def test_param_intersection(self):
'''
Test that passes intersecting parameters and input/output blobs
'''
m = self._create_model()
with self.assertRaises(Exception):
pe.PredictorExportMeta(
predict_net=m.net,
parameters=m.params,
inputs=["data"] + m.params,
outputs=["y"],
shapes={
"y": (1, 10),
"data": (1, 5)
},
)
with self.assertRaises(Exception):
pe.PredictorExportMeta(
predict_net=m.net,
parameters=m.params,
inputs=["data"],
outputs=["y"] + m.params,
shapes={
"y": (1, 10),
"data": (1, 5)
},
)
def SaveModel(args, train_model, epoch):
prefix = "[]_{}".format(train_model._device_prefix, train_model._devices[0])
predictor_export_meta = pred_exp.PredictorExportMeta(
predict_net=train_model.net.Proto(),
parameters=data_parallel_model.GetCheckpointParams(train_model),
inputs=[prefix + "/data"],
outputs=[prefix + "/softmax"],
shapes={
prefix + "/softmax": (1, args.num_labels),
prefix + "/data": (args.num_channels, args.image_size, args.image_size)
}
)
# save the train_model for the current epoch
model_path = "%s/%s_%d.mdl" % (
args.file_store_path,
args.save_model_name,
epoch,
)
# set db_type to be "minidb" instead of "log_file_db", which breaks
# the serialization in save_to_db. Need to switch back to log_file_db
# after migration
pred_exp.save_to_db(
db_type="minidb",
db_destination=model_path,
predictor_export_meta=predictor_export_meta,
)
def test_meta_net_def_net_runs(self):
for param, value in self.params.items():
workspace.FeedBlob(param, value)
extra_init_net = core.Net('extra_init')
extra_init_net.ConstantFill('data', 'data', value=1.0)
pem = pe.PredictorExportMeta(
predict_net=self.predictor_export_meta.predict_net,
parameters=self.predictor_export_meta.parameters,
inputs=self.predictor_export_meta.inputs,
outputs=self.predictor_export_meta.outputs,
shapes=self.predictor_export_meta.shapes,
extra_init_net=extra_init_net,
)
db_type = 'minidb'
db_file = tempfile.NamedTemporaryFile(delete=False,
suffix=".{}".format(db_type))
pe.save_to_db(db_type=db_type,
db_destination=db_file.name,
predictor_export_meta=pem)
workspace.ResetWorkspace()
meta_net_def = pe.load_from_db(
db_type=db_type,
filename=db_file.name,
)
self.assertTrue("data" not in workspace.Blobs())
self.assertTrue("y" not in workspace.Blobs())
init_net = pred_utils.GetNet(meta_net_def, pc.PREDICT_INIT_NET_TYPE)
# 0-fills externalblobs blobs and runs extra_init_net
workspace.RunNetOnce(init_net)
self.assertTrue("data" in workspace.Blobs())
self.assertTrue("y" in workspace.Blobs())
print(workspace.FetchBlob("data"))
np.testing.assert_array_equal(workspace.FetchBlob("data"),
np.ones(shape=(1, 5)))
np.testing.assert_array_equal(workspace.FetchBlob("y"),
np.zeros(shape=(1, 10)))
# Load parameters from DB
global_init_net = pred_utils.GetNet(meta_net_def,
pc.GLOBAL_INIT_NET_TYPE)
workspace.RunNetOnce(global_init_net)
# Run the net with a reshaped input and verify we are
# producing good numbers (with our custom implementation)
workspace.FeedBlob("data", np.random.randn(2, 5).astype(np.float32))
predict_net = pred_utils.GetNet(meta_net_def, pc.PREDICT_NET_TYPE)
workspace.RunNetOnce(predict_net)
np.testing.assert_array_almost_equal(
workspace.FetchBlob("y"),
workspace.FetchBlob("data").dot(self.params["y_w"].T) +
self.params["y_b"])
def SaveModel(args, train_model, epoch):
prefix = "gpu_{}".format(train_model._devices[0])
predictor_export_meta = pred_exp.PredictorExportMeta(
predict_net=train_model.net.Proto(),
parameters=GetCheckpointParams(train_model),
inputs=[prefix + "/data"],
outputs=[prefix + "/softmax"],
shapes={
prefix + "/softmax": (1, args.num_labels),
prefix + "/data":
(args.num_channels,
args.clip_length_of if args.input_type else args.clip_length_rgb,
args.crop_size, args.crop_size)
})
# save the train_model for the current epoch
model_path = "%s/%s_%d.mdl" % (
args.file_store_path,
args.save_model_name,
epoch,
)
# save the model
pred_exp.save_to_db(
db_type='minidb',
db_destination=model_path,
predictor_export_meta=predictor_export_meta,
)
def _export_to_logfiledb(args,
net,
init_net,
inputs,
out_file,
extra_out_tensors=None):
out_tensors = list(net.Proto().external_output)
if extra_out_tensors is not None:
out_tensors += extra_out_tensors
params = list(set(net.Proto().external_input) - set(inputs))
net_type = None
predictor_export_meta = predictor_exporter.PredictorExportMeta(
predict_net=net,
parameters=params,
inputs=inputs,
outputs=out_tensors,
net_type=net_type,
)
logger.info("Exporting Caffe2 model to {}".format(out_file))
predictor_exporter.save_to_db(
db_type="log_file_db",
db_destination=out_file,
predictor_export_meta=predictor_export_meta,
)
def save_model(deploy_model):
"""Write layer weights to files. These are used in Chapter 2.
