SSD.TensorFlow issues

voc_eval.py 211行出现keyerror: File "voc_eval.py", line 211, in voc_eval R = class_recs[image_ids[d]] KeyError: '000000117121'

3

我用自己的数据集训练模型没问题，在执行eval_ssd.py也没报错，但是执行voc_eval.py出现keyerror问题。路径为main文件下的test.txt,但报错图片名称却在main文件下的其他txt文件中。删除了cache文件后重新执行评估，还是出现类似问题，但是是其他图片名称。数据已转化为tfrecord格式，路径all_images_file = 'ImageSets/Main/test.txt' 麻烦问一下有没有可能是做数据集时txt文件出错

yangguoqing666

How can I use multi-GPUs to train the ssd model?

1

Hello, I would like to consult if you can use multi-gpu training, how to modify the code?

cemiboou

TypeError: `default_name` type (<class 'list'>) is not a string type. When run train_ssd.py, I meet a TpyeError.

10

tensorflow 1.14 ,python3.5 ,cuda10.0, cudnn7.5.0 Traceback (most recent call last): File "/home/wzy/SSD.TensorFlow-master/train_ssd.py", line 464, in tf.app.run() File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/platform/app.py", line 40, in run _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef) File "/usr/local/lib/python3.5/dist-packages/absl/app.py", line 300, in...

CaptainKeer

tensorflow.python.framework.errors_impl.NotFoundError: Could not find directory

when I run convert_tfrecords.py to generate TFRecord follow the guidance, it comes out "tensorflow.python.framework.errors_impl.NotFoundError: Could not find directory"

ZhaolinWang0110

请问我在执行eval_ssd.py遇到的问题，下面是报错内容

InvalidArgumentError (see above for traceback): Incompatible shapes: [8732] vs. [279424] [[node decode_all_anchors/truediv (defined at /home/chen/chen/SSD.TensorFlow-master/utility/anchor_manipulator.py:121) = Mul[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"](decode_all_anchors/mul_1, decode_all_anchors/Exp)]] [[{{node select_bboxes/nms_bboxes_20/GatherV2_1/_549}} = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_name="edge_2228_select_bboxes/nms_bboxes_20/GatherV2_1", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"]()]] 这是报错内容，请帮帮我...

chenjjjjuu

InvalidArgumentError (see above for traceback): Restoring from checkpoint failed. This is most likely due to a mismatch between the current graph and the graph from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error: Assign requires shapes of both tensors to match. lhs shape= [1,1,1024,1024] rhs shape= [1,1,4096,4096] [[node save/Assign_29 (defined at E:\Infrared_Deeplearning\SSD-AbsoluteCoord\utility\scaffolds.py:86) ]]

2

InvalidArgumentError (see above for traceback): Restoring from checkpoint failed. This is most likely due to a mismatch between the current graph and the graph from the checkpoint. Please ensure that...

navy63