Closed TokenJan closed 6 years ago
when performing predicting, following code will be invoked in cnn_main.py
cnnModel.fPredict(dData['X_test'], dData['y_test'], dData['model_name'], sOutPath, dData['patchSize'], iBatchSize[0])
However, there is no model_name in param.yml
model_name
Beside, the trained weights are stored like testout4040_lr_0.05_bs_128_weights.h5, testout4040_lr_0.05_bs_128.mat and testout4040_lr_0.05_bs_128_json, while the weights are loaded in motion_all_CNN2D.py as follows:
testout4040_lr_0.05_bs_128_weights.h5
testout4040_lr_0.05_bs_128.mat
testout4040_lr_0.05_bs_128_json
def fPredict(X_test, y_test, model_name, sOutPath, patchSize, batchSize): weight_name = model_name[0] + '_weights.h5' model_json = model_name[0] + '_json' model_all = model_name[0] + '_model.h5'
How can we adapt these changes?
fixed with f8d5bfba1fb06e6960325a31d2db8594c16fcbed closed
when performing predicting, following code will be invoked in cnn_main.py
However, there is no
model_name
in param.ymlBeside, the trained weights are stored like
testout4040_lr_0.05_bs_128_weights.h5
,testout4040_lr_0.05_bs_128.mat
andtestout4040_lr_0.05_bs_128_json
, while the weights are loaded in motion_all_CNN2D.py as follows:How can we adapt these changes?