RuntimeError: Error(s) in loading state_dict for RFBNet: size mismatch for conf.0.weight: copying a param of torch.Size([126, 512, 3, 3]) from checkpoint, where the shape is torch.Size([66, 512, 3, 3]) in current model. size mismatch for conf.0.bias: copying a param of torch.Size([126]) from checkpoint, where the shape is torch.Size([66]) in current model. size mismatch for conf.1.weight: copying a param of torch.Size([126, 1024, 3, 3]) from checkpoint, where the shape is torch.Size([66, 1024, 3, 3]) in current model. size mismatch for conf.1.bias: copying a param of torch.Size([126]) from checkpoint, where the shape is torch.Size([66]) in current model. size mismatch for conf.2.weight: copying a param of torch.Size([126, 512, 3, 3]) from checkpoint, where the shape is torch.Size([66, 512, 3, 3]) in current model. size mismatch for conf.2.bias: copying a param of torch.Size([126]) from checkpoint, where the shape is torch.Size([66]) in current model. size mismatch for conf.3.weight: copying a param of torch.Size([126, 256, 3, 3]) from checkpoint, where the shape is torch.Size([66, 256, 3, 3]) in current model. size mismatch for conf.3.bias: copying a param of torch.Size([126]) from checkpoint, where the shape is torch.Size([66]) in current model. size mismatch for conf.4.weight: copying a param of torch.Size([84, 256, 3, 3]) from checkpoint, where the shape is torch.Size([44, 256, 3, 3]) in current model. size mismatch for conf.4.bias: copying a param of torch.Size([84]) from checkpoint, where the shape is torch.Size([44]) in current model. size mismatch for conf.5.weight: copying a param of torch.Size([84, 256, 3, 3]) from checkpoint, where the shape is torch.Size([44, 256, 3, 3]) in current model. size mismatch for conf.5.bias: copying a param of torch.Size([84]) from checkpoint, where the shape is torch.Size([44]) in current model.

我并不清楚前面的checkpoint的torch.size的126/84这个是在哪修改的

test_RFB.py runs OK when cuda sets as True. However, when I set cuda as False in test_RFB.py and got the following error:

Traceback (most recent call last): File "test_RFB.py", line 193, in top_k, thresh=0.01) File "demo_RFB.py", line 91, in test_net out = net(x) # forward pass File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/module.py", line 357, in call result = self.forward(*input, **kwargs) File "/home/topspinn/2TB/src/RFBNet/models/RFB_Net_mobile.py", line 185, in forward x = self.basek File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/module.py", line 357, in call result = self.forward(*input, **kwargs) File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/container.py", line 72, in forward input = module(input) File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/module.py", line 357, in call result = self.forward(*input, **kwargs) File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/conv.py", line 282, in forward self.padding, self.dilation, self.groups) RuntimeError: Expected object of type Variable[torch.FloatTensor] but found type Variable[torch.cuda.FloatTensor] for argument #1 'weight'

Traceback (most recent call last): File "test_RFB.py", line 49, in from models.RFB_Net_E_vgg import build_net File "/media/media_share/linkfile/RFBNet/models/RFB_Net_E_vgg.py", line 405 return RFBNet(phase, size, *multibox(size, vgg(base[str(size)], 3),add_extras(size, extras[str(size)], 1024),mbox[str(size)], num_classes), num_classes) SyntaxError: only named arguments may follow *expression

could you help me?

thank you very much

Hello, first thanks to your amazing open source algorithm. Maybe it's a minor problem, but I will be appreciated if you have time to answer. In your data/data_augment.py file, you use cv2 to read img file. As we all know, cv2 reads images in BGR order, but you subtract mean value (104, 117, 123), which is RGB order, as you write in annotation. A few days ago, I tried to use (123, 117, 104) instead and got a little improve in both precision and recall, and I'm not sure it is because the order of mean value. Would you please help me with this problem? Thanks again for your great algorithm.

