researchmm / siamdw Goto Github PK

Could you please upload the SiamFC model trained with got10k, thank you :)

@JudasDie Thank you for your excellent research work，I have some questions to ask you.

1. What is the problem about ['GOT10K', 'LASOT']?
   when I trained SiamRPNRes22 on datasets ['GOT10K', 'LASOT'], errors occurred. But others datasets ['YTB', 'VID', 'COCO', 'DET'] are correct.
   detailed errors are : AttributeError: 'NoneType' object has no attribute 'shape'.
   if I trained SiamFC on datasets ['GOT10K'] or ['VID'], it is all right.

2. Why did it only get the best result VOT2015 EAO=0.332, when i trained SiamRPNRes22 on datasets ['YTB', 'VID', 'COCO', 'DET'] in GPU1080, it was lower than your paper result about 0.38.

when I try to analysis testing results i meet some errors that is

and i don't know how to modify my get_eao.m ,can you show me how to modify it.especially what meaning of 'year‘　in pwd = ['/home/han/project/vot-toolkit/', 'vot-workspace/', 'year'] % year is a str (can not be a number)

出错 get_eao (line 32)
practical = get_frame_value(sequence, 'practical');
未定义与 'struct' 类型的输入参数相对应的函数 'get_frame_value'
.....

ERROR: Could not find a version that satisfies the requirement opencv-python==3.1.0.5 (from versions: 3.4.2.17, 3.4.3.18, 3.4.4.19, 3.4.5.20, 3.4.6.27, 3.4.7.28, 4.0.0.21, 4.0.1.23, 4.0.1.24, 4.1.0.25, 4.1.1.26)
ERROR: No matching distribution found for opencv-python==3.1.0.5
Could you help me to fix it?

I used this to run tracker:
CUDA_VISIBLE_DEVICES=0 python ./siamese_tracking/test_siamfc.py --arch SiamFCRes22 --resume ./snapshot/CIResNet22.pth --dataset OTB2013

Error occurred:
load pretrained model from ./snapshot/CIResNet22.pth
remove prefix 'module.'
missing keys:{'features.features.layer2.0.bn2.num_batches_tracked', 'features.features.layer1.1.bn3.num_batches_tracked', 'features.features.layer2.2.bn2.num_batches_tracked', 'features.features.layer2.2.bn1.num_batches_tracked', 'features.features.layer1.1.bn1.num_batches_tracked', 'features.features.layer2.4.bn3.num_batches_tracked', 'features.features.bn1.num_batches_tracked', 'features.features.layer1.2.bn3.num_batches_tracked', 'features.features.layer1.0.bn3.num_batches_tracked', 'features.features.layer2.3.bn2.num_batches_tracked', 'features.features.layer1.0.bn1.num_batches_tracked', 'features.features.layer2.3.bn3.num_batches_tracked', 'features.features.layer1.0.bn2.num_batches_tracked', 'features.features.layer2.0.downsample.1.num_batches_tracked', 'features.features.layer1.0.downsample.1.num_batches_tracked', 'features.features.layer2.4.bn2.num_batches_tracked', 'features.features.layer1.2.bn2.num_batches_tracked', 'features.features.layer2.3.bn1.num_batches_tracked', 'features.features.layer2.0.bn1.num_batches_tracked', 'features.features.layer1.1.bn2.num_batches_tracked', 'features.features.layer2.2.bn3.num_batches_tracked', 'features.features.layer2.4.bn1.num_batches_tracked', 'features.features.layer1.2.bn1.num_batches_tracked', 'features.features.layer2.0.bn3.num_batches_tracked'}
unused checkpoint keys:{'connect_model.loc_adjust.weight', 'connect_model.loc_adjust.bias'}
Traceback (most recent call last):
File "./siamese_tracking/test_siamfc.py", line 248, in
main()
File "./siamese_tracking/test_siamfc.py", line 141, in main
track(tracker, net, dataset[video], args)
File "./siamese_tracking/test_siamfc.py", line 75, in track
if len(im.shape) == 2:
AttributeError: 'NoneType' object has no attribute 'shape'

Thanks for sharing your code. I noticed that the groundtruth in GOT10K's json file is much bigger than the resolution of GOT10K's train pictures. The resolution is 127127 and 255255, but the gt is more like [344, 223, 776, 1002]. I have no idea how it comes, can you please explain it?

i find that your file path in code is crop511. Have you trained with the data of crop511?

