Spaces:
Runtime error
Runtime error
debugging mnist model
Browse files- .gitignore +2 -1
- README.md +190 -12
- app.py +48 -9
- best_weights/mnist_model.pth +1 -1
- best_weights/optimizer.pth +2 -2
- data_mnist +1 -1
- requirements.txt +3 -1
.gitignore
CHANGED
@@ -4,4 +4,5 @@ flagged/*
|
|
4 |
data_mnist/*
|
5 |
model/*
|
6 |
model
|
7 |
-
data_mnist
|
|
|
|
4 |
data_mnist/*
|
5 |
model/*
|
6 |
model
|
7 |
+
data_mnist
|
8 |
+
slurm*
|
README.md
CHANGED
@@ -1,12 +1,190 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Git Large File Storage
|
2 |
+
|
3 |
+
![CI status][1]
|
4 |
+
|
5 |
+
[1]: https://github.com/git-lfs/git-lfs/workflows/CI/badge.svg
|
6 |
+
|
7 |
+
[Git LFS](https://git-lfs.github.com) is a command line extension and
|
8 |
+
[specification](docs/spec.md) for managing large files with Git.
|
9 |
+
|
10 |
+
The client is written in Go, with pre-compiled binaries available for Mac,
|
11 |
+
Windows, Linux, and FreeBSD. Check out the [website](http://git-lfs.github.com)
|
12 |
+
for an overview of features.
|
13 |
+
|
14 |
+
## Getting Started
|
15 |
+
|
16 |
+
### Downloading
|
17 |
+
|
18 |
+
You can install the Git LFS client in several different ways, depending on your
|
19 |
+
setup and preferences.
|
20 |
+
|
21 |
+
* **Linux users**. Debian and RPM packages are available from
|
22 |
+
[PackageCloud](https://packagecloud.io/github/git-lfs/install).
|
23 |
+
* **macOS users**. [Homebrew](https://brew.sh) bottles are distributed, and can
|
24 |
+
be installed via `brew install git-lfs`.
|
25 |
+
* **Windows users**. Git LFS is included in the distribution of
|
26 |
+
[Git for Windows](https://gitforwindows.org/). Alternatively, you can
|
27 |
+
install a recent version of Git LFS from the [Chocolatey](https://chocolatey.org/) package manager.
|
28 |
+
* **Binary packages**. In addition, [binary packages](https://github.com/git-lfs/git-lfs/releases) are
|
29 |
+
available for Linux, macOS, Windows, and FreeBSD.
|
30 |
+
* **Building from source**. [This repository](https://github.com/git-lfs/git-lfs.git) can also be
|
31 |
+
built from source using the latest version of [Go](https://golang.org), and the
|
32 |
+
available instructions in our
|
33 |
+
[Wiki](https://github.com/git-lfs/git-lfs/wiki/Installation#source).
|
34 |
+
|
35 |
+
### Installing
|
36 |
+
|
37 |
+
#### From binary
|
38 |
+
|
39 |
+
The [binary packages](https://github.com/git-lfs/git-lfs/releases) include a script which will:
|
40 |
+
|
41 |
+
- Install Git LFS binaries onto the system `$PATH`
|
42 |
+
- Run `git lfs install` to
|
43 |
+
perform required global configuration changes.
|
44 |
+
|
45 |
+
```ShellSession
|
46 |
+
$ ./install.sh
|
47 |
+
```
|
48 |
+
|
49 |
+
#### From source
|
50 |
+
|
51 |
+
- Place the `git-lfs` binary on your system’s executable `$PATH` or equivalent.
|
52 |
+
- Git LFS requires global configuration changes once per-machine. This can be done by
|
53 |
+
running:
|
54 |
+
|
55 |
+
```ShellSession
|
56 |
+
$ git lfs install
|
57 |
+
```
|
58 |
+
|
59 |
+
## Example Usage
|
60 |
+
|
61 |
+
To begin using Git LFS within a Git repository that is not already configured
|
62 |
+
for Git LFS, you can indicate which files you would like Git LFS to manage.