Also, write model to file.
"""
del_create_dir(WEIGHTS_DIR)
# Iterate weights of model
for i, blob in enumerate(deploy_model.params):
blob_vals = workspace.FetchBlob(blob)
wfpath = "{}/{}.npy".format(WEIGHTS_DIR, str(i))
# Write weights to file.
# These are the weights we imported to our model in Chapter 2.
print("Writing weights file:", wfpath)
with open(wfpath, "w") as ofile:
np.save(ofile, blob_vals, allow_pickle=False)
# Create model for export.
# Specify input and output blobs.
pe_meta = pe.PredictorExportMeta(
predict_net=deploy_model.net.Proto(),
parameters=[str(b) for b in deploy_model.params],
inputs=["input_images"],
outputs=["softmax"],
)
# Save model to file in minidb format.
del_create_dir(MODEL_DIR)
pe.save_to_db("minidb", os.path.join(MODEL_DIR, "mnist_model.minidb"),
pe_meta)
print("Deploy model written to: " + MODEL_DIR + "/mnist_model.minidb")
def save_caffe2_rep_to_db(
caffe2_backend_rep,
output_path,
input_names,
output_names,
num_workers,
):
# netdef external_input includes internally produced blobs
actual_external_inputs = set()
produced = set()
for operator in caffe2_backend_rep.predict_net.op:
for blob in operator.input:
if blob not in produced:
actual_external_inputs.add(blob)
for blob in operator.output:
produced.add(blob)
for blob in output_names:
if blob not in produced:
actual_external_inputs.add(blob)
param_names = [
blob for blob in actual_external_inputs
if blob not in input_names
]
init_net = core.Net(caffe2_backend_rep.init_net)
predict_net = core.Net(caffe2_backend_rep.predict_net)
# predictor_exporter requires disjoint params, inputs and outputs
for i, param in enumerate(param_names):
if param in output_names:
saved_name = param + '_PARAM'
init_net.Copy(param, saved_name)
predict_net.Copy(saved_name, param)
param_names[i] = saved_name
output_shapes = {}
for blob in output_names:
output_shapes[blob] = (0,)
# Required because of https://github.com/pytorch/pytorch/pull/6456/files
with caffe2_backend_rep.workspace._ctx:
workspace.RunNetOnce(init_net)
predictor_export_meta = predictor_exporter.PredictorExportMeta(
predict_net=predict_net,
parameters=param_names,
inputs=input_names,
outputs=output_names,
shapes=output_shapes,
net_type='dag',
num_workers=num_workers,
)
predictor_exporter.save_to_db(
db_type='minidb',
db_destination=output_path,
predictor_export_meta=predictor_export_meta,
)
logger.info('Caffe2 predictor net saved as: {}'.format(output_path))
def test_meta_constructor(self):
'''
Test that passing net itself instead of proto works
'''
m = self._create_model()
pe.PredictorExportMeta(
predict_net=m.net,
parameters=m.params,
inputs=["data"],
outputs=["y"],
shapes={"y": (1, 10), "data": (1, 5)},
)
def export_nets_to_predictor_file(c2_prepared,
input_names,
output_names,
predictor_path,
extra_params=None):
# netdef external_input includes internally produced blobs
actual_external_inputs = set()
produced = set()
for operator in c2_prepared.predict_net.op:
for blob in operator.input:
if blob not in produced:
actual_external_inputs.add(blob)
for blob in operator.output:
produced.add(blob)
for blob in output_names:
if blob not in produced:
actual_external_inputs.add(blob)
param_names = [
blob for blob in actual_external_inputs
if blob not in input_names and blob not in output_names
]
if extra_params is not None:
param_names += extra_params
init_net = core.Net(c2_prepared.init_net)
predict_net = core.Net(c2_prepared.predict_net)
# Required because of https://github.com/pytorch/pytorch/pull/6456/files
with c2_prepared.workspace._ctx:
workspace.RunNetOnce(init_net)
predictor_export_meta = pe.PredictorExportMeta(
predict_net=predict_net,
parameters=param_names,
inputs=input_names,
outputs=output_names,
shapes={x: ()
for x in input_names + output_names},
net_type="simple",
)
pe.save_to_db(
db_type=CAFFE2_DB_TYPE,
db_destination=predictor_path,
predictor_export_meta=predictor_export_meta,
)
def setUp(self):
np.random.seed(1)
m = self._create_model()
self.predictor_export_meta = pe.PredictorExportMeta(
predict_net=m.net.Proto(),
parameters=[str(b) for b in m.params],
inputs=["data"],
outputs=["y"],
shapes={"y": (1, 10), "data": (1, 5)},
)
workspace.RunNetOnce(m.param_init_net)
self.params = {
param: workspace.FetchBlob(param)
