<!DOCTYPE html> <html> <head> <title>Training a model on browser</title> </head> <body></body> </html>
<script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs@latest"></script>
function doTraining(model) {
//here we are going to write logic for training
}
async function doTraining(model){
const history =
await model.fit(xs, ys,
{ epochs: 500,
callbacks:{
onEpochEnd: async(epoch, logs) =>{
console.log("Epoch:"
+ epoch
+ " Loss:"
+ logs.loss);
}
}
});
}
const model = tf.sequential();model.add(tf.layers.dense({units: 1, inputShape: [1]}));model.compile({loss:'meanSquaredError', optimizer:'sgd'});
model.summary()
//pretty simple
const xs = tf.tensor2d([-1.0, 0.0, 1.0, 2.0, 3.0, 4.0], [6, 1]);const ys = tf.tensor2d([-3.0, -1.0, 2.0, 3.0, 5.0, 7.0], [6, 1]);
let xs = [-1.0, 0.0, 1.0, 2.0, 3.0, 4.0] # array[6,1] # shape of that array
doTraining(model).then(() => {
alert(model.predict(tf.tensor2d([10], [1,1])));
}); #calling the function
<h1 align="center">Press 'f12' key or 'Ctrl' + 'Shift' + 'i' to check whats going on</h1>
<!DOCTYPE html> <html> <head> <title>Training a model on browser</title> <script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs@latest"></script><script lang="js"> async function doTraining(model){ const history = await model.fit(xs, ys, { epochs: 500, callbacks:{ onEpochEnd: async(epoch, logs) =>{ console.log("Epoch:" + epoch + " Loss:" + logs.loss); } } }); } const model = tf.sequential(); model.add(tf.layers.dense({units: 1, inputShape: [1]})); model.compile({loss:'meanSquaredError', optimizer:'sgd'}); model.summary(); const xs = tf.tensor2d([-1.0, 0.0, 1.0, 2.0, 3.0, 4.0], [6, 1]); const ys = tf.tensor2d([-3.0, -1.0, 2.0, 3.0, 5.0, 7.0], [6, 1]); doTraining(model).then(() => { alert(model.predict(tf.tensor2d([10], [1,1]))); }); </script> </head> <body> <h1 align="center">Press 'f12' key or 'Ctrl' + 'Shift' + 'i' to check whats going on</h1> </body> </html>
Input: [0, 1.5707963267948966, 3.141592653589793, 4.71238898038469, 6.283185307179586]Sine values: [ 0.0000000e+00 1.0000000e+00 1.2246468e-16 -1.0000000e+00-2.4492936e-16]Cosine values: [ 1.0000000e+00 6.1232340e-17 -1.0000000e+00 -1.8369702e-161.0000000e+00]Sine values: [ 0. 1. 0. -1. -0.]Cosine values: [ 1. 0. -1. -0. 1.]
df = pd.DataFrame('some data...')df.plot(x='label1', y='label2', kind='scatter', ...)
# generate random data with a small set of outliers
np.random.seed(0)
X[:n_outliers] = 3 + 0.5 * np.random.normal(size=(n_outliers, 1))
y[:n_outliers] = -3 + 10 * np.random.normal(size=n_outliers)
# Fit line using all data
lr = linear_model.LinearRegression()
lr.fit(X, y)
# Robustly fit linear model with RANSAC algorithm
ransac = linear_model.RANSACRegressor()
ransac.fit(X, y)
inlier_mask = ransac.inlier_mask_
outlier_mask = np.logical_not(inlier_mask)
# Predict data of estimated models
line_X = np.arange(X.min(), X.max())[:, np.newaxis]
line_y = lr.predict(line_X)
line_y_ransac = ransac.predict(line_X)
sklearn.model_selection.train_test_split(*arrays, **options)[source]
np.array() to convert a list to an array many times, I wasn’t prepared for line after line of linspace, meshgrid and vsplit.ndarray, meaning “N-dimensional array”.import numpy as nparr = np.array([[1,2],[3,4]]) type(arr)#=> numpy.ndarray
np.zeros((2)) generates a 1D array. np.zeros((2,2)) generates a 2D array. np.zeros((2,2,2)) generates a 3D array. np.zeros((2,2,2,2)) generates a 4D array. And so on…np.zeros((2)) #=> array([0., 0.])np.zeros((2,2)) #=> array([[0., 0.], #=> [0., 0.]])np.zeros((2,2,2)) #=> array([[[0., 0.], #=> [0., 0.]], #=> #=> [[0., 0.], #=> [0., 0.]]]) ...
(2,3,2) is a 2x3x2 dimension array. And looks like below.np.zeros((2,3,2))#=> array([[[0., 0.], #=> [0., 0.], #=> [0., 0.]], #=> #=> [[0., 0.], #=> [0., 0.], #=> [0., 0.]]])
dtype can be np.float64, np.int8, int, str or one of several other types.np.zeros((2,3))
#=> array([[0., 0., 0.],
#=> [0., 0., 0.]])
np.ones((2,3))
#=> array([[1., 1., 1.],
#=> [1., 1., 1.]])