|
63 |
+
This can be done by running the following _from within a Git repository_:
|
64 |
+
|
65 |
+
```bash
|
66 |
+
$ git lfs track "*.psd"
|
67 |
+
```
|
68 |
+
|
69 |
+
(Where `*.psd` is the pattern of filenames that you wish to track. You can read
|
70 |
+
more about this pattern syntax
|
71 |
+
[here](https://git-scm.com/docs/gitattributes)).
|
72 |
+
|
73 |
+
> *Note:* the quotation marks surrounding the pattern are important to
|
74 |
+
> prevent the glob pattern from being expanded by the shell.
|
75 |
+
|
76 |
+
After any invocation of `git-lfs-track(1)` or `git-lfs-untrack(1)`, you _must
|
77 |
+
commit changes to your `.gitattributes` file_. This can be done by running:
|
78 |
+
|
79 |
+
```bash
|
80 |
+
$ git add .gitattributes
|
81 |
+
$ git commit -m "track *.psd files using Git LFS"
|
82 |
+
```
|
83 |
+
|
84 |
+
You can now interact with your Git repository as usual, and Git LFS will take
|
85 |
+
care of managing your large files. For example, changing a file named `my.psd`
|
86 |
+
(tracked above via `*.psd`):
|
87 |
+
|
88 |
+
```bash
|
89 |
+
$ git add my.psd
|
90 |
+
$ git commit -m "add psd"
|
91 |
+
```
|
92 |
+
|
93 |
+
> _Tip:_ if you have large files already in your repository's history, `git lfs
|
94 |
+
> track` will _not_ track them retroactively. To migrate existing large files
|
95 |
+
> in your history to use Git LFS, use `git lfs migrate`. For example:
|
96 |
+
>
|
97 |
+
> ```
|
98 |
+
> $ git lfs migrate import --include="*.psd"
|
99 |
+
> ```
|
100 |
+
>
|
101 |
+
> For more information, read [`git-lfs-migrate(1)`](https://github.com/git-lfs/git-lfs/blob/master/docs/man/git-lfs-migrate.1.ronn).
|
102 |
+
|
103 |
+
You can confirm that Git LFS is managing your PSD file:
|
104 |
+
|
105 |
+
```bash
|
106 |
+
$ git lfs ls-files
|
107 |
+
3c2f7aedfb * my.psd
|
108 |
+
```
|
109 |
+
|
110 |
+
Once you've made your commits, push your files to the Git remote:
|
111 |
+
|
112 |
+
```bash
|
113 |
+
$ git push origin master
|
114 |
+
Uploading LFS objects: 100% (1/1), 810 B, 1.2 KB/s
|
115 |
+
# ...
|
116 |
+
To https://github.com/git-lfs/git-lfs-test
|
117 |
+
67fcf6a..47b2002 master -> master
|
118 |
+
```
|
119 |
+
|
120 |
+
Note: Git LFS requires at least Git 1.8.2 on Linux or 1.8.5 on macOS.
|
121 |
+
|
122 |
+
## Limitations
|
123 |
+
|
124 |
+
Git LFS maintains a list of currently known limitations, which you can find and
|
125 |
+
edit [here](https://github.com/git-lfs/git-lfs/wiki/Limitations).
|
126 |
+
|
127 |
+
## Need Help?
|
128 |
+
|
129 |
+
You can get help on specific commands directly:
|
130 |
+
|
131 |
+
```bash
|
132 |
+
$ git lfs help <subcommand>
|
133 |
+
```
|
134 |
+
|
135 |
+
The [official documentation](docs) has command references and specifications for
|
136 |
+
the tool.
|
137 |
+
|
138 |
+
You can always [open an issue](https://github.com/git-lfs/git-lfs/issues), and
|
139 |
+
one of the Core Team members will respond to you. Please be sure to include:
|
140 |
+
|
141 |
+
1. The output of `git lfs env`, which displays helpful information about your
|
142 |
+
Git repository useful in debugging.