Is there any pretrained model for deeper model than XX22 such as ResNet50 with SiamFC?

Hi, Zhipeng, good job! Thanks for your kind release of this code. When I test the siamRPN with pre-trained model, however, I find the results is always lost even at the beginning. I wonder if you released the right version of the pretrained model? I see the following on my terminal:

python test_siamrpn.py
load pretrained model from ../snapshot/CIResNet22.pth
remove prefix 'module.'
missing keys:set(['connect_model.adjust.weight', 'connect_model.search_reg.bias', 'connect_model.search_cls.bias', 'connect_model.search_reg.weight', 'connect_model.template_reg.weight', 'connect_model.template_reg.bias', 'connect_model.search_cls.weight', 'connect_model.template_cls.bias', 'connect_model.template_cls.weight', 'connect_model.adjust.bias'])
unused checkpoint keys:set([u'connect_model.loc_adjust.weight', u'connect_model.loc_adjust.bias'])

Would you please kindly help to run the code succesfully? the code of SiamFC is OK (I tried). I used this setting for testing:

parser.add_argument('--arch', dest='arch', default='SiamRPNRes22', help='backbone architecture')
parser.add_argument('--resume', default='../snapshot/CIResNet22.pth', type=str, help='pretrained model')

I only run the parameter tuning process of pretrained SiamFCRes22 model with OTB2015 and got the error message:
Traceback (most recent call last): File "siamese_tracking/onekey_fc.py", line 101, in <module> main() File "siamese_tracking/onekey_fc.py", line 92, in main 2>&1 | tee logs/tpe_tune_fc.log'.format(trainINFO['MODEL'], 'snapshot/'+ resume, tuneINFO['DATA'], (len(info['GPUS']) + 1) // 2)) UnboundLocalError: local variable 'resume' referenced before assignment.
Could you please to tell me what can I do to avoid this error?

Hyperlink is not active or attached.

Hi, Zhipeng,

A nice work! I noticed that for LaSOT, you only provide the results for 279 videos. Did you want us to guess which one was missing (I am kidding :))? Could you please share the complete version. Thanks.

The repository gives some pretrained model, Are they only trained with VOT, OTB, and GOT10K?

excuse me ,when i modify the path_to/toolkit in lib/core/get_eao.m, I don't kown (pwd = ['/home/lym/vot-toolkit/','vot-workspace',year]), what is the "vot-workspace"?Can you show me your pwd=?
Thank you very much!

Thanks for your job！
Could you give me permission? I can't download training pairs by GoogleDrive.

Hi,

During training for SiamFC+, do you freeze the weights of first 7*7 conv as described in the paper? If yes, why I cannot find the corresponding operations in this code? And does the same operation applies for the SiamRPN+?

Thanks for your time.

How to unzip your training pairs?

what can i modify the pwd in the get_eao.m to make the evaluation work? i am a stranger to VOT dataset. And should i need to run the workspace_create.m in the toolkit?

Thanks for sharing your code first. I am sorry to bother you as a deep learning beginner.
I did modified path_to/toolkit in lib/core/get_eao.m to my vot-toolkit path as

addpath('/home/ltp/vot-toolkit/'); toolkit_path; % Make sure that VOT toolkit is in the path
pwd = ['/home/ltp/vot-toolkit/', 'vot', year]  % year is a str (can not be a number)

but I still got warning before training like this:

File /home/ltp/桌面/Workspace/SiamDW-master/lib/core/get_eao.m, line 12, in get_eao
unrecognized argument /home/ltp/vot-toolkit/vot2017

This problem has bothered me for weeks，hope you can help，thanks.

Some researers have shared their break-through with me. For example, Baojie told me that after replacing backbone to DenceNet in my code, the performance can still get improvement (as in the figure). So glad you people implement ideas and get improvement with our code rather than stop at the original things. This is the exact purpose for us to build a complete train-test-tuning system for siamese tracking.

Share your break-through with other researchers and get a comment！

I get the problem 'NaN or Inf found in input tensor' when training SiamRPN in the dataset that you give.

When trained SiamRPN on the dataset VID and GOT10K, i get a problem that REG_Loss is nan. But it was ok at the beginning of the epoch.

