RuntimeError: The size of tensor a (900) must match the size of tensor b (300) at non-singleton dimension 1

[weixiangzhan]

(python36) pytorch@pytorch:~/cascade-rcnn_Pytorch$ CUDA_VISIBLE_DEVICES=0 python demo.py exp_name --dataset pascal_voc --net detnet59 --checksession 1 --checkepoch 19 --checkpoint 631 --cuda --soft_nms
Called with args:
Namespace(cascade=False, cfg_file='cfgs/detnet59.yml', checkepoch=19, checkpoint=631, checksession=1, class_agnostic=False, cuda=True, dataset='pascal_voc', exp_name='exp_name', image_dir='demo_images/', load_dir='models/', net='detnet59', result_dir='vis_results/', set_cfgs=None, soft_nms=True)
/home/pytorch/cascade-rcnn_Pytorch/lib/model/utils/config.py:405: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.
yaml_cfg = edict(yaml.load(f))
Using config:
{'ANCHOR_RATIOS': [0.5, 1, 2],
'ANCHOR_SCALES': [8, 16, 32],
'CROP_RESIZE_WITH_MAX_POOL': False,
'CUDA': False,
'DATA_DIR': '/home/pytorch/cascade-rcnn_Pytorch/data',
'DEDUP_BOXES': 0.0625,
'DETNET': {'FIXED_BLOCKS': 1, 'MAX_POOL': False},
'EPS': 1e-14,
'EXP_DIR': 'res101',
'FEAT_STRIDE': [16],
'FPN_ANCHOR_SCALES': [32, 64, 128, 256, 512],
'FPN_ANCHOR_STRIDE': 1,
'FPN_FEAT_STRIDES': [4, 8, 16, 32, 64],
'GPU_ID': 0,
'HAS_MASK': True,
'MATLAB': 'matlab',
'MAX_NUM_GT_BOXES': 20,
'MOBILENET': {'DEPTH_MULTIPLIER': 1.0,
'FIXED_LAYERS': 5,
'REGU_DEPTH': False,
'WEIGHT_DECAY': 4e-05},
'PIXEL_MEANS': array([[[0.485, 0.456, 0.406]]]),
'PIXEL_STDS': array([[[0.229, 0.224, 0.225]]]),
'POOLING_MODE': 'align',
'POOLING_SIZE': 14,
'RESNET': {'FIXED_BLOCKS': 1, 'MAX_POOL': False},
'RNG_SEED': 3,
'ROOT_DIR': '/home/pytorch/cascade-rcnn_Pytorch',
'TEST': {'BBOX_REG': True,
'HAS_RPN': True,
'MAX_SIZE': 1000,
'MODE': 'nms',
'NMS': 0.3,
'PROPOSAL_METHOD': 'gt',
'RPN_MIN_SIZE': 16,
'RPN_NMS_THRESH': 0.7,
'RPN_POST_NMS_TOP_N': 300,
'RPN_PRE_NMS_TOP_N': 6000,
'RPN_TOP_N': 5000,
'SCALES': [600],
'SOFT_NMS_METHOD': 1,
'SVM': False},
'TRAIN': {'ASPECT_CROPPING': False,
'ASPECT_GROUPING': False,
'BATCH_SIZE': 128,
'BBOX_INSIDE_WEIGHTS': [1.0, 1.0, 1.0, 1.0],
'BBOX_NORMALIZE_MEANS': [0.0, 0.0, 0.0, 0.0],
'BBOX_NORMALIZE_STDS': [0.1, 0.1, 0.2, 0.2],
'BBOX_NORMALIZE_TARGETS': True,
'BBOX_NORMALIZE_TARGETS_PRECOMPUTED': True,
'BBOX_REG': True,
'BBOX_THRESH': 0.5,
'BG_THRESH_HI': 0.5,
'BG_THRESH_LO': 0.0,
'BIAS_DECAY': False,
'BN_TRAIN': False,
'DISPLAY': 20,
'DOUBLE_BIAS': False,
'FG_FRACTION': 0.25,
'FG_THRESH': 0.5,
'FG_THRESH_2ND': 0.6,
'FG_THRESH_3RD': 0.7,
'GAMMA': 0.1,
'HAS_RPN': True,
'IMS_PER_BATCH': 1,
'LEARNING_RATE': 0.001,
'MAX_SIZE': 1000,
'MOMENTUM': 0.9,
'PROPOSAL_METHOD': 'gt',
'RPN_BATCHSIZE': 256,
'RPN_BBOX_INSIDE_WEIGHTS': [1.0, 1.0, 1.0, 1.0],
'RPN_CLOBBER_POSITIVES': False,
'RPN_FG_FRACTION': 0.5,
'RPN_MIN_SIZE': 8,
'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': 2000,
'RPN_PRE_NMS_TOP_N': 12000,
'SCALES': [600],
'SNAPSHOT_ITERS': 5000,
'SNAPSHOT_KEPT': 3,
'SNAPSHOT_PREFIX': 'res101_faster_rcnn',
'STEPSIZE': [30000],
'SUMMARY_INTERVAL': 180,
'TRIM_HEIGHT': 600,
'TRIM_WIDTH': 600,
'TRUNCATED': False,
'USE_ALL_GT': True,
'USE_FLIPPED': True,
'USE_GT': False,
'WEIGHT_DECAY': 0.0001},
'USE_GPU_NMS': True}
load model successfully!
load checkpoint models//detnet59/pascal_voc/exp_name/fpn_1_19_631.pth
demo.py:199: UserWarning: volatile was removed and now has no effect. Use with torch.no_grad(): instead.
im_data = Variable(im_data, volatile=True)
demo.py:200: UserWarning: volatile was removed and now has no effect. Use with torch.no_grad(): instead.
im_info = Variable(im_info, volatile=True)
demo.py:201: UserWarning: volatile was removed and now has no effect. Use with torch.no_grad(): instead.
num_boxes = Variable(num_boxes, volatile=True)
demo.py:202: UserWarning: volatile was removed and now has no effect. Use with torch.no_grad(): instead.
gt_boxes = Variable(gt_boxes, volatile=True)
Loaded Photo: 5 images.
/home/pytorch/anaconda3/envs/python36/lib/python3.6/site-packages/torch/nn/functional.py:1749: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
"See the documentation of nn.Upsample for details.".format(mode))
/home/pytorch/cascade-rcnn_Pytorch/lib/model/rpn/rpn_fpn.py:79: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
rpn_cls_prob_reshape = F.softmax(rpn_cls_score_reshape)
/home/pytorch/cascade-rcnn_Pytorch/lib/model/fpn/non_cascade/fpn.py:263: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
cls_prob = F.softmax(cls_score)
Traceback (most recent call last):
File "demo.py", line 310, in
pred_boxes = bbox_transform_inv(boxes, box_deltas, 1)
File "/home/pytorch/cascade-rcnn_Pytorch/lib/model/rpn/bbox_transform.py", line 118, in bbox_transform_inv
pred_ctr_x = dx * widths.unsqueeze(2) + ctr_x.unsqueeze(2)
RuntimeError: The size of tensor a (900) must match the size of tensor b (300) at non-singleton dimension 1