|
143 |
+
2. Any failed commands re-run with `GIT_TRACE=1` in the environment, which
|
144 |
+
displays additional information pertaining to why a command crashed.
|
145 |
+
|
146 |
+
## Contributing
|
147 |
+
|
148 |
+
See [CONTRIBUTING.md](CONTRIBUTING.md) for info on working on Git LFS and
|
149 |
+
sending patches. Related projects are listed on the [Implementations wiki
|
150 |
+
page](https://github.com/git-lfs/git-lfs/wiki/Implementations).
|
151 |
+
|
152 |
+
## Core Team
|
153 |
+
|
154 |
+
These are the humans that form the Git LFS core team, which runs the project.
|
155 |
+
|
156 |
+
In alphabetical order:
|
157 |
+
|
158 |
+
| [@bk2204][bk2204-user] | [@larsxschneider][larsxschneider-user] | [@PastelMobileSuit][PastelMobileSuit-user] |
|
159 |
+
|---|---|---|
|
160 |
+
| [![][bk2204-img]][bk2204-user] | [![][larsxschneider-img]][larsxschneider-user] | [![][PastelMobileSuit-img]][PastelMobileSuit-user] |
|
161 |
+
|
162 |
+
[bk2204-img]: https://avatars1.githubusercontent.com/u/497054?s=100&v=4
|
163 |
+
[larsxschneider-img]: https://avatars1.githubusercontent.com/u/477434?s=100&v=4
|
164 |
+
[PastelMobileSuit-img]: https://avatars2.githubusercontent.com/u/37254014?s=100&v=4
|
165 |
+
[bk2204-user]: https://github.com/bk2204
|
166 |
+
[larsxschneider-user]: https://github.com/larsxschneider
|
167 |
+
[PastelMobileSuit-user]: https://github.com/PastelMobileSuit
|
168 |
+
|
169 |
+
### Alumni
|
170 |
+
|
171 |
+
These are the humans that have in the past formed the Git LFS core team, or
|
172 |
+
have otherwise contributed a significant amount to the project. Git LFS would
|
173 |
+
not be possible without them.
|
174 |
+
|
175 |
+
In alphabetical order:
|
176 |
+
|
177 |
+
| [@andyneff][andyneff-user] | [@rubyist][rubyist-user] | [@sinbad][sinbad-user] | [@technoweenie][technoweenie-user] | [@ttaylorr][ttaylorr-user] |
|
178 |
+
|---|---|---|---|---|
|
179 |
+
| [![][andyneff-img]][andyneff-user] | [![][rubyist-img]][rubyist-user] | [![][sinbad-img]][sinbad-user] | [![][technoweenie-img]][technoweenie-user] | [![][ttaylorr-img]][ttaylorr-user] |
|
180 |
+
|
181 |
+
[andyneff-img]: https://avatars1.githubusercontent.com/u/7596961?v=3&s=100
|
182 |
+
[rubyist-img]: https://avatars1.githubusercontent.com/u/143?v=3&s=100
|
183 |
+
[sinbad-img]: https://avatars1.githubusercontent.com/u/142735?v=3&s=100
|
184 |
+
[technoweenie-img]: https://avatars3.githubusercontent.com/u/21?v=3&s=100
