class ModelParam:
train_symbol = train_sym
test_symbol = test_sym
rpn_test_symbol = rpn_test_sym
from_scratch = False
random = True
memonger = False
memonger_until = "stage3_unit21_plus"
process_weight = lambda sym, arg, aux: \
add_anchor_to_arg(
sym, arg, aux, RpnParam.anchor_generate.max_side,
RpnParam.anchor_generate.stride,RpnParam.anchor_generate.scale,
RpnParam.anchor_generate.ratio)
class pretrain:
prefix = "pretrain_model/resnet%s_v1b" % BackboneParam.depth
epoch = 0
fixed_param = ["conv0", "stage1", "gamma", "beta"]
class QuantizeTrainingParam:
quantize_flag = False
# quantized_op = ("Convolution", "FullyConnected", "Deconvolution","Concat", "Pooling", "add_n", "elemwise_add")
quantized_op = ("Convolution", "FullyConnected", "Deconvolution")
class WeightQuantizeParam:
delay_quant = 0
ema_decay = 0.99
grad_mode = "ste"
is_weight = True
is_weight_perchannel = False
quant_mode = "minmax"
class ActQuantizeParam:
delay_quant = 0
ema_decay = 0.99
grad_mode = "ste"
is_weight = False
is_weight_perchannel = False
quant_mode = "minmax"
def process_weight(sym, arg, aux):
for stride in RpnParam.anchor_generate.stride:
add_anchor_to_arg(sym, arg, aux,
RpnParam.anchor_generate.max_side, stride,
RpnParam.anchor_generate.scale,
RpnParam.anchor_generate.ratio)
