I am trying to train the Alexnet upon the data that i collected. It contains the images converted to grayscale and the associated key. This is a program to simulate a self driving car.
The keys are :
w = [1,0,0]
a = [0,1,0]
d = [0,0,1]
This is my code
import numpy as np
from alexnet import alexnet
WIDTH = 100
HEIGHT = 80
LR = 1e-3
EPOCHS = 8
MODEL_NAME = 'Udacity Model Car NN'
model = alexnet(WIDTH,HEIGHT,LR)
train_data = np.load('data.npy',encoding="bytes")
train = train_data[:-200]
test = train_data[-200:]
X = np.array([i[0] for i in train]).reshape(-1,WIDTH,HEIGHT,1)
Y = [i[1] for i in train]
test_X = np.array([i[0] for i in test]).reshape(-1,WIDTH,HEIGHT,1)
test_Y = [i[1] for i in test]
model.fit({'input':X},{'targets':Y},n_epoch=EPOCHS,validation_set=({'input':test_X},{'targets:test_y'}),snapshot_step=500,show_metric=True,run_id=MODEL_NAME)
model.save(MODEL_NAME)
But after every Epoch the validation accuracy remains 0 as well as the validation loss remains 0 as well.
Training Step: 104 | total loss: 1.31713 | time: 119.279s| Momentum |epoch: 008 | loss: 1.31713 - acc: 0.3878 | val_loss: 0.00000 - val_acc: 0.0000 -- iter: 801/801
This is probably a typo, look what you are passing as validation:
{'input':test_X},{'targets:test_y'}
\______________/ \_______________/
correct dict this is a set with a string!
while it should be
{'input':test_X},{'targets':test_Y}
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.