|
185 |
+
[ttaylorr-img]: https://avatars2.githubusercontent.com/u/443245?s=100&v=4
|
186 |
+
[andyneff-user]: https://github.com/andyneff
|
187 |
+
[sinbad-user]: https://github.com/sinbad
|
188 |
+
[rubyist-user]: https://github.com/rubyist
|
189 |
+
[technoweenie-user]: https://github.com/technoweenie
|
190 |
+
[ttaylorr-user]: https://github.com/ttaylorr
|
app.py
CHANGED
@@ -20,11 +20,12 @@ n_epochs = 10
|
|
20 |
batch_size_train = 128
|
21 |
batch_size_test = 1000
|
22 |
learning_rate = 0.01
|
|
|
23 |
momentum = 0.5
|
24 |
log_interval = 10
|
25 |
random_seed = 1
|
26 |
TRAIN_CUTOFF = 10
|
27 |
-
TEST_PER_SAMPLE =
|
28 |
DASHBOARD_EXPLANATION = DASHBOARD_EXPLANATION.format(TEST_PER_SAMPLE=TEST_PER_SAMPLE)
|
29 |
WHAT_TO_DO=WHAT_TO_DO.format(num_samples=TRAIN_CUTOFF)
|
30 |
MODEL_PATH = 'model'
|
@@ -162,7 +163,6 @@ TRAIN_TRANSFORM = torchvision.transforms.Compose([
|
|
162 |
test_loader = torch.utils.data.DataLoader(MNISTCorrupted(TRAIN_TRANSFORM),
|
163 |
batch_size=batch_size_test, shuffle=False)
|
164 |
|
165 |
-
|
166 |
# Source: https://nextjournal.com/gkoehler/pytorch-mnist
|
167 |
class MNIST_Model(nn.Module):
|
168 |
def __init__(self):
|
@@ -220,6 +220,7 @@ def test():
|
|
220 |
acc = acc.item()
|
221 |
test_metric = '〽Current test metric -> Avg. loss: `{:.4f}`, Accuracy: `{:.0f}%`\n'.format(
|
222 |
test_loss,acc)
|
|
|
223 |
return test_metric,acc
|
224 |
|
225 |
|
@@ -233,6 +234,34 @@ optimizer = optim.SGD(network.parameters(), lr=learning_rate,
|
|
233 |
momentum=momentum)
|
234 |
|
235 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
236 |
def train_and_test(train_model=True):
|
237 |
|
238 |
if train_model:
|
@@ -244,6 +273,7 @@ def train_and_test(train_model=True):
|
|
244 |
|
245 |
test_metric,test_acc = test()
|
246 |
|
|
|
247 |
if os.path.exists(METRIC_PATH):
|
248 |
metric_dict = read_json(METRIC_PATH)
|
249 |
metric_dict['all'] = metric_dict['all']+ [test_acc] if 'all' in metric_dict else [] + [test_acc]
|
@@ -273,6 +303,7 @@ def train_and_test(train_model=True):
|
|
273 |
return test_metric
|
274 |
|
275 |
|
|
|
276 |
model_state_dict = MODEL_WEIGHTS_PATH
|
277 |
optimizer_state_dict = OPTIMIZER_PATH
|
278 |
model_repo.git_pull()
|
@@ -287,9 +318,14 @@ else:
|
|
287 |
# Use best weights
|
288 |
BEST_WEIGHTS_MODEL = "best_weights/mnist_model.pth"
|
289 |
BEST_WEIGHTS_OPTIMIZER = "best_weights/optimizer.pth"
|
290 |
-
|
291 |
-
torch.
