FairMOT
FairMOT copied to clipboard
incorrect pretrained model in only MOT17 training.
Dear authors.
recently, I'm trying to reproduce the ablation studies but with more dimension changes.
the code version is [4aa6297](https://github.com/ifzhang/FairMOT/commit/4aa62976bde6266cbafd0509e24c3d98a7d0899f)
.
when I i tried MOT17
.
sh experiments/mot17_dla34.sh
I got below errors..
heads {'hm': 1, 'wh': 4, 'id': 128, 'reg': 2} Namespace(K=500, arch='dla_34', batch_size=12, cat_spec_wh=False, chunk_sizes=[6, 6], conf_thres=0.4, data_cfg='../src/lib/cfg/mot17.json', data_dir='/face/hnren/3.track/data', dataset='jde', debug_dir='/workspace/src/lib/../../exp/mot/mot17_dla34/debug', dense_wh=False, det_thres=0.3, down_ratio=4, exp_dir='/workspace/src/lib/../../exp/mot', exp_id='mot17_dla34', fix_res=True, gpus=[2, 3], gpus_str='2, 3', head_conv=256, heads={'hm': 1, 'wh': 4, 'id': 128, 'reg': 2}, hide_data_time=False, hm_weight=1, id_loss='ce', id_weight=1, img_size=(1088, 608), input_h=1088, input_res=1088, input_video='../videos/MOT16-03.mp4', input_w=608, keep_res=False, load_model='../models/ctdet_coco_dla_2x.pth', lr=0.0001, lr_step=[20], ltrb=True, master_batch_size=6, mean=None, metric='loss', min_box_area=100, mse_loss=False, multi_loss='uncertainty', nID=1425, nms_thres=0.4, norm_wh=False, not_cuda_benchmark=False, not_prefetch_test=False, not_reg_offset=False, num_classes=1, num_epochs=30, num_iters=-1, num_stacks=1, num_workers=8, off_weight=1, output_format='video', output_h=272, output_res=272, output_root='../demos', output_w=152, pad=31, print_iter=0, reg_loss='l1', reg_offset=True, reid_dim=128, resume=False, root_dir='/workspace/src/lib/../..', save_all=False, save_dir='/workspace/src/lib/../../exp/mot/mot17_dla34', seed=317, std=None, task='mot', test=False, test_hie=False, test_mot15=False, test_mot16=False, test_mot17=False, test_mot20=False, track_buffer=30, trainval=False, val_hie=False, val_intervals=5, val_mot15=False, val_mot16=False, val_mot17=True, val_mot20=False, vis_thresh=0.5, wh_weight=0.1) Creating model... Starting training... loaded ../models/ctdet_coco_dla_2x.pth, epoch 230 Skip loading parameter hm.2.weight, required shapetorch.Size([1, 256, 1, 1]), loaded shapetorch.Size([80, 256, 1, 1]). If you see this, your model does not fully load the pre-trained weight. Please make sure you have correctly specified --arch xxx or set the correct --num_classes for your own dataset. Skip loading parameter hm.2.bias, required shapetorch.Size([1]), loaded shapetorch.Size([80]). If you see this, your model does not fully load the pre-trained weight. Please make sure you have correctly specified --arch xxx or set the correct --num_classes for your own dataset. Skip loading parameter wh.2.weight, required shapetorch.Size([4, 256, 1, 1]), loaded shapetorch.Size([2, 256, 1, 1]). If you see this, your model does not fully load the pre-trained weight. Please make sure you have correctly specified --arch xxx or set the correct --num_classes for your own dataset. Skip loading parameter wh.2.bias, required shapetorch.Size([4]), loaded shapetorch.Size([2]). If you see this, your model does not fully load the pre-trained weight. Please make sure you have correctly specified --arch xxx or set the correct --num_classes for your own dataset. No param id.0.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you have correctly specified --arch xxx or set the correct --num_classes for your own dataset. No param id.0.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you have correctly specified --arch xxx or set the correct --num_classes for your
own dataset.
No param id.2.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you have correctly specified --arch xxx or set the correct --num_classes for your own dataset.
No param id.2.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you have correctly specified --arch xxx or set the correct --num_classes for your
own dataset.
Could you be so kind as to let me know what happens?
Thanks.