mirror/DeepCreamPy
1
0
Fork 0
mirror of https://github.com/Deepshift/DeepCreamPy.git synced 2025-04-10 21:44:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

update README

Browse Source
This commit is contained in:
deeppomf 2018-03-19 12:21:36 -04:00
parent 0baa81b7c5
commit 349845a818
3 changed files with 6 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -104,6 +104,8 @@ Contributions are welcome! Special thanks to StartleStars for contributing code
# License # License
This code is for personal use and research use only.
Example image by dannychoo under [CC BY-NC-SA 2.0 License](https://creativecommons.org/licenses/by-nc-sa/2.0/). The example image is modified from the original, which can be found [here](https://www.flickr.com/photos/dannychoo/16081096643/in/photostream/). Example image by dannychoo under [CC BY-NC-SA 2.0 License](https://creativecommons.org/licenses/by-nc-sa/2.0/). The example image is modified from the original, which can be found [here](https://www.flickr.com/photos/dannychoo/16081096643/in/photostream/).
Model is licensed under CC BY-NC-SA 4.0 License. Model is licensed under CC BY-NC-SA 4.0 License.
@ -139,4 +141,4 @@ Code is licensed under CC BY-NC-SA 4.0 License and is modified from tadax's proj
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE. # SOFTWARE.
``` ```

0
models_backup/.gitkeep Normal file
View File

3
train.py
View File

@ -87,6 +87,9 @@ def train(args):
d_loss_value = 0 d_loss_value = 0
for i in tqdm.tqdm(range(step_num)): for i in tqdm.tqdm(range(step_num)):
x_batch = x_train[i * args.batch_size:(i + 1) * args.batch_size] x_batch = x_train[i * args.batch_size:(i + 1) * args.batch_size]
#janky way of doing horizonal flips
if (np.random.random() < 0.5):
x_batch = np.fliplr(x_batch)
points_batch, mask_batch = get_points() points_batch, mask_batch = get_points()
_, g_loss, completion = sess.run([g_train_op, model.g_loss, model.completion], feed_dict={x: x_batch, mask: mask_batch, is_training: True}) _, g_loss, completion = sess.run([g_train_op, model.g_loss, model.completion], feed_dict={x: x_batch, mask: mask_batch, is_training: True})