|
292 |
-
|
|
|
|
|
|
|
|
|
|
|
293 |
|
294 |
|
295 |
def image_classifier(inp):
|
@@ -305,20 +341,23 @@ def image_classifier(inp):
|
|
305 |
model_repo.git_pull()
|
306 |
model_state_dict = MODEL_WEIGHTS_PATH
|
307 |
optimizer_state_dict = OPTIMIZER_PATH
|
|
|
308 |
|
309 |
if os.path.exists(model_state_dict) and os.path.exists(optimizer_state_dict):
|
|
|
310 |
network_state_dict = torch.load(model_state_dict)
|
311 |
network.load_state_dict(network_state_dict)
|
312 |
optimizer_state_dict = torch.load(optimizer_state_dict)
|
313 |
optimizer.load_state_dict(optimizer_state_dict)
|
314 |
else:
|
315 |
-
# Use best weights
|
|
|
316 |
BEST_WEIGHTS_MODEL = "best_weights/mnist_model.pth"
|
317 |
BEST_WEIGHTS_OPTIMIZER = "best_weights/optimizer.pth"
|
318 |
network.load_state_dict(torch.load(BEST_WEIGHTS_MODEL))
|
319 |
optimizer.load_state_dict(torch.load(BEST_WEIGHTS_OPTIMIZER))
|
320 |
-
|
321 |
-
input_image =
|
322 |
with torch.no_grad():
|
323 |
|
324 |
prediction = torch.nn.functional.softmax(network(input_image)[0], dim=0)
|
@@ -512,7 +551,7 @@ def main():
|
|
512 |
|
513 |
|
514 |
|
515 |
-
block.launch()
|
516 |
|
517 |
|
518 |
|
|
|
20 |
batch_size_train = 128
|
21 |
batch_size_test = 1000
|
22 |
learning_rate = 0.01
|
23 |
+
adv_learning_rate= 0.001
|
24 |
momentum = 0.5
|
25 |
log_interval = 10
|
26 |
random_seed = 1
|
27 |
TRAIN_CUTOFF = 10
|
28 |
+
TEST_PER_SAMPLE = 5000
|
29 |
DASHBOARD_EXPLANATION = DASHBOARD_EXPLANATION.format(TEST_PER_SAMPLE=TEST_PER_SAMPLE)
|
30 |
WHAT_TO_DO=WHAT_TO_DO.format(num_samples=TRAIN_CUTOFF)
|
31 |
MODEL_PATH = 'model'
|
|
|
163 |
test_loader = torch.utils.data.DataLoader(MNISTCorrupted(TRAIN_TRANSFORM),
|
164 |
batch_size=batch_size_test, shuffle=False)
|
165 |
|
|
|
166 |
# Source: https://nextjournal.com/gkoehler/pytorch-mnist
|
167 |
class MNIST_Model(nn.Module):
|
168 |
def __init__(self):
|
|
|
220 |
acc = acc.item()
|
221 |
test_metric = '〽Current test metric -> Avg. loss: `{:.4f}`, Accuracy: `{:.0f}%`\n'.format(
|
222 |
test_loss,acc)
|
223 |
+
print(test_metric)
|
224 |
return test_metric,acc
|
225 |
|
226 |
|
|
|
234 |
momentum=momentum)
|
235 |
|
236 |
|
237 |
+
|
238 |
+
train_loader = torch.utils.data.DataLoader(
|
239 |
+
torchvision.datasets.MNIST('./files/', train=True, download=True,
|
240 |
+
transform=TRAIN_TRANSFORM),
|
241 |
+
batch_size=batch_size_train, shuffle=True)
|
242 |
+
|
243 |
+
test_iid_loader = torch.utils.data.DataLoader(
|
244 |
+
torchvision.datasets.MNIST('./files/', train=False, download=True,
|
245 |
+
transform=TRAIN_TRANSFORM),
|
246 |
+
batch_size=batch_size_test, shuffle=True)
|
247 |
+
|
248 |
+
model_state_dict = MODEL_WEIGHTS_PATH
|
249 |
+
optimizer_state_dict = OPTIMIZER_PATH
|
250 |
+
if os.path.exists(model_state_dict) and os.path.exists(optimizer_state_dict):
|
251 |
+
network_state_dict = torch.load(model_state_dict)
|
252 |
+
network.load_state_dict(network_state_dict)
|
253 |
+
|
254 |
+
optimizer_state_dict = torch.load(optimizer_state_dict)
|
255 |
+
optimizer.load_state_dict(optimizer_state_dict)
|
256 |
+
|
257 |
+
# Train model
|
258 |
+
#n_epochs=20
