I would like to know how to convert between the two versions because it seems the quantization capabilities are mainly for the syms, arg_params, aux_params
tuple style passing, which can be wrapped around modules well, but not gluon models(correct me if I’m wrong).
Here’s a small code snippet that trains a cnn model:
batch_size = 64
num_inputs = 784
num_outputs = 10
data_iter = mx.io.NDArrayIter(x, y, batch_size=batch_size)
num_fc = 512
net = gluon.nn.HybridSequential()
with net.name_scope():
net.add(gluon.nn.Conv2D(channels=20, kernel_size=5, activation='relu'))
net.add(gluon.nn.MaxPool2D(pool_size=2, strides=2))
net.add(gluon.nn.Conv2D(channels=50, kernel_size=5, activation='relu'))
net.add(gluon.nn.MaxPool2D(pool_size=2, strides=2))
net.add(gluon.nn.Flatten())
net.add(gluon.nn.Dense(num_fc, activation="relu"))
net.add(gluon.nn.Dense(num_outputs))
net.hybridize()
# Parameter initialization
net.collect_params().initialize(mx.init.Xavier(magnitude=2.24), ctx=ctx)
trainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': .1})
softmax_cross_entropy = gluon.loss.SoftmaxCrossEntropyLoss()
for i, batch in enumerate(data_iter):
data = batch.data[0].as_in_context(ctx)
label = batch.label[0].as_in_context(ctx)
with autograd.record():
output = net(data)
loss = softmax_cross_entropy(output, label)
loss.backward()
trainer.step(data.shape[0])
If I want to quantize a gluon model, I would try to serialize gluon into disk, and then bring it back out as module. This may cause troubles:
import os
net.export('mxnet')
mod = mx.module.Module.load('mxnet', 0) # 0 epoch
FWIW, I got a warning during the loading step, but was not sure what this was about:
/Users/ray_zhang/anaconda3/envs/idp3/lib/python3.6/site-packages/mxnet/module/base_module.py:54: UserWarning: You created Module with Module(..., label_names=['softmax_label']) but input with name 'softmax_label' is not found in symbol.list_arguments(). Did you mean one of:
data
warnings.warn(msg)
and as per the module API:
mod.bind( data_shapes = data_iter.provide_data,
label_shapes = data_iter.provide_label)
mod.predict(x)
but it does not work upon bind()
, with the following stacktrace:
----------------------------------------------
KeyError Traceback (most recent call last)
<ipython-input-10-f53137bb5e95> in <module>()
1 mod.bind( data_shapes = data_iter.provide_data,
----> 2 label_shapes = data_iter.provide_label)
3 mod.predict(x)
~/anaconda3/envs/idp3/lib/python3.6/site-packages/mxnet/module/module.py in bind(self, data_shapes, label_shapes, for_training, inputs_need_grad, force_rebind, shared_module, grad_req)
434 fixed_param_names=self._fixed_param_names,
435 grad_req=grad_req, group2ctxs=self._group2ctxs,
--> 436 state_names=self._state_names)
437 self._total_exec_bytes = self._exec_group._total_exec_bytes
438 if shared_module is not None:
~/anaconda3/envs/idp3/lib/python3.6/site-packages/mxnet/module/executor_group.py in __init__(self, symbol, contexts, workload, data_shapes, label_shapes, param_names, for_training, inputs_need_grad, shared_group, logger, fixed_param_names, grad_req, state_names, group2ctxs)
281
282 eprint(sys._getframe().f_lineno, data_shapes, label_shapes)
--> 283 self.bind_exec(data_shapes, label_shapes, shared_group)
284
285 def decide_slices(self, data_shapes):
~/anaconda3/envs/idp3/lib/python3.6/site-packages/mxnet/module/executor_group.py in bind_exec(self, data_shapes, label_shapes, shared_group, reshape)
388 if label_shapes is not None:
389 self.label_names = [i.name for i in self.label_shapes]
--> 390 self._collect_arrays()
391
392 def reshape(self, data_shapes, label_shapes):
~/anaconda3/envs/idp3/lib/python3.6/site-packages/mxnet/module/executor_group.py in _collect_arrays(self)
324 self.label_arrays = [[(self.slices[i], e.arg_dict[name])
325 for i, e in enumerate(self.execs)]
--> 326 for name, _ in self.label_shapes]
327 else:
328 self.label_arrays = None
~/anaconda3/envs/idp3/lib/python3.6/site-packages/mxnet/module/executor_group.py in <listcomp>(.0)
324 self.label_arrays = [[(self.slices[i], e.arg_dict[name])
325 for i, e in enumerate(self.execs)]
--> 326 for name, _ in self.label_shapes]
327 else:
328 self.label_arrays = None
~/anaconda3/envs/idp3/lib/python3.6/site-packages/mxnet/module/executor_group.py in <listcomp>(.0)
323 eprint(323, e.arg_dict.keys())
324 self.label_arrays = [[(self.slices[i], e.arg_dict[name])
--> 325 for i, e in enumerate(self.execs)]
326 for name, _ in self.label_shapes]
327 else:
KeyError: 'softmax_label'
Which is complaining about me missing that label in my e.arg_dict
.
I printed out e.arg_dict
:
dict_keys(['data', 'hybridsequential1_conv0_weight', 'hybridsequential1_conv0_bias', 'hybridsequential1_conv1_weight', 'hybridsequential1_conv1_bias', 'hybridsequential1_dense0_weight', 'hybridsequential1_dense0_bias', 'hybridsequential1_dense1_weight', 'hybridsequential1_dense1_bias'])
And indeed, softmax_label
is not in there. Where is this label coming from and how can I convert gluon to module correctly?