 dataset. The data collection \nfor CIFAR-10.1 was designed to minimize distribution shift relative to the original dataset. We describe \nthe creation of CIFAR-10.1 in the pap
@Eshan-Agarwal
Eshan-Agarwal / dataset_info.json
Created May 1, 2020 13:18
dataset_info for oxford_iiit_pet dataset
{
"citation": "@InProceedings{parkhi12a,\n author = \"Parkhi, O. M. and Vedaldi, A. and Zisserman, A. and Jawahar, C.~V.\",\n title = \"Cats and Dogs\",\n booktitle = \"IEEE Conference on Computer Vision and Pattern Recognition\",\n year = \"2012\",\n}",
"description": "The Oxford-IIIT pet dataset is a 37 category pet image dataset with roughly 200\nimages for each class. The images have large variations in scale, pose and\nlighting. All images have an associated ground truth annotation of breed.",
"downloadSize": "811092049",
"location": {
"urls": [
"http://www.robots.ox.ac.uk/~vgg/data/pets/"
]
},
"name": "oxford_iiit_pet",
@Eshan-Agarwal
Eshan-Agarwal / dataset_info.json
Created April 30, 2020 16:16
dataset_info for oxford_flowers102
{
"citation": "@InProceedings{Nilsback08,\n author = \"Nilsback, M-E. and Zisserman, A.\",\n title = \"Automated Flower Classification over a Large Number of Classes\",\n booktitle = \"Proceedings of the Indian Conference on Computer Vision, Graphics and Image Processing\",\n year = \"2008\",\n month = \"Dec\"\n}",
"description": "The Oxford Flowers 102 dataset is a consistent of 102 flower categories commonly occurring\nin the United Kingdom. Each class consists of between 40 and 258 images. The images have\nlarge scale, pose and light variations. In addition, there are categories that have large\nvariations within the category and several very similar categories.\n\nThe dataset is divided into a training set, a validation set and a test set.\nThe training set and validation set each consist of 10 images per class (totalling 1020 images each).\nThe test set consists of the remaining 6149 images (minimum 20 per class).",
"downloadSize": "344878000",
"location": {
"urls": [
"https:/
@Eshan-Agarwal
Eshan-Agarwal / dataset_info.json
Created April 29, 2020 19:34
dataset_info for rock_paper_scissors
{
"citation": "@ONLINE {rps,\nauthor = \"Laurence Moroney\",\ntitle = \"Rock, Paper, Scissors Dataset\",\nmonth = \"feb\",\nyear = \"2019\",\nurl = \"http://laurencemoroney.com/rock-paper-scissors-dataset\"\n}",
"description": "Images of hands playing rock, paper, scissor game.",
"downloadSize": "230198979",
"location": {
"urls": [
"http://laurencemoroney.com/rock-paper-scissors-dataset"
]
},
"name": "rock_paper_scissors",
@Eshan-Agarwal
Eshan-Agarwal / dataset_info.json
Created April 29, 2020 19:33
dataset_info for horses_or_humans
{
"citation": "@ONLINE {horses_or_humans,\nauthor = \"Laurence Moroney\",\ntitle = \"Horses or Humans Dataset\",\nmonth = \"feb\",\nyear = \"2019\",\nurl = \"http://laurencemoroney.com/horses-or-humans-dataset\"\n}",
"description": "A large set of images of horses and humans.",
"downloadSize": "161055054",
"location": {
"urls": [
"http://laurencemoroney.com/horses-or-humans-dataset"
]
},
"name": "horses_or_humans",
[Errno 2] No such file or directory: 'datasets'
/content/datasets
Downloading and preparing dataset nsynth/gansynth_subset/2.3.2 (download: 73.08 GiB, generated: 20.73 GiB, total: 93.80 GiB) to gs://beamm/nsynth/gansynth_subset/2.3.2...
WARNING:absl:Dataset nsynth is hosted on GCS. It will automatically be downloaded to your
local data directory. If you'd instead prefer to read directly from our public
GCS bucket (recommended if you're running on GCP), you can instead pass
`try_gcs=True` to `tfds.load` or set `data_dir=gs://tfds-data/datasets`.
********************************************************************************
prefix : datasets/nsynth/gansynth_subset/2.3.2
Error in atexit._run_exitfuncs:
Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/IPython/core/history.py", line 786, in writeout_cache
self._writeout_input_cache(conn)
File "/usr/local/lib/python3.6/dist-packages/IPython/core/history.py", line 770, in _writeout_input_cache
(self.session_number,)+line)
sqlite3.ProgrammingError: SQLite objects created in a thread can only be used in that same thread. The object was created in thread id 140422523496192 and this is thread id 140424189716352.
Error in atexit._run_exitfuncs:
Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/IPython/core/history.py", line 786, in writeout_cache
@Eshan-Agarwal
Eshan-Agarwal / stacktrace.txt
Created April 17, 2020 19:41
Stacktrace for caltech_birds.py
AssertionError Traceback (most recent call last)
<ipython-input-1-0cac24b5abed> in <module>
1 import tensorflow_datasets as tfds
2
----> 3 ds, ds_info = tfds.load("caltech_birds2011", with_info=True)
4 print(ds_info)
~\Desktop\TF_TFDS\datasets\tensorflow_datasets\core\api_utils.py in disallow_positional_args_dec(fn, instance, args, kwargs)
51 _check_no_positional(fn, args, ismethod, allowed=allowed)
52 _check_required(fn, kwargs)
@Eshan-Agarwal
Eshan-Agarwal / Logs.txt
Created April 6, 2020 17:24
Traceback for subsplit
---------------------------------------------------------------------------
AssertionError Traceback (most recent call last)
<ipython-input-6-ba8aad3a0131> in <module>()
3 s1, s2, s3 = tfds.Split.TRAIN.subsplit(weighted = [2, 1, 1])
4
----> 5 dataset,info= tfds.load('mnist',with_info=True, split=s1)
13 frames
/content/datasets/tensorflow_datasets/core/tfrecords_reader.py in _str_to_relative_instruction(spec)
355 res = _SUB_SPEC_RE.match(spec)
@Eshan-Agarwal
Eshan-Agarwal / registered_test.txt
Created April 4, 2020 09:11
Test output of registered_test.py after adding unitests
2020-04-04 09:05:14.877488: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1
Running tests under Python 3.6.9: /usr/bin/python3
[ RUN ] RegisteredTest.test_abstract
[ OK ] RegisteredTest.test_abstract
[ RUN ] RegisteredTest.test_builder_fullname
[ OK ] RegisteredTest.test_builder_fullname
[ RUN ] RegisteredTest.test_builder_with_kwargs
[ OK ] RegisteredTest.test_builder_with_kwargs
[ RUN ] RegisteredTest.test_duplicate_dataset
[ OK ] RegisteredTest.test_duplicate_dataset