ssxlconch
ssxlconch
Hi,I run the python finetune.py --train but the output accuracy is always 1.0 and python finetune.py --prune it shows: Accuracy : 1.0 Number of prunning iterations to reduce 67% filters...
@RohitKeshari where did you add the modify code? I added it: if not next_conv is None: next_conv.bias = False if conv.bias is not None: next_conv.bias = True next_new_conv = \...
@hewumars 你好，我在运行python finetune.py --train的时候遇到这个问题： Traceback (most recent call last): File "/home/wade/Downloads/finetune-res.py", line 351, in print model NameError: name 'model' is not defined 是我缺少什么文件吗？
我遇到了另一个问题，在运行python finetune.py --train的过程中 我输出的精度一直为100% Epoch: 0 Accuracy : 100.0% Epoch: 1 Accuracy : 100.0% Epoch: 2 Accuracy : 100.0% Epoch: 3 Accuracy : 100.0% Epoch: 4 Accuracy : 100.0% 这是训练集的问题吗？我是在kaggle官网上下载的Dogs...
> 需要去下载 http://xiaoyongshen.me/webpage_portrait/index.html 您好，我这边不能用网盘，方便共享一下你在网盘上下载的数据集和代码吗？我的邮箱是[email protected]
> This failure is this: > `File "FCN_plus.py", line 295, in tf.app.run() File "/home/gpu/liuruoze/Matting/venv2/local/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 43, in run sys.exit(main(sys.argv[:1] + flags_passthrough)) File "FCN_plus.py", line 181, in main train_dataset_reader = BatchDatset('data/trainlist.mat')...
> 我用cpu TF跑FCN.py，一天半才跑到Step2000，不知道大概要多长时间才能跑完 您好，您跑通FCN了吗？我想问一下您除了按照readme里面说的建立文件夹还有运行两个文件并且copy到指定目录之外，在运行FCN.py的时候需要什么其他的指令吗？我这边运行之后网络不训练……
请问一下您跑通这个代码了吗？在运行的时候除了建文件夹和运行那两个mat文件之外，还需要别的操作吗？我运行python FCN.py跑不通代码……
> see #6 Thank you for reply. I saw #6 and could you please tell me your email address or send me the model? My email address: [email protected]
> validation loss is very high about 109, however training loss is 0.5, so can you help me with this issue? sorry for bothering do you have the pretrained model?...