The problems are as follows:

PROGRESS: 0.18%

Epoch: [1][180/3125] lr : 0.0010000 Batch Time: 0.283 Data Time:0.012 CLS_Loss:0.45886 REG_Loss:2.81824 Loss:3.27710
Progress: 180 / 93750 [0%], Speed: 0.283 s/iter, ETA 0:07:21 (D:H:M)

PROGRESS: 0.19%

Epoch: [1][190/3125] lr : 0.0010000 Batch Time: 0.282 Data Time:0.012 CLS_Loss:0.45153 REG_Loss:2.76308 Loss:3.21461
Progress: 190 / 93750 [0%], Speed: 0.282 s/iter, ETA 0:07:19 (D:H:M)

PROGRESS: 0.20%

Epoch: [1][200/3125] lr : 0.0010000 Batch Time: 0.281 Data Time:0.011 CLS_Loss:0.44463 REG_Loss:nan Loss:nan
Progress: 200 / 93750 [0%], Speed: 0.281 s/iter, ETA 0:07:17 (D:H:M)

PROGRESS: 0.21%

Epoch: [1][210/3125] lr : 0.0010000 Batch Time: 0.280 Data Time:0.011 CLS_Loss:0.43784 REG_Loss:nan Loss:nan
Progress: 210 / 93750 [0%], Speed: 0.280 s/iter, ETA 0:07:17 (D:H:M)

/home/xgd/sunyang/SiamDW/siamese_tracking/../lib/dataset/siamrpn.py:291: RuntimeWarning: invalid value encountered in log
delta[2] = np.log(tw / (w + eps) + eps)
/home/xgd/sunyang/SiamDW/siamese_tracking/../lib/dataset/siamrpn.py:292: RuntimeWarning: invalid value encountered in log
delta[3] = np.log(th / (h + eps) + eps)
/home/xgd/sunyang/SiamDW/siamese_tracking/../lib/dataset/siamrpn.py:291: RuntimeWarning: invalid value encountered in log
delta[2] = np.log(tw / (w + eps) + eps)
/home/xgd/sunyang/SiamDW/siamese_tracking/../lib/dataset/siamrpn.py:292: RuntimeWarning: invalid value encountered in log
delta[3] = np.log(th / (h + eps) + eps)
Warning: NaN or Inf found in input tensor.
Warning: NaN or Inf found in input tensor.

It seems that the gradient exploded and i can not figured it out ,can you help me?

Hi, thanks for sharing the code.
I found the estimated time in my machine is about several days, and most of the time-consuming stage is Data Time.
Is this reasonable?

Thank you for your excellent job in object tracking area. I downloaded the SiamDW_DATA datas in Baidu driver,but some errors occured when I tried to unzip the datasets.The errors are shown below.

I tried several times,but there are same problems, I don't know how to solve these problem.Could you help me? or someone could help me?

I run the tuning process of SiamFC with OTB-2015 on the cloud by 8 GPUs, but it takes a long time to get the results.

The population and group size of GA in tune_gune are both set to 100, the population size seems quite bigger, so I am thinking to reduce it, is that possible? Do you test the tuning process of SiamFC using GA
with small population size?

Thanks for your code fisrt, it help so much
Here is a question:
I used the same processing method as SiamFC paper mentioned to preprocess the GOT-10K, but when I tried to train SiamFCRes22 on it, the auc result of OTB2015 is only 0.61+

Hi, Thank you for your excellent work. I have a quetion about PAIRS. Why is it set to 600000?

First，thanks for your wonderful work！
the download speed of preprocessed dataset is too slow，could you provide the code of generating the preprocess dataset？so that i can generate the dataset myself.

Hello,the link of parameter tuning toolkit is not available for me.

Thanks for your code fisrt, it help so much.
According to the configuration process you said, I successfully ran the test code.
I then converted the txt files into a mat files and put it into the OTB framework to calculate the result. However, I found that the SiamFCRes22 model only reached 0.615 on the OTB2013. So I am very confused about what is the reason.

Thanks for your great works and I found this repo to be really helpful.

Yet, other than the best-performing model CIResNet-22, I am also interested in several variants that's discussed in your paper, including the light-weight CIResNet-16 and the deeper CIResNet-43. However, I did not find the pre-trained model nor the code in the repo.

Could you please also share those models?

Thanks in advance.

"2>&1 | tee logs/siamfc_train.log" what is it:?

And when i running the training code. There is a mistake ---"BrokenPipeError: [Errno 32] Broken pipe".

How are you planning to submit your results to vot-challenge?

