def train_net(args, ctx):
logger.auto_set_dir()
sym_instance = resnet101_deeplab_new()
sym = sym_instance.get_symbol(NUM_CLASSES, is_train=True,memonger=False)
#digraph = mx.viz.plot_network(sym, save_format='pdf')
#digraph.render()
# setup multi-gpu
gpu_nums = len(ctx)
input_batch_size = args.batch_size * gpu_nums
train_data = get_data("train", DATA_DIR, LIST_DIR, len(ctx))
test_data = get_data("val", DATA_DIR, LIST_DIR, len(ctx))
# infer max shape
max_scale = [args.crop_size]
max_data_shape = [('data', (args.batch_size, 3, max([v[0] for v in max_scale]), max([v[1] for v in max_scale])))]
max_label_shape = [('label', (args.batch_size, 1, max([v[0] for v in max_scale]), max([v[1] for v in max_scale])))]
# infer shape
data_shape_dict = {'data':(args.batch_size, 3, args.crop_size[0],args.crop_size[1])
,'label':(args.batch_size, 1, args.crop_size[0],args.crop_size[1])}
pprint.pprint(data_shape_dict)
sym_instance.infer_shape(data_shape_dict)
eval_sym_instance = resnet101_deeplab_new()
# load and initialize params
epoch_string = args.load.rsplit("-",2)[1]
begin_epoch = 1
if not args.scratch:
begin_epoch = int(epoch_string)
logger.info('continue training from {}'.format(begin_epoch))
arg_params, aux_params = load_init_param(args.load, convert=True)
else:
logger.info(args.load)
arg_params, aux_params = load_init_param(args.load, convert=True)
sym_instance.init_weights(arg_params, aux_params)
# check parameter shapes
sym_instance.check_parameter_shapes(arg_params, aux_params, data_shape_dict)
data_names = ['data']
label_names = ['label']
mod = MutableModule(sym, data_names=data_names, label_names=label_names,context=ctx, max_data_shapes=[max_data_shape for _ in xrange(gpu_nums)],
max_label_shapes=[max_label_shape for _ in xrange(gpu_nums)], fixed_param_prefix=fixed_param_prefix)
# decide training params
# metric
fcn_loss_metric = metric.FCNLogLossMetric(args.frequent)
eval_metrics = mx.metric.CompositeEvalMetric()
for child_metric in [fcn_loss_metric]:
eval_metrics.add(child_metric)
# callback
batch_end_callbacks = [callback.Speedometer(input_batch_size, frequent=args.frequent)]
#batch_end_callbacks = [mx.callback.ProgressBar(total=train_data.size/train_data.batch_size)]
epoch_end_callbacks = \
[mx.callback.module_checkpoint(mod, os.path.join(logger.get_logger_dir(),"mxnetgo"), period=1, save_optimizer_states=True),
]
lr_scheduler = StepScheduler(train_data.size()*EPOCH_SCALE,lr_step_list)
# optimizer
optimizer_params = {
'wd': 0.0005,
'learning_rate': init_lr,
'lr_scheduler': lr_scheduler,
'rescale_grad': 1.0,
'clip_gradient': None}
logger.info("epoch scale = {}".format(EPOCH_SCALE))
mod.fit(train_data=train_data, args = args, eval_sym_instance=eval_sym_instance, eval_data=test_data, eval_metric=eval_metrics, epoch_end_callback=epoch_end_callbacks,
batch_end_callback=batch_end_callbacks, kvstore=kvstore,
optimizer='adam', optimizer_params=optimizer_params,
arg_params=arg_params, aux_params=aux_params, begin_epoch=begin_epoch, num_epoch=end_epoch,epoch_scale=EPOCH_SCALE, validation_on_last=validation_on_last)
def do_validation(ctx):
#logger.auto_set_dir()
test_data = get_data("val", DATA_DIR, LIST_DIR, len(ctx))
ctx = [mx.gpu(int(i)) for i in args.gpu.split(',')]
sym_instance = resnet101_deeplab_new()
val_provide_data = [[("data", (1, 3, tile_height, tile_width))]]
val_provide_label = [[("softmax_label", (1, 1, tile_height, tile_width))]]
data_shape_dict = {
'data': (1, 3, tile_height, tile_width),
'softmax_label': (1, 1, tile_height, tile_width)
}
eval_sym = sym_instance.get_symbol(NUM_CLASSES, is_train=False)
sym_instance.infer_shape(data_shape_dict)
arg_params, aux_params = load_init_param(args.load, process=True)
sym_instance.check_parameter_shapes(arg_params,
aux_params,
data_shape_dict,
is_train=False)
data_names = ['data']
label_names = ['softmax_label']
# create predictor
predictor = Predictor(eval_sym,
data_names,
label_names,
context=ctx,
provide_data=val_provide_data,
provide_label=val_provide_label,
arg_params=arg_params,
aux_params=aux_params)
logger.info("begin prediction.. evaluation size: {}x{}".format(
tile_width, tile_height))
if args.vis:
from mxnetgo.myutils.fs import mkdir_p
vis_dir = os.path.join(logger.get_logger_dir(), "vis")
mkdir_p(vis_dir)
stats = MIoUStatistics(NUM_CLASSES)
test_data.reset_state()
nbatch = 0
for data, label in tqdm(test_data.get_data()):
output_all = predict_scaler(data,
predictor,
scales=[0.9, 1.0, 1.1],
classes=NUM_CLASSES,
tile_size=(tile_height, tile_width),
is_densecrf=False,
nbatch=nbatch,
val_provide_data=val_provide_data,
val_provide_label=val_provide_label)
output_all = np.argmax(output_all, axis=0)
label = np.squeeze(label)
if args.vis:
cv2.imwrite(os.path.join(vis_dir, "{}.jpg".format(nbatch)),
visualize_label(output_all))
stats.feed(output_all, label) # very time-consuming
nbatch += 1
logger.info("mIoU: {}, meanAcc: {}, acc: {} ".format(
stats.mIoU, stats.mean_accuracy, stats.accuracy))