7156c7163b046686064d7c9de445041870e672bc,tutorials/1_first.py,,,#,136

Before Change

//////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
// See the python wrapper:

g_boring = a_boring_graph()
graph_sum = readout(g_boring)
print("graph sum before send() and recv() is: ", graph_sum)
super_useful_comp(g_boring)
graph_sum = readout(g_boring)
print("graph sum after send() and recv() is: ", graph_sum)

g_better = an_interesting_graph()
graph_sum = readout(g_better)

After Change

optimizer = torch.optim.Adam(net.parameters(), lr=0.01)
all_logits = []
for epoch in range(30):
    logits = net(G, inputs)
    // we save the logits for visualization later
    all_logits.append(logits.detach())
    logp = F.log_softmax(logits, 1)
    // we only compute loss for labeled nodes
    loss = F.nll_loss(logp[labeled_nodes], labels)

    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

    print("Epoch %d | Loss: %.4f" % (epoch, loss.item()))

//////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
// Since the model produces a 2-dimensional vector for each node, we can
// visualize it very easily.
import matplotlib.animation as animation
import matplotlib.pyplot as plt

def draw(i):

Instances