summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorxAlpharax <42233094+xAlpharax@users.noreply.github.com>2023-09-01 02:58:35 +0300
committerxAlpharax <42233094+xAlpharax@users.noreply.github.com>2023-09-01 02:58:35 +0300
commit570128d1f3fa6948fe9ffcc771d8c1c15af08232 (patch)
treecde1beee9c5843943d858e7b949f5602ec4d1c4c
parent8f4ab67633231a96736da860861f35c044b30323 (diff)
Changed the weights download URL to something that can be CURL-ed
Changes to be committed: modified: README.md modified: neuralart.py
-rw-r--r--README.md2
-rw-r--r--neuralart.py4
2 files changed, 3 insertions, 3 deletions
diff --git a/README.md b/README.md
index 919ec79..936a95a 100644
--- a/README.md
+++ b/README.md
@@ -2,7 +2,7 @@
Neural Style Transfer done from the CLI using a VGG backbone and presented as an MP4.
-Weights can be downloaded from [here](https://drive.google.com/file/d/1Pfh-dHvCdhn97MpLT0_I6QAAzvejqs1i/). The downloaded file should be placed in `./weights/` and any file will be ignored from there when pushing, as seen in `./.gitignore`. Update: Alternatively, if the `./weights/` directory is empty, `./neuralart.py` will automatically download publicly available VGG19 weights for the user.
+Weights can be downloaded from [here](https://files.catbox.moe/wcao20.pth). The downloaded file (renamed to `vgg_conv_weights.pth`) should be placed in `./weights/` and it will be ignored when pushing, as seen in `./.gitignore`. Update: Alternatively, if the `./weights/` directory is empty, `./neuralart.py` will automatically download publicly available VGG19 weights for the user.
More in depth information about Neural Style Transfer ( NST ) can be found in this great [paper](https://arxiv.org/abs/1705.04058). Make sure to check [Requirements](#requirements) and [Usage](#usage).
diff --git a/neuralart.py b/neuralart.py
index 349c989..fadaf12 100644
--- a/neuralart.py
+++ b/neuralart.py
@@ -30,10 +30,10 @@ image_path = '' # by default use neural-art as relative dir
### userland testing for multiple instances, a big nono currently
n_instances = os.popen('ps aux | grep "python neuralart.py" | wc -l').read()
-if int(n_instances) > 3: print("Woah, running 2 or more instances of neural-art at the same time?\nThis is an experimental feature as of now... try it later favorably :3")
+if int(n_instances) > 3: print("Woah, running 2 or more instances of neural-art at the same time?\nThis is an experimental feature as of now... try it later :3")
### check if there are any weights to use, if not, download the default provided ones
-#if int(os.popen('ls -l weights | wc -l').read()) == 1: os.system('wget -O "weights/vgg_conv_weights.pth" "https://m1.afileditch.ch/ajjMsHrRhnikrrCiUXgY.pth"')
+if int(os.popen('ls -l weights | wc -l').read()) == 1: os.system(f'curl https://files.catbox.moe/wcao20.pth --output {model_path}')
### Defining neural architecture