FastMaskRCNN

FastMaskRCNN copied to clipboard

Hi all, I found that mask-rcnn has been released and upload to github. Prehasp, we can fix the known issues because of this code. https://github.com/TuSimple/mx-maskrcnn

jackytu256

hello evryone!!when I python/train/train.py ,meet this issue :Restored 267(544) vars from /home/bc/work/fastMaskCnn/data/pretrained_models/resnet_v1_50.ckpt 2017-09-11 19:56:08.315092: W tensorflow/core/framework/op_kernel.cc:1192] Invalid argument: Size 0 must be non-negative, not -1113667835 2017-09-11 19:56:08.315156: F tensorflow/core/framework/tensor_shape.cc:249] Check failed: 0 <= new_num_elements (0 vs. -1) 2017-09-11 19:56:08.315190: W tensorflow/core/framework/op_kernel.cc:1192] Invalid argument: Input to reshape is a tensor with 55 values, but the requested shape has 5120793180 [[Node: Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:GPU:0"](DecodeRaw_1/_559, Reshape/shape)]] Aborted (core dumped) if anyone has idea,please tell me

2

restoring resnet_v1_50/block4/unit_3/bottleneck_v1/conv1/BatchNorm/gamma:0 restoring resnet_v1_50/block4/unit_3/bottleneck_v1/conv1/BatchNorm/beta:0 restoring resnet_v1_50/block4/unit_3/bottleneck_v1/conv1/BatchNorm/moving_mean:0 restoring resnet_v1_50/block4/unit_3/bottleneck_v1/conv1/BatchNorm/moving_variance:0 restoring resnet_v1_50/block4/unit_3/bottleneck_v1/conv2/weights:0 restoring resnet_v1_50/block4/unit_3/bottleneck_v1/conv2/BatchNorm/gamma:0 restoring resnet_v1_50/block4/unit_3/bottleneck_v1/conv2/BatchNorm/beta:0 restoring resnet_v1_50/block4/unit_3/bottleneck_v1/conv2/BatchNorm/moving_mean:0 restoring resnet_v1_50/block4/unit_3/bottleneck_v1/conv2/BatchNorm/moving_variance:0 restoring resnet_v1_50/block4/unit_3/bottleneck_v1/conv3/weights:0 restoring resnet_v1_50/block4/unit_3/bottleneck_v1/conv3/BatchNorm/gamma:0 restoring resnet_v1_50/block4/unit_3/bottleneck_v1/conv3/BatchNorm/beta:0 restoring resnet_v1_50/block4/unit_3/bottleneck_v1/conv3/BatchNorm/moving_mean:0 restoring resnet_v1_50/block4/unit_3/bottleneck_v1/conv3/BatchNorm/moving_variance:0 restoring resnet_v1_50/logits/weights:0...

zhanglijian

Is it possible to train coco dataset for keypoint detection? Has someone experience on it? Thank you.

rujiao

pycocotools/make

6

I cloned your repo, and started to run how you describe in instructions. Whenever I run make command in pycocotools directory an error had been rised. That: python setup.py build_ext...

blgnksy

Testing the model

1

Hello, does anyone know how to test the trained model?

InesBeltaief

Fixed "Input to reshape is a tensor with 1 values, but the requested shape has 0" bug. Small changes: Python 3 compartible. Fixed tab/space mix in sample.py p.s. If you...

anatolix

Does anyone have idea on Testing the model?

17

I have trained the model for 500000 iterations and finally gained the ckpt file, but I have no idea on testing it. Has anyone finished testing the model?

sairin1202

Hello ,everyone !!!Now,python train/train.py meet this issue:ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[1,256,160,551] Is my NIVIDA out of memory? GPU device:GeForce GTX 1050 Ti 4.0G

9

ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[1,256,160,551] [[Node: pyramid_1/P2/rpn/convolution = Conv2D[T=DT_FLOAT, data_format="NHWC", padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/gpu:0"](pyramid/C2/fusion/BiasAdd, pyramid/P2/rpn/weights/read)]] [[Node: pyramid_1/AssignGTBoxes/Equal_5/_1175 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0",...

zhanglijian

Cannot train with Nvidia Titan 1080 11GB

1

shamanez

Almost all predictions are persons (the first class)

16

I tried prediction with the trained model, however it seems the output are strongly biased towards the first non-background class (person):    The above predictions are obtained from...

realwecan