|
259 |
+
#train(n_epochs,network,optimizer,train_loader)
|
260 |
+
#test()
|
261 |
+
|
262 |
+
|
263 |
+
|
264 |
+
|
265 |
def train_and_test(train_model=True):
|
266 |
|
267 |
if train_model:
|
|
|
273 |
|
274 |
test_metric,test_acc = test()
|
275 |
|
276 |
+
network.eval()
|
277 |
if os.path.exists(METRIC_PATH):
|
278 |
metric_dict = read_json(METRIC_PATH)
|
279 |
metric_dict['all'] = metric_dict['all']+ [test_acc] if 'all' in metric_dict else [] + [test_acc]
|
|
|
303 |
return test_metric
|
304 |
|
305 |
|
306 |
+
# Update model weights again
|
307 |
model_state_dict = MODEL_WEIGHTS_PATH
|
308 |
optimizer_state_dict = OPTIMIZER_PATH
|
309 |
model_repo.git_pull()
|
|
|
318 |
# Use best weights
|
319 |
BEST_WEIGHTS_MODEL = "best_weights/mnist_model.pth"
|
320 |
BEST_WEIGHTS_OPTIMIZER = "best_weights/optimizer.pth"
|
321 |
+
|
322 |
+
network_state_dict = torch.load(BEST_WEIGHTS_MODEL)
|
323 |
+
network.load_state_dict(network_state_dict)
|
324 |
+
|
325 |
+
optimizer_state_dict = torch.load(BEST_WEIGHTS_OPTIMIZER)
|
326 |
+
optimizer.load_state_dict(optimizer_state_dict)
|
327 |
+
if not os.path.exists(METRIC_PATH):
|
328 |
+
_ = train_and_test(False)
|
329 |
|
330 |
|
331 |
def image_classifier(inp):
|
|
|
341 |
model_repo.git_pull()
|
342 |
model_state_dict = MODEL_WEIGHTS_PATH
|
343 |
optimizer_state_dict = OPTIMIZER_PATH
|
344 |
+
which_weights=''
|
345 |
|
346 |
if os.path.exists(model_state_dict) and os.path.exists(optimizer_state_dict):
|
347 |
+
which_weights = "Using weights from model repo"
|
348 |
network_state_dict = torch.load(model_state_dict)
|
349 |
network.load_state_dict(network_state_dict)
|
350 |
optimizer_state_dict = torch.load(optimizer_state_dict)
|
351 |
optimizer.load_state_dict(optimizer_state_dict)
|
352 |
else:
|
353 |
+
# Use best weights
|
354 |
+
which_weights = "Using default best weights"
|
355 |
BEST_WEIGHTS_MODEL = "best_weights/mnist_model.pth"
|
356 |
BEST_WEIGHTS_OPTIMIZER = "best_weights/optimizer.pth"
|
357 |
network.load_state_dict(torch.load(BEST_WEIGHTS_MODEL))
|
358 |
optimizer.load_state_dict(torch.load(BEST_WEIGHTS_OPTIMIZER))
|
359 |
+
network.eval()
|
360 |
+
input_image = TRAIN_TRANSFORM(inp).unsqueeze(0)
|
361 |
with torch.no_grad():
|
362 |
|
363 |
prediction = torch.nn.functional.softmax(network(input_image)[0], dim=0)
|
|
|
551 |
|
552 |
|
553 |
|
554 |
+
block.launch(share=True)
|
555 |
|
556 |
|
557 |
|
best_weights/mnist_model.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 89871
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:148112958ca9545938f0660cec604ac4c7f52dca3523091e1e8e4e6a26e1ebc7
|
3 |
size 89871
|
best_weights/optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aac1c136737d50c2665563392a5b220396398cf1e2a2049dbefd7dc95473f5a5
|
3 |
+
size 89807
|
data_mnist
CHANGED
@@ -1 +1 @@
|
|
1 |
-
Subproject commit
|
|
|
1 |
+
Subproject commit c26d5d2bfb2623f637df6101899ad1f334b05de3
|
requirements.txt
CHANGED
@@ -1,3 +1,5 @@
|
|
1 |
torch
|
2 |
torchvision
|
3 |
-
matplotlib
|
|
|
|
|
|
1 |
torch
|
2 |
torchvision
|
3 |
+
matplotlib
|
4 |
+
gradio
|
5 |
+
huggingface_hub
|