tf-faster-rcnn

tf-faster-rcnn copied to clipboard

loss is always the same,dont smaller

7

iter: 47220 / 70000, total loss: 0.354476 >>> rpn_loss_cls: 0.000126 >>> rpn_loss_box: 0.000068 >>> loss_cls: 0.003523 >>> loss_box: 0.000122 >>> lr: 0.001000 speed: 0.276s / iter iter: 47240 / 70000,...

henbucuoshanghai

How to find the output node name

1

I want to freeze the model from the .meta file ,but I do not konw the output node name, please help me

TristramAr

loss is nan

7

iter: 20 / 70000, total loss: nan >>> rpn_loss_cls: 0.648382 >>> rpn_loss_box: 0.045217 >>> loss_cls: 2.149889 >>> loss_box: 0.199051 >>> lr: 0.010000 speed: 0.794s / iter iter: 40 / 70000,...

henbucuoshanghai

Downloading the pre-trained model fails

5

`ladoga.graphics.cs.cmu.edu` didn't work so I replaced it with `gs11655.sp.cs.cmu.edu` Then I got the error ``` File already exists. Checking md5... Checksum is incorrect. Need to download again. Downloading Resnet 101...

arjunpmm

sorry, I have a question ; when i run './experiments/scripts/train_faster_rcnn.sh 1 coco res101 ' in terminal to begin train, it failed and showed this: + set -e + export PYTHONUNBUFFERED=True...

ESCEBT

CuDNN library

2

E tensorflow/stream_executor/cuda/cuda_dnn.cc:378] Loaded runtime CuDNN library: 7201 (compatibility version 7200) but source was compiled with 7004 (compatibility version 7000). If using a binary install, upgrade your CuDNN library to match....

zjmlovlin

How to train Faster R-CNN on my own dataset?

35

Hi,every: I want to train Faster R-CNN on my own dataset,and this dataset has only two classes. I do not know how to change the code.Could you give me a...

tp227

I get zeros everywhere. Any idea? Reading annotation for 4951/4952 Reading annotation for 4952/4952 Saving cached annotations to /home/sagarwal/tf-faster-rcnn/data/VOCdevkit2007/annotations_cache/test_annots.pkl AP for aeroplane = 0.0000 AP for bicycle = 0.0000 AP...

shankar-agarwal

I get zeros everywhere. Any idea? Reading annotation for 4951/4952 Reading annotation for 4952/4952 Saving cached annotations to /home/sagarwal/tf-faster-rcnn/data/VOCdevkit2007/annotations_cache/test_annots.pkl AP for aeroplane = 0.0000 AP for bicycle = 0.0000 AP...

shankar-agarwal

I get zeros everywhere. Any idea? Reading annotation for 4951/4952 Reading annotation for 4952/4952 Saving cached annotations to /home/sagarwal/tf-faster-rcnn/data/VOCdevkit2007/annotations_cache/test_annots.pkl AP for aeroplane = 0.0000 AP for bicycle = 0.0000 AP...

shankar-agarwal