Is it the same way you are doing it now by copying handcrafted script results to vot-workspace?

because vot-toolkit works only with pytorch=0.3.1

any related suggestion would be helpful :)
Thank you

I recently read your paper. It is not clear how to calculate the RF of table3 in the paper. Can you introduce it? Thank you.

how to train train_siamRPN ?
just change MODEL:"SiamRPNRes22" in yaml ?
I think it need rpn loss function .

Hi there!
I train the SiamFCRes22 following the instruction, but the performance is much lower than yours (see below)

And my questions are:

• According the training details in the paper, you trained 50 epoches, so is X-checkpoint_50.pth the final model?
• I use the default parameters(SiamFCRes22.yaml) to test, do i need to perform Param-Tune to tune my parameters for my X-checkpoint_e50.pth?

Thanks a lot, and here is my training log:

2019-05-07 20:25:27,742 Namespace(cfg='../experiments/train/SiamFC.yaml', gpus='0', workers=32)
2019-05-07 20:25:27,743 {'CHECKPOINT_DIR': 'snapshot',
'GPUS': '0',
'OUTPUT_DIR': 'logs',
'PRINT_FREQ': 10,
'SIAMFC': {'DATASET': {'BLUR': 0,
'COLOR': 1,
'FLIP': 0,
'GOT10K': {'ANNOTATION': '/home/tjcv/dataset/SiamDW_trainset/GOT10K/train.json',
'PATH': '/home/tjcv/dataset/SiamDW_trainset/GOT10K/crop255'},
'ROTATION': 0,
'SCALE': 0.05,
'SHIFT': 4,
'VID': {'ANNOTATION': '/home/tjcv/dataset/SiamDW_trainset/VID/train.json',
'PATH': '/home/tjcv/dataset/SiamDW_trainset/VID/crop255'}},
'TEST': {'DATA': 'OTB2015',
'END_EPOCH': 50,
'MODEL': 'SiamFCIncep22',
'START_EPOCH': 30},
'TRAIN': {'BATCH': 32,
'END_EPOCH': 50,
'LR': 0.001,
'LR_END': 1e-07,
'LR_POLICY': 'log',
'MODEL': 'SiamFCRes22',
'MOMENTUM': 0.9,
'PAIRS': 600000,
'PRETRAIN': '../pretrain/CIResNet22_PRETRAIN.model',
'RESUME': False,
'SEARCH_SIZE': 255,
'START_EPOCH': 0,
'STRIDE': 8,
'TEMPLATE_SIZE': 127,
'WEIGHT_DECAY': 0.0001,
'WHICH_USE': 'VID'},
'TUNE': {'DATA': 'OTB2015',
'METHOD': 'GENE',
'MODEL': 'SiamFCIncep22'}},
'WORKERS': 32}
2019-05-07 20:25:30,937 trainable params:
2019-05-07 20:25:30,937 features.features.conv1.weight
2019-05-07 20:25:30,937 features.features.bn1.weight
2019-05-07 20:25:30,937 features.features.bn1.bias
2019-05-07 20:25:30,938 features.features.layer1.0.conv1.weight
2019-05-07 20:25:30,938 features.features.layer1.0.bn1.weight
2019-05-07 20:25:30,938 features.features.layer1.0.bn1.bias
2019-05-07 20:25:30,938 features.features.layer1.0.conv2.weight
2019-05-07 20:25:30,938 features.features.layer1.0.bn2.weight
2019-05-07 20:25:30,938 features.features.layer1.0.bn2.bias
2019-05-07 20:25:30,938 features.features.layer1.0.conv3.weight
2019-05-07 20:25:30,938 features.features.layer1.0.bn3.weight
2019-05-07 20:25:30,938 features.features.layer1.0.bn3.bias
2019-05-07 20:25:30,938 features.features.layer1.0.downsample.0.weight
2019-05-07 20:25:30,938 features.features.layer1.0.downsample.1.weight
2019-05-07 20:25:30,938 features.features.layer1.0.downsample.1.bias
2019-05-07 20:25:30,938 features.features.layer1.1.conv1.weight
2019-05-07 20:25:30,938 features.features.layer1.1.bn1.weight
2019-05-07 20:25:30,938 features.features.layer1.1.bn1.bias
2019-05-07 20:25:30,938 features.features.layer1.1.conv2.weight
2019-05-07 20:25:30,938 features.features.layer1.1.bn2.weight
2019-05-07 20:25:30,938 features.features.layer1.1.bn2.bias
2019-05-07 20:25:30,938 features.features.layer1.1.conv3.weight
