def test_base_model_config(self):
config_dict = {
'graph': {
'input_layers': ['image'],
'output_layers': ['dense_0'],
'layers': [
{
'Conv2D': {
'filters': 64,
'strides': [1, 1],
'kernel_size': [2, 2],
'activation': 'relu',
'name': 'convolution_1',
}
},
{'Dense': {'units': 17, 'name': 'dense_0'}}
]
},
'loss': SoftmaxCrossEntropyConfig(input_layer=['image', 0, 0],
output_layer=['dense_0', 0, 0]).to_schema(),
'optimizer': AdamConfig(learning_rate=0.01).to_schema(),
'metrics': [
AccuracyConfig(input_layer=['image', 0, 0],
output_layer=['dense_0', 0, 0]).to_schema(),
PrecisionConfig(input_layer=['image', 0, 0],
output_layer=['dense_0', 0, 0]).to_schema(),
],
'summaries': ['loss', 'gradients'],
'clip_gradients': 0.5,
'clip_embed_gradients': 0.,
'name': 'model'}
config = BaseModelConfig.from_dict(config_dict)
config_to_dict = config.to_dict()
self.assert_equal_models(config_to_dict, config_dict)
def model_fn(features, labels, params, mode, config):
model = plx.models.Classifier(
mode=mode,
graph_fn=graph_fn,
loss=SigmoidCrossEntropyConfig(),
optimizer=AdamConfig(
learning_rate=0.007, decay_type='exponential_decay', decay_rate=0.1),
metrics=[
AccuracyConfig(),
PrecisionConfig()
],
summaries='all',
one_hot_encode=True,
n_classes=10)
return model(features=features, labels=labels, params=params, config=config)