Cascade-RCNN_Tensorflow
Cascade-RCNN_Tensorflow copied to clipboard
DetectionTeamUCAS
Hello, we encountered the following problems when we replaced Resnet101 with Mobilenet_v2. How can I solve it? Traceback (most recent call last): File "train.py", line 185, in train() File "train.py",...
I used mobilenet V2 with CasCade R-CNN network training, but compared to Resnet101, the accuracy rate is reduced by 20%, but the paper of mobilenet V2 will not decrease so...
2019-12-27 13:16:01.269879: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 AVX512F FMA restore model ../libs/box_utils/encode_and_decode.py:85: RuntimeWarning: invalid value encountered...
OutOfRangeError (see above for traceback): PaddingFIFOQueue '_1_get_batch/batch/padding_fifo_queue' is closed and has insufficient elements (requested 1, current size 0) [[Node: get_batch/batch = QueueDequeueManyV2[component_types=[DT_STRING, DT_FLOAT, DT_INT32, DT_INT32], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/device:CPU:0"](get_batch/batch/padding_fifo_queue, get_batch/batch/n)]] 你好，我用你的代码来跑我自己的数据集的时候，迭代了850次以后出现了上述问题，我想请问一下这个是由三名引进的
Why batchsize only support one? I want to change it ? Can you explain it to me?
I have changed the database and converted to tfrecords . when i run it for minutes, fast_rcnn_loc_loss become 0.0 rpn_loc_loss become nan. ``  for t_w = np.log(w/reference_w), I have...
I'm sorry I met a new problem.Now running step exceed MAX_ITERATION for 100000，but it still train. Can you tell me the end steps?  In your code, are there other...