Faster-rcnn.pytorch: Testing error

[EldorIbragimov]

/usr/bin/python2.7 /home/e/R-CNN/faster-rcnn.pytorch-master/test_net.py
Called with args:
Namespace(batch_size=1, cfg_file='cfgs/res101.yml', checkepoch=1, checkpoint=10021, checksession=1, class_agnostic=False, cuda='cuda', dataset='pascal_voc', large_scale=False, load_dir='/home/e/R-CNN/faster-rcnn.pytorch-master/data/pretrained_model', mGPUs=False, net='res101', parallel_type=0, set_cfgs=None, vis=False)
Using config:
{'ANCHOR_RATIOS': [0.5, 1, 2],
'ANCHOR_SCALES': [8, 16, 32],
'CROP_RESIZE_WITH_MAX_POOL': False,
'CUDA': False,
'DATA_DIR': '/home/e/R-CNN/faster-rcnn.pytorch-master/data',
'DEDUP_BOXES': 0.0625,
'EPS': 1e-14,
'EXP_DIR': 'res101',
'FEAT_STRIDE': [16],
'GPU_ID': 0,
'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([[[102.9801, 115.9465, 122.7717]]]),
'POOLING_MODE': 'align',
'POOLING_SIZE': 7,
'RESNET': {'FIXED_BLOCKS': 1, 'MAX_POOL': False},
'RNG_SEED': 3,
'ROOT_DIR': '/home/e/R-CNN/faster-rcnn.pytorch-master',
'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],
'SVM': False},
'TRAIN': {'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,
'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}
Loaded dataset voc_2007_test for training
Set proposal method: gt
Preparing training data...
voc_2007_test gt roidb loaded from /home/e/R-CNN/faster-rcnn.pytorch-master/data/cache/voc_2007_test_gt_roidb.pkl
done
4952 roidb entries
load checkpoint /home/e/R-CNN/faster-rcnn.pytorch-master/data/pretrained_model/res101/pascal_voc/faster_rcnn_1_1_10021.pth
load model successfully!
/home/e/R-CNN/faster-rcnn.pytorch-master/test_net.py:190: UserWarning: volatile was removed and now has no effect. Use with torch.no_grad(): instead.
im_data = Variable(im_data, volatile=True)
/home/e/R-CNN/faster-rcnn.pytorch-master/test_net.py:191: UserWarning: volatile was removed and now has no effect. Use with torch.no_grad(): instead.
im_info = Variable(im_info, volatile=True)
/home/e/R-CNN/faster-rcnn.pytorch-master/test_net.py:192: UserWarning: volatile was removed and now has no effect. Use with torch.no_grad(): instead.
num_boxes = Variable(num_boxes, volatile=True)
/home/e/R-CNN/faster-rcnn.pytorch-master/test_net.py:193: UserWarning: volatile was removed and now has no effect. Use with torch.no_grad(): instead.
gt_boxes = Variable(gt_boxes, volatile=True)
/home/e/R-CNN/faster-rcnn.pytorch-master/lib/model/rpn/rpn.py:68: 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/e/R-CNN/faster-rcnn.pytorch-master/lib/model/faster_rcnn/faster_rcnn.py:98: 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 "/home/e/R-CNN/faster-rcnn.pytorch-master/test_net.py", line 267, in
pred_boxes /= data[1][0][2]
RuntimeError: Expected object of type torch.cuda.FloatTensor but found type torch.FloatTensor for argument #3 'other'

[Worulz]

@EldorIbragimov
change
pred_boxes /= data[1][0][2]
to
pred_boxes /= data[1][0][2].cuda()

this was my quick fix. I'm not sure if it's correct, but it runs. Can anyone confirm if this is the correct way to patch this error?

[wjx2]