Hi !@ruinmessi I run the ./make.sh but get g++ -pthread -shared -B /home/liye/anaconda3/compiler_compat -L/home/liye/anaconda3/lib -Wl,-rpath=/home/liye/anaconda3/lib,--no-as-needed build/temp.linux-x86_64-3.6/nms/nms_kernel.o build/temp.linux-x86_64-3.6/nms/gpu_nms.o -L/usr/local/cuda-8.0/lib64 -L/home/liye/anaconda3/lib -R/usr/local/cuda-8.0/lib64 -lcudart -lpython3.6m -o /media/ubuntue/extdisk1/liye/RFBNet-master/utils/nms/gpu_nms.cpython-36m-x86_64-linux-gnu.so g++: error: unrecognized command line option ‘-R’ error: command 'g++' failed with exit status 1

why? can you help me?

@ruinmessi

I follow your instruction below to train VOC with mobilenet, but got an error:

python3 train_RFB.py -d VOC -v RFB_mobile -s 300 300 21 Traceback (most recent call last): File "train_RFB.py", line 88, in net = build_net('train', img_dim, num_classes) File "/home/topspin/2TB/src/RFBNet/models/RFB_Net_mobile.py", line 348, in build_net mbox[str(size)], num_classes), num_classes) TypeError: init() missing 2 required positional arguments: 'head' and 'num_classes'

Any idea why this happens?

Thanks,

The conversion of boxes (cuda float tensors) which are returned from the detector forward to cpu float tensors has extremely high overhead. (I ignored the conversion to numpy array,takes about a microsecond)

boxes = boxes.cpu().numpy()

It takes approximately 22 milliseconds on a 512 input size (detection time is approximately 9 milliseconds)

Hi, thank you for your great work.

When I try to evaluate the trained model RFBNet300_VOC_80_7, which is one of your given models. I got the following error:

im_detect: 1/10 0.022s 0.001s Evaluating detections Writing aeroplane VOC results file Writing bicycle VOC results file Writing bird VOC results file Writing boat VOC results file Writing bottle VOC results file Writing bus VOC results file Writing car VOC results file Writing cat VOC results file Writing chair VOC results file Writing cow VOC results file Writing diningtable VOC results file Writing dog VOC results file Writing horse VOC results file Writing motorbike VOC results file Writing person VOC results file Writing pottedplant VOC results file Writing sheep VOC results file Writing sofa VOC results file Writing train VOC results file Writing tvmonitor VOC results file VOC07 metric? Yes Traceback (most recent call last): File "/home/johnsnore/Research/RFBNet/test_RFB.py", line 190, in top_k, thresh=0.01) File "/home/johnsnore/Research/RFBNet/test_RFB.py", line 143, in test_net testset.evaluate_detections(all_boxes, save_folder) File "/home/johnsnore/Research/RFBNet/data/voc0712.py", line 253, in evaluate_detections self._do_python_eval(output_dir) File "/home/johnsnore/Research/RFBNet/data/voc0712.py", line 310, in _do_python_eval use_07_metric=use_07_metric) File "/home/johnsnore/Research/RFBNet/data/voc_eval.py", line 152, in voc_eval BB = BB[sorted_ind, :] IndexError: too many indices for array

And I found BB=[] Is that something wrong? Should I do something else before run test_RFB.py？

I'm trying to train this code on my pc with your instructions. But there is a problem that generating ~_gt_roidb.pkl process. I've read dataset instructions but nothing explained about generating MS COCO cache folder and ~_gt_roidb.pkl file, even can not find the method on https://github.com/rbgirshick/py-faster-rcnn/blob/77b773655505599b94fd8f3f9928dbf1a9a776c7/data/README.md . Is there any way to get that file to train this model?

Hello, first of all, thanks for your code releasing. I got the training loss inf, acutally loss_l = inf, i use your original code (only fixed some bug), but i don't know why i got inf. Parameters: lr:0.004, batchsize:32, base_model:vgg_reducedfc.pth GPU: 1080ti

Any comments will be appreciated. Thanks very much!

