def features(self, input): x = self.conv1(input) x = self.bn1(x) x = autograd.relu(x) x = self.conv2(x) x = self.bn2(x) x = autograd.relu(x) x = self.block1(x) x = self.block2(x) x = self.block3(x) x = self.block4(x) x = self.block5(x) x = self.block6(x) x = self.block7(x) x = self.block8(x) x = self.block9(x) x = self.block10(x) x = self.block11(x) x = self.block12(x) x = self.conv3(x) x = self.bn3(x) x = autograd.relu(x) x = self.conv4(x) x = self.bn4(x) return x
def onnx_loss(a,model,target): ''' input: a graph node dictionary model: graph model target: label load other nodes of onnx ''' for i in model.graph.node: if (i.op_type == 'Constant'): pass # do nothing if (i.op_type == 'LeakyRelu'): a[str(i.output[0])] = autograd.relu(a[str(i.input[0])]) elif (i.op_type == 'Relu'): a[str(i.output[0])] = autograd.relu(a[str(i.input[0])]) elif (i.op_type == 'Softmax'): a[str(i.output[0])] = autograd.softmax(a[str(i.input[0])]) elif (i.op_type == 'Add'): if(str(i.input[1])[-1] == 'b'): a[str(i.output[0])] = autograd.add_bias(a[str(i.input[0])], a[str(i.input[1])]) else: a[str(i.output[0])] = autograd.add(a[str(i.input[0])],a[str(i.input[1])]) elif (i.op_type == 'MatMul'): a[str(i.output[0])] = autograd.matmul(a[str(i.input[0])], a[str(i.input[1])]) loss = autograd.cross_entropy(a['Y'], target) return loss
def forward(self, x): y = sg_ir.run([x], last_layers=self.last_layers)[0] y = self.append_linear1(y) y = autograd.relu(y) y = self.append_linear2(y) y = autograd.relu(y) y = self.append_linear3(y) y = autograd.relu(y) return y
def forward(x, t): y = conv1(x) y = autograd.relu(y) y = conv2(y) y = autograd.relu(y) y = pooling(y) y = autograd.flatten(y) y = linear(y) loss = autograd.softmax_cross_entropy(y, t) return loss, y
def __call__(self, input): x = self.features(input) x = self.logits(x) x = autograd.relu(x) x = self.linear1(x) x = autograd.relu(x) x = self.linear2(x) return x
def forward(x, t): y = conv1(x) y = autograd.relu(y) y1 = conv21(y) y2 = conv22(y) y = autograd.cat((y1, y2), 1) y = autograd.relu(y) y = autograd.flatten(y) y = linear(y) loss = autograd.softmax_cross_entropy(y, t) return loss, y
def forward(x, t): y = conv1(x) y = autograd.relu(y) y = conv2(y) y = autograd.relu(y) y = autograd.max_pool_2d(y) y = autograd.flatten(y) y = linear(y) y = autograd.soft_max(y) loss = autograd.cross_entropy(y, t) return loss, y
def forward(self, x): y = self.conv1(x) y = autograd.relu(y) y = self.pooling1(y) y = self.conv2(y) y = autograd.relu(y) y = self.pooling2(y) y = autograd.flatten(y) y = self.linear1(y) y = autograd.relu(y) y = self.linear2(y) return y
def forward(self, inputs): x = autograd.matmul(inputs, self.w0) x = autograd.add_bias(x, self.b0) x = autograd.relu(x) x = autograd.matmul(x, self.w1) x = autograd.add_bias(x, self.b1) return x
def forward(x, t): y = conv1(x) y = autograd.relu(y) y = bn1(y) y = pooling1(y) y1 = conv21(y) y2 = conv22(y) y = autograd.cat((y1, y2), 1) y = bn2(y) y = autograd.relu(y) y = bn2(y) y = pooling2(y) y = autograd.flatten(y) y = linear(y) loss = autograd.softmax_cross_entropy(y, t) return loss, y
def forward(self, x): y = self.lstm(x) y = autograd.reshape(y, (y.shape[0], -1)) y = self.l1(y) y = autograd.relu(y) y = self.l2(y) return y
def __call__(self, x): residual = x out = self.conv1(x) out = self.bn1(out) out = autograd.relu(out) out = self.conv2(out) out = self.bn2(out) if self.downsample is not None: residual = self.downsample(x) out = autograd.add(out, residual) out = autograd.relu(out) return out
def __call__(self, x): x = self.conv1(x) x = self.bn1(x) x = autograd.relu(x) x = self.maxpool(x) x = self.layer1(x) x = self.layer2(x) x = self.layer3(x) x = self.layer4(x) x = self.avgpool(x) x = autograd.flatten(x) x = self.fc(x) return x
