Codekiller

同样提问 conv10 = Conv2D(3,(1,1),activation='softmax')(conv9) model = Model(inputs=inputs, outputs=conv10) model.compile(optimizer=Adam(lr=1e-4), loss='binary_crossentropy', metrics=['accuracy']) 我做打算做三分类图片，图片已经进行了one-hot编码,但model结果不对，请问如何能正确改成多分类呀

可以看我的github，我用这个改了一个做三分类的

win64 py3.6 support？ **the error is：** d:\programfiles\anaconda 3.6\include\pyconfig.h(59): fatal error C1083: 无法打开包括文件: “io.h”: No such file or directory error: command 'C:\\Program Files (x86)\\Microsoft Visual Studio 14.0\\VC\\BIN\\x86_amd64\\cl.exe' failed with exit status...

> @whatevercyh I have an implementation here https://github.com/dimimal/semantics_segmentation_of_urban_environments/blob/master/trainCRF.py > > in crfRNN function with (512,512,3) as you refer sorry , but your url is broken...emmm,please share your methods thx very...