-
It is saying that " File b'fer2013.csv' does not exist ". How to get the csv file.
-
-
I only have one .csv file, named fer2013.csv. How can I make the train and test .csv file?
-
Hello, why is my accuracy rate on fer2013 data set only around 47%? I didn't make any changes to your code
-
sorry, I tried to run the main_fer2013.py file and specified the model name is resmasking_dropout1, but I only got 65.63% accuracy on the private test dataset. What caused this?
-
求问作者，是不是深度越浅就越没有提升啊？我在ResNet上apply，用的FER2013表情database，用SGD大概72% accuracy左右，改用SGD_GC后基本一样，甚至还低了...用的是Res18，要不我再用Res34对比一下？
-
Testing on 48x48 fer2013 led to undetected faces...
-
sorry, I tried to run the main_fer2013.py file and specified the model name is resnet34,I can got 72.88%, but specified the model name is resmasking_dropout1, I only got 69.09% accuracy on the pri…
-
Trying the first step [ tf_to_trt_image_classification/scripts/models_to_frozen_graphs.py](https://github.com/NVIDIA-AI-IOT/tf_to_trt_image_classification/blob/master/scripts/models_to_frozen_graphs.p…
-
I tried to get just the accuracy figure of 79.79% proposed in the paper for FER2013 dataset but only got 71.57%.
I gave the model the best shot I could by using the model weights provided in the RE…