@Worulz
Hi,
When I resume a pretrained model, it get below errors:
Called with args:
Namespace(batch_size=1, checkepoch=20, checkpoint=3557, checkpoint_interval=10000, checksession=1, class_agnostic=False, cuda='--cuda', dataset='pascal_voc', disp_interval=100, large_scale=False, lr=0.0005, lr_decay_gamma=0.1, lr_decay_step=5, mGPUs=False, max_epochs=26, net='vgg16', num_workers=0, optimizer='sgd', resume=True, save_dir='/home/smartdsp/new_home/faster-rcnn.pytorch/models', session=1, start_epoch=1, use_tfboard=False)
Using config:
{'ANCHOR_RATIOS': [0.5, 1, 2],
'ANCHOR_SCALES': [8, 16, 32],
'CROP_RESIZE_WITH_MAX_POOL': False,
'CUDA': False,
'DATA_DIR': '/home/smartdsp/new_home/faster-rcnn.pytorch/data',
'DEDUP_BOXES': 0.0625,
'EPS': 1e-14,
'EXP_DIR': 'vgg16',
'FEAT_STRIDE': [16],
'GPU_ID': 0,
'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([[[102.9801, 115.9465, 122.7717]]]),
'POOLING_MODE': 'align',
'POOLING_SIZE': 7,
'RESNET': {'FIXED_BLOCKS': 1, 'MAX_POOL': False},
'RNG_SEED': 3,
'ROOT_DIR': '/home/smartdsp/new_home/faster-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],
'SVM': False},
'TRAIN': {'ASPECT_GROUPING': False,
'BATCH_SIZE': 256,
'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': 10,
'DOUBLE_BIAS': True,
'FG_FRACTION': 0.25,
'FG_THRESH': 0.5,
'GAMMA': 0.1,
'HAS_RPN': True,
'IMS_PER_BATCH': 1,
'LEARNING_RATE': 0.01,
'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': 0.0005},
'USE_GPU_NMS': True}
Loaded dataset voc_2007_trainval for training
Set proposal method: gt
Appending horizontally-flipped training examples...
voc_2007_trainval gt roidb loaded from /home/smartdsp/new_home/faster-rcnn.pytorch/data/cache/voc_2007_trainval_gt_roidb.pkl
done
Preparing training data...
done
before filtering, there are 2372 images...
after filtering, there are 2372 images...
2372 roidb entries
Loading pretrained weights from data/pretrained_model/vgg16_caffe.pth
loading checkpoint /home/smartdsp/new_home/faster-rcnn.pytorch/models/vgg16/pascal_voc/vgg16_baseline/faster_rcnn_1_20_3557.pth
loaded checkpoint /home/smartdsp/new_home/faster-rcnn.pytorch/models/vgg16/pascal_voc/vgg16_baseline/faster_rcnn_1_20_3557.pth
lib/model/rpn/rpn.py:68: 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)
lib/model/faster_rcnn/faster_rcnn.py:98: 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)
/home/smartdsp/new_home/faster-rcnn.pytorch/trainval_net_finetune.py:330: UserWarning: invalid index of a 0-dim tensor. This will be an error in PyTorch 0.5. Use tensor.item() to convert a 0-dim tensor to a Python number
loss_temp += loss.data[0]
Traceback (most recent call last):

File "", line 1, in
runfile('/home/smartdsp/new_home/faster-rcnn.pytorch/trainval_net_finetune.py', wdir='/home/smartdsp/new_home/faster-rcnn.pytorch')

File "/home/smartdsp/anaconda2/lib/python2.7/site-packages/spyder/utils/site/sitecustomize.py", line 705, in runfile
execfile(filename, namespace)

File "/home/smartdsp/anaconda2/lib/python2.7/site-packages/spyder/utils/site/sitecustomize.py", line 94, in execfile
builtins.execfile(filename, *where)

File "/home/smartdsp/new_home/faster-rcnn.pytorch/trainval_net_finetune.py", line 337, in
optimizer.step()

File "/home/smartdsp/anaconda2/lib/python2.7/site-packages/torch/optim/sgd.py", line 101, in step
buf.mul_(momentum).add_(1 - dampening, d_p)

RuntimeError: Expected object of type torch.FloatTensor but found type torch.cuda.FloatTensor for argument #4 'other'.
I think this error seems similar with this issus, so I post it here.
Can you help me to deal with this error?

[Worulz]

@wjx2 change lines in train and test files

loss_temp += loss.data[0]
to
loss_temp += loss.item()
replacing data[0] with "item()"

do the same to these lines
loss_rpn_cls = rpn_loss_cls.mean().data[0]
loss_rpn_box = rpn_loss_box.mean().data[0]
loss_rcnn_cls = RCNN_loss_cls.mean().data[0]
loss_rcnn_box = RCNN_loss_bbox.mean().data[0]

[wjx2]

@Worulz I change my pytorch version from 0.4.0 to 0.3.0. Everything is OK! Thank you.

[maozezhong]

@wjx2 Hello, I have the same problem. And I changed my pytorch version from 0.4.0 to 0.3.1 as your recommened, my cuda version is 9.1. However, new problem occurs when loading checkpoint:
AttributeError: 'module' object has no attribute '_rebuild_tensor_v2'
Can you help me if you know?
Thanks

[Liu0329]

Why would pytorch 0.4 cause this error ?