2019-05-07 20:25:30,938 features.features.layer1.1.bn3.weight
2019-05-07 20:25:30,938 features.features.layer1.1.bn3.bias
2019-05-07 20:25:30,938 features.features.layer1.2.conv1.weight
2019-05-07 20:25:30,939 features.features.layer1.2.bn1.weight
2019-05-07 20:25:30,939 features.features.layer1.2.bn1.bias
2019-05-07 20:25:30,939 features.features.layer1.2.conv2.weight
2019-05-07 20:25:30,939 features.features.layer1.2.bn2.weight
2019-05-07 20:25:30,939 features.features.layer1.2.bn2.bias
2019-05-07 20:25:30,939 features.features.layer1.2.conv3.weight
2019-05-07 20:25:30,939 features.features.layer1.2.bn3.weight
2019-05-07 20:25:30,939 features.features.layer1.2.bn3.bias
2019-05-07 20:25:30,939 features.features.layer2.0.conv1.weight
2019-05-07 20:25:30,939 features.features.layer2.0.bn1.weight
2019-05-07 20:25:30,939 features.features.layer2.0.bn1.bias
2019-05-07 20:25:30,939 features.features.layer2.0.conv2.weight
2019-05-07 20:25:30,939 features.features.layer2.0.bn2.weight
2019-05-07 20:25:30,939 features.features.layer2.0.bn2.bias
2019-05-07 20:25:30,939 features.features.layer2.0.conv3.weight
2019-05-07 20:25:30,939 features.features.layer2.0.bn3.weight
2019-05-07 20:25:30,939 features.features.layer2.0.bn3.bias
2019-05-07 20:25:30,939 features.features.layer2.0.downsample.0.weight
2019-05-07 20:25:30,939 features.features.layer2.0.downsample.1.weight
2019-05-07 20:25:30,939 features.features.layer2.0.downsample.1.bias
2019-05-07 20:25:30,939 features.features.layer2.2.conv1.weight
2019-05-07 20:25:30,939 features.features.layer2.2.bn1.weight
2019-05-07 20:25:30,940 features.features.layer2.2.bn1.bias
2019-05-07 20:25:30,940 features.features.layer2.2.conv2.weight
2019-05-07 20:25:30,940 features.features.layer2.2.bn2.weight
2019-05-07 20:25:30,940 features.features.layer2.2.bn2.bias
2019-05-07 20:25:30,940 features.features.layer2.2.conv3.weight
2019-05-07 20:25:30,940 features.features.layer2.2.bn3.weight
2019-05-07 20:25:30,940 features.features.layer2.2.bn3.bias
2019-05-07 20:25:30,940 features.features.layer2.3.conv1.weight
2019-05-07 20:25:30,940 features.features.layer2.3.bn1.weight
2019-05-07 20:25:30,940 features.features.layer2.3.bn1.bias
2019-05-07 20:25:30,940 features.features.layer2.3.conv2.weight
2019-05-07 20:25:30,940 features.features.layer2.3.bn2.weight
2019-05-07 20:25:30,940 features.features.layer2.3.bn2.bias
2019-05-07 20:25:30,940 features.features.layer2.3.conv3.weight
2019-05-07 20:25:30,940 features.features.layer2.3.bn3.weight
2019-05-07 20:25:30,940 features.features.layer2.3.bn3.bias
2019-05-07 20:25:30,940 features.features.layer2.4.conv1.weight
2019-05-07 20:25:30,940 features.features.layer2.4.bn1.weight
2019-05-07 20:25:30,940 features.features.layer2.4.bn1.bias
2019-05-07 20:25:30,940 features.features.layer2.4.conv2.weight
2019-05-07 20:25:30,940 features.features.layer2.4.bn2.weight
2019-05-07 20:25:30,940 features.features.layer2.4.bn2.bias
2019-05-07 20:25:30,940 features.features.layer2.4.conv3.weight
2019-05-07 20:25:30,940 features.features.layer2.4.bn3.weight
2019-05-07 20:25:30,941 features.features.layer2.4.bn3.bias
2019-05-07 20:25:30,941 GPU NUM: 1
2019-05-07 20:25:30,945 model prepare done
2019-05-07 20:25:40,947 Epoch: [1][10/18750] lr: 0.0010000 Batch Time: 0.642s Data Time:0.334s Loss:11.23705
2019-05-07 20:25:40,947 Progress: 10 / 937500 [0%], Speed: 0.642 s/iter, ETA 6:23:12 (D:H:M)

