This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
version: '3.1' | |
services: | |
zookeeper: | |
platform: linux/amd64 | |
container_name: zookeeper | |
image: zookeeper:3.4 | |
restart: on-failure | |
volumes: | |
- "./zookeeper/data:/data" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# parameters | |
nc: 7 # number of classes # CHANGED HERE | |
depth_multiple: 0.33 # model depth multiple | |
width_multiple: 0.50 # layer channel multiple | |
# anchors | |
anchors: | |
- [10,13, 16,30, 33,23] # P3/8 | |
- [30,61, 62,45, 59,119] # P4/16 | |
- [116,90, 156,198, 373,326] # P5/32 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<h1>SignUp</h1> | |
<form method="POST"> | |
{% csrf_token %} | |
{{ form.as_p }} | |
<button type="submit">Sign Up</button> | |
</form> |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
absl-py==0.8.1 | |
astor==0.8.0 | |
certifi==2019.11.28 | |
chardet==3.0.4 | |
cogapp==3.0.0 | |
Cython | |
decorator==4.4.1 | |
defusedxml==0.6.0 | |
gast==0.3.2 | |
google-pasta==0.1.8 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
for c in classes: | |
print(c) | |
verify_images(path/c, delete=True, max_size=500) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
urls = Array.from(document.querySelectorAll('.rg_di .rg_meta')).map(el=>JSON.parse(el.textContent).ou); | |
window.open('data:text/csv;charset=utf-8,' + escape(urls.join('\n'))); |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import glob, os | |
# change the path of your images folder | |
dataset_path = '/home/thecaffeinedev/yolov3/training/images' | |
# Percentage of images to be used for the test set | |
percentage_test = 30; | |
# Create and/or truncate train.txt and test.txt | |
file_train = open('train.txt', 'w') |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy as np | |
def nonlin(x,deriv=False): | |
if(deriv==True): | |
return x*(1-x) | |
return 1/(1+np.exp(-x)) | |
X = np.array([[0,0,1], | |
[0,1,1], |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Here, about 1.2 MB of data produced a pickle of about 120MB Of data 100 times | |
# training might take a lot of time on bigger data sets | |
# saving the model as you train it helps here | |
import tensorflow as tf | |
from TF_own_data_model import create_feature_sets_and_labels | |
import numpy as np | |
# can load the data from the pickle | |
# or you could just write it down |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from numpy import exp, array, random, dot | |
class NeuralNetwork(): | |
def __init__(self): | |
# Seed the random number generator, so it generates the same numbers | |
# every time the program runs. | |
random.seed(1) | |
# We model a single neuron, with 3 input connections and 1 output connection. |