alu/tra-analysis
1
0
Fork 0
mirror of https://github.com/titanscouting/tra-analysis.git synced 2024-12-27 01:59:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update titanlearn.py

Browse Source
This commit is contained in:
ltcptgeneral 2019-03-01 13:49:33 -06:00
parent 28b5f9d6a2
commit 110da31d50
1 changed files with 9 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
data analysis/titanlearn.py
View File

@ -30,6 +30,7 @@ from sklearn import metrics
import numpy as np import numpy as np
import matplotlib.pyplot as plt import matplotlib.pyplot as plt
import math import math
from sklearn import datasets
#enable CUDA if possible #enable CUDA if possible
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
@ -112,8 +113,8 @@ def train_sgd_simple(net, evalType, data, ground, dev=None, devg=None, iters=100
dev_losses.append(ap) dev_losses.append(ap)
plt.plot(np.array(range(0,i+1,testevery)),np.array(losses), label="dev AP") plt.plot(np.array(range(0,i+1,testevery)),np.array(losses), label="dev AP")
elif evalType == "regression": elif evalType == "regression":
ev = metrics.explained_variance_score(devg.numpy(), output.numpy()) ap = metrics.explained_variance_score(devg.numpy(), output.numpy())
dev_losses.append(ev) dev_losses.append(ap)
plt.plot(np.array(range(0,i+1,testevery)),np.array(losses), label="dev EV") plt.plot(np.array(range(0,i+1,testevery)),np.array(losses), label="dev EV")
@ -190,13 +191,9 @@ def train_sgd_minibatch(net, data, ground, dev=None, devg=None, epoch=100, batch
plt.show() plt.show()
return model return model
def retyuoipufdyu(): data = datasets.load_diabetes()
print(data["data"], data["target"])
data = torch.tensor([[ 1., 2., 5., 2., 5.], ground = torch.tensor(data["target"]).to(torch.float)
[27., 8., 4., 6., 10.], data = torch.tensor(data["data"]).to(torch.float)
[12., 12., 12., 5., 6.], model = linear_nn(10, 100, 1, 20, act_fn = "tanh")
[10., 12., 10., 20., 2.], model = train_sgd_simple(model,"regression", data, ground, learnrate=1e-4)
[ 1., 2., 3., 4., 5.]])
ground = torch.tensor([15., 55., 47., 54., 15.])
model = linear_nn(5, 10, 1, 3, act_fn = "relu")
return train_sgd_simple(model,"regression", data, ground, learnrate=1e-2)