-
Notifications
You must be signed in to change notification settings - Fork 39
Conversation
报错信息: |
resnet50/model.py
Outdated
@@ -202,19 +202,19 @@ def run_benchmark(model, args): | |||
else: | |||
dshape = [224, 224, 3] | |||
|
|||
input = fluid.layers.data(name='data', shape=dshape, dtype='float32') | |||
image = fluid.layers.data(name='image', shape=dshape, dtype='float32') |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Is it because the data name is changed?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
这里只是个符号? 我们在模型代码似乎没用到这个变量? 我看其他模型写的image, 我想保持统一
resnet50/model.py
Outdated
@@ -241,24 +249,21 @@ def test(exe): | |||
y_data = np.array(map(lambda x: x[1], data)).astype("int64") | |||
y_data = y_data.reshape([-1, 1]) | |||
|
|||
acc, weight = exe.run(inference_program, | |||
acc, weight = test_exe.run(inference_program, | |||
feed={"data": img_data, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The name here is 'data'
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
恩恩, 还没调到这里, 先忽略这里把。。。。 主要是297 train 那儿
resnet50/model.py
Outdated
|
||
place = core.CPUPlace() if args.device == 'CPU' else core.CUDAPlace(0) | ||
exe = fluid.Executor(place) | ||
#exe.run(fluid.default_startup_program()) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
why deleted
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
似乎是这儿的问题。。。这个错误输出把我给迷惑了。
谢谢潘老师
请yuyang,jiayi老师帮忙看个问题