testing never finish about fcis HOT 9 OPEN

It seems that the problem is in lib/dataset/coco.py line 371: results = pool.map(coco_results_one_category_kernel, data_pack)

from fcis.

My solution right now is folllowing :
coco.py line 371 :
replace
pool = mp.Pool(mp.cpu_count())
results = pool.map(coco_results_one_category_kernel, data_pack)
pool.close()
pool.join()

with
results = []
for i in range(len(data_pack)):
results.append(coco_results_one_category_kernel(data_pack[i]))

Thank you for your amazing code

from fcis.

Hi, @gaopeng-eugene , were you running it in debug mode?

from fcis.

no

from fcis.

@gaopeng-eugene Hi, I also encounter the same problem with you, but after I change the code as you provided, the testing process becomes very very slow....Extremely slow...And I still don't know why the original code never finish testing.

from fcis.

Of course, my code running in single process while the original code running in multiple process. My guess is there is deadlock in the original code.

from fcis.

Replacing "import multiprocessing" in coco.py by "import multiprocessing.dummy" fixed the problem.

from fcis.

I don't know what the reason is not going down, can someone help me to have a look? Thank you very much!

xbw@xbw-P65xRP:~/FCIS$ python experiments/fcis/fcis_end2end_train_test.py --cfg experiments/fcis/cfgs/resnet_v1_101_coco_fcis_end2end_ohem.yaml
Called with argument: Namespace(cfg='experiments/fcis/cfgs/resnet_v1_101_coco_fcis_end2end_ohem.yaml', frequent=100)
{'BINARY_THRESH': 0.4,
'CLASS_AGNOSTIC': True,
'MASK_SIZE': 21,
'MXNET_VERSION': 'mxnet',
'SCALES': [(600, 1000)],
'TEST': {'BATCH_IMAGES': 1,
'CXX_PROPOSAL': False,
'HAS_RPN': True,
'ITER': 2,
'MASK_MERGE_THRESH': 0.5,
'MIN_DROP_SIZE': 2,
'NMS': 0.3,
'PROPOSAL_MIN_SIZE': 2,
'PROPOSAL_NMS_THRESH': 0.7,
'PROPOSAL_POST_NMS_TOP_N': 2000,
'PROPOSAL_PRE_NMS_TOP_N': 20000,
'RPN_MIN_SIZE': 2,
'RPN_NMS_THRESH': 0.7,
'RPN_POST_NMS_TOP_N': 300,
'RPN_PRE_NMS_TOP_N': 6000,
'USE_GPU_MASK_MERGE': True,
'USE_MASK_MERGE': True,
'test_epoch': 8},
'TRAIN': {'ASPECT_GROUPING': True,
'BATCH_IMAGES': 1,
'BATCH_ROIS': -1,
'BATCH_ROIS_OHEM': 128,
'BBOX_MEANS': [0.0, 0.0, 0.0, 0.0],
'BBOX_NORMALIZATION_PRECOMPUTED': True,
'BBOX_REGRESSION_THRESH': 0.5,
'BBOX_STDS': [0.2, 0.2, 0.5, 0.5],
'BBOX_WEIGHTS': array([ 1., 1., 1., 1.]),
'BG_THRESH_HI': 0.5,
'BG_THRESH_LO': 0,
'BINARY_THRESH': 0.4,
'CONVNEW3': True,
'CXX_PROPOSAL': False,
'ENABLE_OHEM': True,
'END2END': True,
'FG_FRACTION': 0.25,
'FG_THRESH': 0.5,
'FLIP': True,
'GAP_SELECT_FROM_ALL': False,
'IGNORE_GAP': False,
'LOSS_WEIGHT': [1.0, 10.0, 1.0],
'RESUME': False,
'RPN_ALLOWED_BORDER': 0,
'RPN_BATCH_SIZE': 256,
'RPN_BBOX_WEIGHTS': [1.0, 1.0, 1.0, 1.0],
'RPN_CLOBBER_POSITIVES': False,
'RPN_FG_FRACTION': 0.5,
'RPN_MIN_SIZE': 2,
'RPN_NEGATIVE_OVERLAP': 0.3,
'RPN_NMS_THRESH': 0.7,
'RPN_POSITIVE_OVERLAP': 0.7,
'RPN_POSITIVE_WEIGHT': -1.0,
'RPN_POST_NMS_TOP_N': 300,
'RPN_PRE_NMS_TOP_N': 6000,
'SHUFFLE': True,
'begin_epoch': 0,
'end_epoch': 8,
'lr': 0.0005,
'lr_step': '5.33',
'model_prefix': 'e2e',
'momentum': 0.9,
'warmup': True,
'warmup_lr': 5e-05,
'warmup_step': 250,
'wd': 0.0005},
'dataset': {'NUM_CLASSES': 81,
'dataset': 'coco',
'dataset_path': './data/coco',
'image_set': 'train2014+valminusminival2014',
'proposal': 'rpn',
'root_path': './data',
'test_image_set': 'test-dev2015'},
'default': {'frequent': 100, 'kvstore': 'device'},
'gpus': '0,1,2,3,4,5,6,7',
'network': {'ANCHOR_RATIOS': [0.5, 1, 2],
'ANCHOR_SCALES': [4, 8, 16, 32],
'FIXED_PARAMS': ['conv1',
'bn_conv1',
'res2',
'bn2',
'gamma',
'beta'],
'FIXED_PARAMS_SHARED': ['conv1',
'bn_conv1',
'res2',
'bn2',
'res3',
'bn3',
'res4',
'bn4',
'gamma',
'beta'],
'IMAGE_STRIDE': 0,
'NUM_ANCHORS': 12,
'PIXEL_MEANS': array([ 103.06, 115.9 , 123.15]),
'RCNN_FEAT_STRIDE': 16,
'RPN_FEAT_STRIDE': 16,
'pretrained': './model/pretrained_model/resnet_v1_101',
'pretrained_epoch': 0},
'output_path': './output/fcis/coco',
'symbol': 'resnet_v1_101_fcis'}
loading annotations into memory...
Done (t=12.97s)
creating index...
index created!
num_images 82783
prepare gt_sdsdb using 30.2918889523 seconds

from fcis.

just wait ,it will take a long time to prepare image for train.

from fcis.