for param in self.predictor_export_meta.parameters}
# Reset the workspace, to ensure net creation proceeds as expected.
workspace.ResetWorkspace()
def SaveModel(train_model, save_dir, epoch):
predictor_export_meta = pred_exp.PredictorExportMeta(
predict_net=train_model.net.Proto(),
parameters=GetCheckpointParams(train_model),
inputs=['data_uint8'],
outputs=['softmax'],
shapes={
'data': {1, 9600},
'softmax': {1, 40}
})
model_path = '%s/%s_%d.mdl' % (
save_dir,
train_model.net.Proto().name,
epoch,
)
pred_exp.save_to_db(
db_type='minidb',
db_destination=model_path,
predictor_export_meta=predictor_export_meta,
)
def test_load_device_scope(self):
for param, value in self.params.items():
workspace.FeedBlob(param, value)
pem = pe.PredictorExportMeta(
predict_net=self.predictor_export_meta.predict_net,
parameters=self.predictor_export_meta.parameters,
inputs=self.predictor_export_meta.inputs,
outputs=self.predictor_export_meta.outputs,
shapes=self.predictor_export_meta.shapes,
net_type='dag',
)
db_type = 'minidb'
db_file = tempfile.NamedTemporaryFile(delete=False,
suffix=".{}".format(db_type))
pe.save_to_db(db_type=db_type,
db_destination=db_file.name,
predictor_export_meta=pem)
workspace.ResetWorkspace()
with core.DeviceScope(core.DeviceOption(caffe2_pb2.CPU, 1)):
meta_net_def = pe.load_from_db(
db_type=db_type,
filename=db_file.name,
)
init_net = core.Net(
pred_utils.GetNet(meta_net_def, pc.GLOBAL_INIT_NET_TYPE))
predict_init_net = core.Net(
pred_utils.GetNet(meta_net_def, pc.PREDICT_INIT_NET_TYPE))
# check device options
for op in list(init_net.Proto().op) + list(
predict_init_net.Proto().op):
self.assertEqual(1, op.device_option.device_id)
self.assertEqual(caffe2_pb2.CPU, op.device_option.device_type)
for i in range(total_iters):
workspace.RunNet(train_model.net)
accuracy[i] = workspace.blobs["accuracy"]
loss[i] = workspace.blobs['loss']
if i % 25 == 0:
print("Iter: {}, loss: {}, accuracy: {}".format(
i, loss[i], accuracy[i]))
plt.plot(loss, 'b')
plt.plot(accuracy, 'r')
plt.title("Summary of Training Run")
plt.xlabel("Iteration")
plt.legend(("Loss", "Accuracy"), loc="upper right")
plt.show()
pe_meta = pe.PredictorExportMeta(
predict_net=deploy_model.net.Proto(),
parameters=[str(b) for b in deploy_model.params],
inputs=["data"],
outputs=["softmax"],
)
pe.save_to_db("minidb", os.path.join(root_folder, "mnist_model.minidb"),
pe_meta)
print("Deploy model saved to:" + root_folder + "/mnist_model.minidb")
blob = workspace.FetchBlob("data")
plt.figure()
plt.title("Batch of Testing Data")
_ = visualize.NCHW.ShowMultiple(blob)
workspace.ResetWorkspace(root_folder)
print("The blobs in the workspace after reset: {}".format(workspace.Blobs()))
predict_net = pe.prepare_prediction_net(
os.path.join(root_folder, "mnist_model.minidb"), "minidb")
