-
Hi, I am training custom objects on faster_rcnn_nas but total loss doesn't go down 0.9 or takes so long. I trained same dataset with faster_rcnn_inception_resnet_v2 loss goes under 0.1 around a couple…
-
@AlexeyAB I have seen gru.cfg and rnn.cfg in cfg folder If I use this file instead of v3 will it give higher accuracy. And If I want to add more layers in v3 is it possible? And how it differ from…
-
OSError: Unable to open file (unable to open file: name = 'model/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)
-
# Bug Report
### Which model does this pertain to?
-models/vision/classification/rcnn_ilsvrc13/model/rcnn-ilsvrc13-3.onnx
-models/vision/classification/alexnet/model/bvlcalexnet-3.onnx
-models…
-
Hello,
I get this error when running the commond line "python train.py --logtostderr --train_dir --train_dir=train/ --pipeline_config_path=training/faster_rcnn_inception_resnet_v2_atrous_oid.config",…
-
[ltrace_out.tar.gz](https://github.com/tensorflow/ngraph-bridge/files/5345200/ltrace_out.tar.gz)
[ngraph_log.tar.gz](https://github.com/tensorflow/ngraph-bridge/files/5345201/ngraph_log.tar.gz)
[s…
-
-
参考来源：
```
https://blog.csdn.net/m0_62128864/article/details/124527129
```
1. 简介
GoogLeNet是2014年Christian Szegedy提出的一种全新的深度学习结构，GoogLeNet名字致敬了LeNet，因此大写了L。在这之前的AlexNet、VGG等结构都是通过增大网络的深度（层数）来获得更好的训…
-
'''
InvalidArgumentError (see above for traceback): Tried to explicitly squeeze dimension 1 but dimension was not 1: 2
'''
-
I understand this issue is very basic problem.
In evaluate_mobilenet.py, how should I set my directry (C:\users\ ...), images, and resize option.
Could you show a sample in your case to me??
######…