def saveEncodings(SHAPENET_PATH=os.path.join("G:\\", "Documenti",
"ShapeNetCore.v2"),
cat_filter=["table", "chair", "sofa"],
SUBDIVISIONS=2,
NAME="learning_pred_and_gen_vector_autoencoder_adam_lr_5",
BATCH_SIZE=8,
TMP="C:\\GL\\3DShapeGen\\tmp\\pathslist.pk"):
#
# Instantiate model
#
model = Model(name=NAME, lr=10**-5)
model.initialize(BATCH_SIZE)
model.load()
#
# Load in advance the paths of all the elements
# we need to get the embeddings
#
if os.path.exists(TMP):
with open(TMP, "rb") as f:
paths = pickle.load(f)
else:
paths = [
x for x in dataGenerator(
SHAPENET_PATH, cat_filter=cat_filter, generate_path=True)
]
with open(TMP, "wb") as f:
pickle.dump(paths, f)
#
# batch the elements and for each batch produce a tensor of binvoxes
#
batches = []
for i in range(0, len(paths), BATCH_SIZE):
batches.append(paths[i:i + BATCH_SIZE])
for batch in tqdm(batches):
models_paths = [
os.path.join(x, "models", "model_normalized.solid.binvox")
for x in batch
]
binvoxs = []
for x in models_paths:
if os.path.exists(x):
binvoxs.append(binvoxToNumpy(x))
else:
binvoxs.append(np.zeros(shape=(128, 128, 128)))
binvoxs = tf.convert_to_tensor(binvoxs, dtype=tf.float32)
binvoxs = tf.reshape(binvoxs,
shape=[
binvoxs.shape[0], binvoxs.shape[1],
binvoxs.shape[2], binvoxs.shape[3], 1
])
binvoxs = tf.nn.max_pool3d(binvoxs,
2 * SUBDIVISIONS,
2 * SUBDIVISIONS,
'VALID',
data_format='NDHWC',
name=None)
#
# Produce the embeddings, the embeddings has shape: (bs,embedding_dim)
#
embeddings = model.encode(binvoxs)
#
# parallel write of the elements to disk
#
args = [(path, emb, NAME) for path, emb in zip(batch, embeddings)]
p = Pool(BATCH_SIZE)
p.map(__writeDiskMapFn, args)
epochs = 1000
for i in range(epochs):
optimizer.zero_grad()
output = AE(data_torch)
loss = loss_fn(output, data_torch)
loss.backward()
optimizer.step()
if i % 100 == 0:
print('Epoch {}: {:.4f}'.format(i, loss))
AE.eval()
with torch.no_grad():
data_transformed = AE.encode(data_torch).detach().numpy()
else:
raise Exception('Please specify a valid solver!')
edges2d = []
for e in edge_list:
edges2d.append(data_transformed[[e[0], e[1]]])
# check crosses
crosses = cross(edges2d, edge_list, findall=True)
print('{}: {} crosses'.format(method, len(crosses)))
plt.scatter(data_transformed[:, 0],
data_transformed[:, 1],
c=t,