np.empty() is a little different than zeros and ones, as it doesn’t preset any values in the array. Some people say it’s slightly faster to initialize but that’s negligible.arr = np.empty((2,2))
arr
#=> array([[1.00000000e+000, 1.49166815e-154],
#=> [4.44659081e-323, 0.00000000e+000]])
10. And then another array with ['a','b'] pairs.np.full((3,2), 10) #=> array([[10, 10], #=> [10, 10], #=> [10, 10]])np.full((3,2), ['a','b']) #=> array([['a', 'b'], #=> ['a', 'b'], #=> ['a', 'b']], dtype='<U1')
li = ['a','b','c'] np.array(li)#=> array(['a', 'b', 'c'], dtype='<U1')
np.array also has a parameter called copy which you can set to True to guarantee a new array object is generated rather than pointing to an existing object._like functions corresponding to the functions we’ve discussed: empty_like, ones_like, zeros_like and full_like.ones_like generates an array of ones, but you pass it an existing array and it takes the shape of that, instead of you specifying the shape directly.a1 = np.array([[1,2],[3,4]]) #=> array([[1, 2], #=> [3, 4]])np.ones_like(a1) #=> array([[1, 1], #=> [1, 1]])
np.random.rand(3,2)
#=> array([[0.94664048, 0.76616114],
#=> [0.395549 , 0.84680126],
#=> [0.42873 , 0.77736086]])
np.asarray is a wrapper around np.array, which sets the parameter copy=False. See np.array above.list(range(50,60,2)) with lists.np.arange(50,60,2)
#=> array([50, 52, 54, 56, 58])
arange, we specify how many numbers to generate between the upper and lower limit.np.linspace(10, 20, 6) #=> array([10., 12., 14., 16., 18., 20.])np.linspace(0, 2, 5) #=> array([0. , 0.5, 1. , 1.5, 2. ])
np.meshgrid.x = np.array([1,2,3]) y = np.array([-3,-2,-1]) xcors, ycors = np.meshgrid(x, y) xcors #=> [[1 2 3] #=> [1 2 3] #=> [1 2 3]]ycors #=> [[-3 -3 -3] #=> [-2 -2 -2] #=> [-1 -1 -1]]
[[(1, -3), (2, -3), (3, -3)]
[(1, -2), (2, -2), (3, -2)],
[(1, -1), (2, -1), (3, -1)]]
a2, the value of a1 also changes.a1 = np.array([1,2,3]) a2 = a1a2[0] = 10 a1 #=> array([10, 2, 3])
a2 but a1 does not change… because we made a copy!a1 = np.array([1,2,3]) a2 = a1.copy()a2[0] = 10 a1 #=> array([1, 2, 3])
a = np.array([[1,2],[3,4],[5,6]])
a.shape
#=> (3, 2)
a = np.array([[1,2],[3,4],[5,6]])
a
#=> array([[1, 2],
#=> [3, 4],
#=> [5, 6]])
a.shape
#=> (3, 2)
a.reshape(2,3)
#=> array([[1, 2, 3],
#=> [4, 5, 6]])
a.reshape(6)
#=> array([1, 2, 3, 4, 5, 6])
a.reshape(6,1)
#=>array([[1],
#=> [2],
#=> [3],
#=> [4],
#=> [5],
#=> [6]])
a.reshape(2,3,1)
#=> array([[[1],
#=> [2],
#=> [3]],
#=>
#=> [[4],
#=> [5],
#=> [6]]])
reshape but it mutates the original array.a = np.array([['a','b'],['c','d']]) a #=>array([['a', 'b'], #=> ['c', 'd']], dtype='<U1')a.reshape(1,4) #=> array([['a', 'b', 'c', 'd']], dtype='<U1')a #=>array([['a', 'b'], #=> ['c', 'd']], dtype='<U1')a.resize(1,4) a #=> array([['a', 'b', 'c', 'd']], dtype='<U1')
reshape didn’t change a, but calling resize permanently changed its shape.a = np.array([['s','t','u'],['x','y','z']]) a #=> array([['s', 't', 'u'], #=> ['x', 'y', 'z']], dtype='<U1')a.T #=> array([['s', 'x'], #=> ['t', 'y'], #=> ['u', 'z']], dtype='<U1')
s and z .reshape(6) below. But flatten can be useful when you don’t know the size of an array in advance.a = np.array([[1,2,3],['a','b','c']]) a.flatten() #=> array(['1', '2', '3', 'a', 'b', 'c'], dtype='<U21')a.reshape(6) #=> array(['1', '2', '3', 'a', 'b', 'c'], dtype='<U21')
flatten but it returns a view of an array instead of a copy.flatten would fail.np.ravel([[1,2,3],[4,5,6]]) #=> array([1, 2, 3, 4, 5, 6])np.flatten([[1,2,3],[4,5,6]]) #=> AttributeError: module 'numpy' has no attribute 'flatten'
a = np.array( [[1,2,3], [4,5,6]]) a #=> array([[1, 2, 3], #=> [4, 5, 6]])np.hsplit(a,3)# #=> [array([[1],[4]]), # #=> array([[2],[5]]), # #=> array([[3],[6]])]
a = np.array( [[1,2,3], [4,5,6]]) a #=> array([[1, 2, 3], #=> [4, 5, 6]])np.vsplit(a,2)#=> [array([[1, 2, 3]]), #=> array([[4, 5, 6]])]
vsplit and hsplit in that it combines separate arrays into a single array.axis=0a = np.array(['a', 'b', 'c']) b = np.array(['d', 'e', 'f'])np.stack((a, b), axis=0) #=> array([['a', 'b', 'c'], #=> ['d', 'e', 'f']], dtype='<U1')
axis=1a = np.array(['a', 'b', 'c']) b = np.array(['d', 'e', 'f'])np.stack((a, b), axis=1) #=> array([['a', 'd'], #=> ['b', 'e'], #=> ['c', 'f']], dtype='<U1')
meshgrid is used to generate a matplotlib chart. Or how to quickly add a dimension so your data conforms with input requirements to a Keras model.The rise of Large Language Models (LLMs) has generated significant excitement in the tech community. However, the real value lies in turni...