2019-05-07 20:25:40,947
PROGRESS: 0.00%

2019-05-07 20:25:43,821 Epoch: [1][20/18750] lr: 0.0010000 Batch Time: 0.465s Data Time:0.167s Loss:8.01549
2019-05-07 20:25:43,821 Progress: 20 / 937500 [0%], Speed: 0.465 s/iter, ETA 5:01:01 (D:H:M)

2019-05-07 20:25:43,821
PROGRESS: 0.00%

2019-05-07 20:25:46,703 Epoch: [1][30/18750] lr: 0.0010000 Batch Time: 0.406s Data Time:0.112s Loss:5.91713
2019-05-07 20:25:46,703 Progress: 30 / 937500 [0%], Speed: 0.406 s/iter, ETA 4:09:41 (D:H:M)

2019-05-07 20:25:46,703
PROGRESS: 0.00%

2019-05-07 20:25:49,628 Epoch: [1][40/18750] lr: 0.0010000 Batch Time: 0.378s Data Time:0.084s Loss:4.73139
2019-05-07 20:25:49,629 Progress: 40 / 937500 [0%], Speed: 0.378 s/iter, ETA 4:02:19 (D:H:M)

2019-05-07 20:25:49,629
PROGRESS: 0.00%

2019-05-07 20:25:52,498 Epoch: [1][50/18750] lr: 0.0010000 Batch Time: 0.359s Data Time:0.067s Loss:3.99356
2019-05-07 20:25:52,498 Progress: 50 / 937500 [0%], Speed: 0.359 s/iter, ETA 3:21:35 (D:H:M)

2019-05-07 20:25:52,498
PROGRESS: 0.01%
...

Hi, thanks for the wonderful work.
We'd like to re-train your trackers from the ImageNet pretrained weights, as described in the paper of SiamDW. However, we cannot find the initial model links in the README. Will you provide your initial weights of ResNet22, Incep22, etc. to facilitate training? Thanks.

I ran ./snapshot/CIResNet22.pth on OTB2015 and got 0.6437 auc

Thanks for your great work! It helps me a lot.

The code of convolution layer of Siamfc model is:
def forward(self, z_f, x_f): if not self.training: return 0.1 * F.conv2d(x_f, z_f) else: return 0.1 * self._conv2d_group(x_f, z_f)

Why change the scale of the results of cross-correlation? How to determine parameter 0.1?

Thanks for your code fisrt, it help so much.
According to the configuration process you said, I successfully ran the training code of SiamFCRes22 network with CIResNet22_PRETRAIN.model as pretrained model.
In the SamFC. yaml file, the only thing I changed was the path of data. And because of the limited conditions, the number of my GPU is one.
The training code I run is as follows:
python ./siamese_tracking/train_siamfc.py --cfg experiments/train/SiamFC.yaml --gpus 0,1,2,3 --workers 32 2>&1 | tee logs/siamfc_train.log
But the best result of training 50 epochs is only about 0.62. I don't know what the problem is. I would like to ask if there is any inconsistency or neglect that caused this problem.

Thank you.

When i try to train a model on my dataset , i find the SiamFC.yaml Annotation infomation is organized to a json file. But, i can not find a json file sample in the code.
How should i organize the dataset to a json file? Can you upload this json file sample and explain it? 3Q so much,

who can share the VID, YTB, GOT10K, COCO, DET and LASOT according to baiduyun? they are so huge and difficult to download in domestic. can share a baiduyun link ?thanks so much!

Hi Team Researchmm
First, thanks for your brilliant work!
I encountered problems with the data you provided(both GOT-10k and VID), although the images are cropped to the size 255 times 255, probably the labels still stay the same as that of the original GOT-10k and VID. Can you please explain how to map labels with those cropped images and if it is possible could you please upload the processing file?
Thanks a lot!

There seems to be a problem with BaiduDrive links of Pretrained model preparation? could you fix it, thanks!

I notice that different parameters are used when test proposed models with different benchmarks.
For example, the parameters of SiamFCRes22 of OTB2015 are
scale_step: 1.1897 scale_lr: 0.2226 scale_penalty: 0.9370 w_influence: 0.2897
Could you please detail the selection strategy?

OTB2015 Best: F:\python\tracking\SiamDWmaster\siamese_tracking\result\OTB2015\SiamFCIncep22(0.1734)

The result when i run eval_otb.py .what is the 0.1734?