Hi, Thank you for share your codes! When I test your code on VOC and SSD, I cannot reproduce the speed as you reported. My configuration is Titan XP, pytorch 0.4, cuda 9.0, and get 20+ms for VOC, 30+ms for COCO, not like yours (80+fps, and 15ms for COCO). When test the speed, I use conf_thresh 0.01, gpunms. I have also tried pytorch 0.3, still cannot reproduce the speed. The time of nms for me is ~20ms for COCO, and ~10ms for VOC. So have you consider the NMS time when report the fps? Any advice for getting the correct speed? Thank you very much!

Loading base network... Initializing weights... Loading Dataset... Traceback (most recent call last): File "train_RFB.py", line 257, in train() File "train_RFB.py", line 165, in train dataset = VOCDetection(VOCroot, train_sets, preproc( File "/home/fsr/code/RFBNet/data/voc0712.py", line 173, in init for line in open(os.path.join(rootpath, 'ImageSets', 'Main', name+'.txt')): FileNotFoundError: [Errno 2] No such file or directory: '/home/fsr/data/VOCdevkit/VOC2007/ImageSets/Main/trainval.txt'

The document exists, still reported the error, ask how to modify it

class BasicSepConv(nn.Module):

def __init__(self, in_planes, kernel_size, stride=1, padding=0, dilation=1, groups=1, relu=True, bn=True, bias=False):
    super(BasicSepConv, self).__init__()
    self.out_channels = in_planes
    self.conv = nn.Conv2d(in_planes, in_planes, kernel_size=kernel_size, stride=stride, padding=padding, dilation=dilation, groups = in_planes, bias=bias) #这是深度可分离卷积吗 用keras 的depthwise代替可以吗？
    self.bn = nn.BatchNorm2d(in_planes,eps=1e-5, momentum=0.01, affine=True) if bn else None
    self.relu = nn.ReLU(inplace=True) if relu else None

def forward(self, x):
    x = self.conv(x)
    if self.bn is not None:
        x = self.bn(x)
    if self.relu is not None:
        x = self.relu(x)
    return x

Hi! First of all thanks for your great job and contribution!

I was checking the code of the data augmentation transforms, specifically the _crop function. But, I have found that in some images it is almost impossible to find a valid crop (according to what I understand), when the image has more than 3 or 4 bboxes.

According to what I see in the code, you decide a minimum and maxium IoU randomly in this list:

mode = random.choice((
            None,
            (0.1, None),
            (0.3, None),
            (0.5, None),
            (0.7, None),
            (0.9, None),
            (None, None),
        ))
...
min_iou, max_iou = mode

Later on you compute the crop (roi variable) and the IoU of the bboxes with the full crop:

roi = np.array((l, t, l + w, t + h))
iou = matrix_iou(boxes, roi[np.newaxis])

and finally you check if all the bboxes have a minimum IoU with the whole crop bigger the randomly selected one:

if not (min_iou <= iou.min() and iou.max() <= max_iou):
            continue

and if they are not, you try again until you reach 50 trials.

However, I think its almost impossible to find a valid crop for images with a couple of bboxes. So, they are never cropped unless we fall in the (None, None) case. E.g. https://cocodataset.org/#explore?id=363917.

The reasons I find are:

1. The IoU is computed against the whole crop area, so it is difficult to get high IoU values unless the crop is tight around the BBox.
2. The minimum IoU is required for all the BBoxes. That is, it is always required that the crop takes all the BBoxes of the image.

Am I right? Was this intended somehow?

Thank you so much in advance!

c_type’? tstate->exc_type = local_type; ^~~~~~~~ curexc_type pycocotools/_mask.c:14327:13: error: ‘PyThreadState {aka struct _ts’ has no member named ‘exc_value’; did you mean ‘curexc_value’? tstate->exc_value = local_value; ^~~~~~~~~ curexc_value pycocotools/_mask.c:14328:13: error: ‘PyThreadState {aka struct _ts’ has no member named ‘exc_traceback’; did you mean ‘curexc_tracebac’? tstate->exc_traceback = local_tb; ^~~~~~~~~~~~~ curexc_traceback error: command 'gcc' failed with exit status 1