def singa_to_onnx(niter, use_cpu=False): if use_cpu: print("Using CPU") dev = device.get_default_device() else: print("Using GPU") dev = device.create_cuda_gpu() inputs = Tensor( data=data, device=dev, requires_grad=False, stores_grad=False, name="input", ) target = Tensor( data=label, device=dev, requires_grad=False, stores_grad=False, name="target", ) w0 = Tensor(shape=(2, 3), device=dev, requires_grad=True, stores_grad=True) w0.gaussian(0.0, 0.1) b0 = Tensor(shape=(3,), device=dev, requires_grad=True, stores_grad=True) b0.set_value(0.0) w1 = Tensor(shape=(3, 2), device=dev, requires_grad=True, stores_grad=True) w1.gaussian(0.0, 0.1) b1 = Tensor(shape=(2,), device=dev, requires_grad=True, stores_grad=True) b1.set_value(0.0) sgd = opt.SGD(0.1) # training process for i in range(100): x = autograd.matmul(inputs, w0) x = autograd.add_bias(x, b0) x = autograd.relu(x) x = autograd.matmul(x, w1) x = autograd.add_bias(x, b1) loss = autograd.softmax_cross_entropy(x, target) for p, gp in autograd.backward(loss): sgd.update(p, gp) print("training loss = ", tensor.to_numpy(loss)[0]) sonnx.export([inputs], [x], file_path="mlp.onnx")
def forward(x, t): y = conv1(x) y = autograd.tanh(y) y1 = conv21(y) y2 = conv22(y) y = autograd.cat((y1, y2), 1) y = autograd.sigmoid(y) y = bn(y) y = autograd.relu(y) y = autograd.mul(y, y) y = pooling1(y) y = autograd.sigmoid(y) y = pooling2(y) print(tensor.to_numpy(y).shape) y = autograd.flatten(y) y = linear(y) print(tensor.to_numpy(y).shape) loss = autograd.softmax_cross_entropy(y, t) return loss, y
def run(model, modeldic, layer,inputs): ''' input: input for singa model load other nodes of onnx ''' supportLayer = ['Linear','Conv','MaxPool','AveragePool','BatchNormalization'] #supportLayer = ['Conv', 'MaxPool', 'AveragePool', 'BatchNormalization'] oper=modeldic for counter,i in enumerate(model.graph.input): oper[i.name] = inputs[counter] for i in model.graph.node: if (i.op_type == 'Relu'): oper[str(i.output[0])] = autograd.relu(oper[str(i.input[0])]) elif (i.op_type == 'Softmax'): oper[str(i.output[0])] = autograd.softmax(oper[str(i.input[0])]) elif (i.op_type == 'Add'): oper[str(i.output[0])] = autograd.add(oper[str(i.input[0])], oper[str(i.input[1])]) elif (i.op_type == 'MatMul'): oper[str(i.output[0])] = autograd.matmul(oper[str(i.input[0])], oper[str(i.input[1])]) elif (i.op_type == 'Flatten'): oper[str(i.output[0])] = autograd.flatten(oper[str(i.input[0])]) elif(i.op_type == 'Concat'): oper[str(i.output[0])] = autograd.cat((oper[str(i.input[0])], oper[str(i.input[1])]),int(i.attribute[0].i)) elif(i.op_type == 'Tanh'): oper[str(i.output[0])] = autograd.tanh(oper[str(i.input[0])]) elif (i.op_type == 'Sigmoid'): oper[str(i.output[0])] = autograd.sigmoid(oper[str(i.input[0])]) elif (i.op_type == 'Mul'): oper[str(i.output[0])] = autograd.mul(oper[str(i.input[0])],oper[str(i.input[1])]) elif (i.op_type in supportLayer): oper[str(i.output[0])] = layer[str(i.output[0])](oper[str(i.input[0])]) out =[] for counter,i in enumerate(model.graph.output): out.append(modeldic[i.name]) return out
print("train_label_shape:", label.shape) inputs = Tensor(data=data) target = Tensor(data=label) w0 = Tensor(shape=(2, 3), requires_grad=True, stores_grad=True) w0.gaussian(0.0, 0.1) b0 = Tensor(shape=(1, 3), requires_grad=True, stores_grad=True) b0.set_value(0.0) w1 = Tensor(shape=(3, 2), requires_grad=True, stores_grad=True) w1.gaussian(0.0, 0.1) b1 = Tensor(shape=(1, 2), requires_grad=True, stores_grad=True) b1.set_value(0.0) sgd = optimizer.SGD(0.05) # training process for i in range(1001): x = autograd.matmul(inputs, w0) x = autograd.add_bias(x, b0) x = autograd.relu(x) x = autograd.matmul(x, w1) x = autograd.add_bias(x, b1) x = autograd.softmax(x) loss = autograd.cross_entropy(x, target) for p, gp in autograd.backward(loss): sgd.apply(0, gp, p, "") if i % 100 == 0: print("training loss = ", tensor.to_numpy(loss)[0])
def logits(self, features): x = autograd.relu(features) x = self.globalpooling(x) x = autograd.flatten(x) x = self.fc(x) return x
print('train_label_shape:', label.shape) inputs = Tensor(data=data) target = Tensor(data=label) w0 = Tensor(shape=(2, 3), requires_grad=True, stores_grad=True) w0.gaussian(0.0, 0.1) b0 = Tensor(shape=(1, 3), requires_grad=True, stores_grad=True) b0.set_value(0.0) w1 = Tensor(shape=(3, 2), requires_grad=True, stores_grad=True) w1.gaussian(0.0, 0.1) b1 = Tensor(shape=(1, 2), requires_grad=True, stores_grad=True) b1.set_value(0.0) sgd = optimizer.SGD(0.05) # training process for i in range(1001): x = autograd.matmul(inputs, w0) x = autograd.add_bias(x, b0) x = autograd.relu(x) x = autograd.matmul(x, w1) x = autograd.add_bias(x, b1) x = autograd.softmax(x) loss = autograd.cross_entropy(x, target) for p, gp in autograd.backward(loss): sgd.apply(0, gp, p, '') if (i % 100 == 0): print('training loss = ', tensor.to_numpy(loss)[0])