I have created a generic vectorized algorithm for a feed forward network, as one of the exercise in DL-105. However i am not able to get satisfied result while implementing, can you please guide me through this. I’m attaching my developed code. kindly help me out by verifying this code is it correct or have to do any changes… I’m getting the op but its with high loss
```
class FFN_Genclass:
def __init__(self, inputs, outputs, hidden_neurons=[1]):
self.ni = inputs.shape\[1\]
self.no = outputs.shape\[1\]
self.hl = len(hidden\_neurons)
self.hn = hidden\_neurons
self.sizes = \[self.ni\] + self.hn + \[self.no\]
self.W = {}
self.B = {}
for i in range(self.hl + 1):
self.W\[i+1\] = np.random.randn(self.sizes\[i\], self.sizes\[i+1\])
self.B\[i+1\] = np.random.randn(1, self.sizes\[i+1\])
def sigmoid(self, X):
return 1.0/(1.0 + np.exp(-X))
def softmax(self, X):
exps = np.exp(X)
return exps / np.sum(exps, axis=1).reshape(-1,1)
def forward_pass(self,X):
self.H = {}
self.A = {}
self.H\[0\] = X
for i in range(self.hl):
self.A\[i+1\] = np.matmul(self.H\[i\],self.W\[i+1\]) + self.B\[i+1\]
self.H\[i+1\] = self.sigmoid(self.A\[i+1\])
self.A\[self.hl+1\] = np.matmul(self.H\[self.hl\], self.W\[self.hl + 1\])
self.H\[self.hl+1\] = self.softmax(self.A\[self.hl+1\])
self.OP\_H = self.H\[self.hl+1\]
return self.OP\_H
def grad_sigmoid(self, X):
return X\*(1-X)
def grad(self,X,Y):
self.forward\_pass(X)
n = len(self.sizes) - 1
self.DH = {}
self.DA = {}
self.DW = {}
self.DB = {}
self.DA\[n\] = self.OP\_H - Y
for k in range(n,0,-1):
self.DW\[k\] = np.matmul(self.H\[k-1\].T,self.DA\[k\])
self.DB\[k\] = np.sum(self.DA\[k\], axis=0).reshape(1,-1)
self.DH\[k-1\] = np.matmul(self.DA\[k\],self.W\[k\].T)
self.DA\[k-1\] = np.multiply(self.DH\[k-1\], self.sigmoid(self.H\[k-1\]))
def fit(self,X,Y,epochs=1,learning_rate=1,display_loss=False):
DW = {}
DB = {}
if display\_loss:
loss = {}
m = X.shape\[0\]
for i in tqdm\_notebook(range(epochs), total=epochs, unit="epoch"):
self.grad(X,Y)
for j in range(self.hl + 1):
self.W\[j+1\] -= (learning\_rate \* self.DW\[j+1\]/m)
self.B\[j+1\] -= (learning\_rate \* self.DB\[j+1\]/m)
if display\_loss:
y\_pred = self.predict(X)
loss\[i\] = log\_loss(np.argmax(Y, axis=1), y\_pred)
if display\_loss:
plt.plot(loss.values())
plt.xlabel('Epochs')
plt.ylabel('CE\_loss')
plt.show()
def predict(self, X):
Y\_pred = self.forward\_pass(X)
return np.array(Y\_pred).squeeze()
```
