python - How do I re-use trained fastai models?

Question

How do I load pretrained model using fastai implementation over PyTorch? Like in SkLearn I can use pickle to dump a model in file then load and use later. I've use .load() method after declaring learn instance like bellow to load previously saved weights:

arch=resnet34
data = ImageClassifierData.from_paths(PATH, tfms=tfms_from_model(arch, sz))
learn = ConvLearner.pretrained(arch, data, precompute=False)
learn.load('resnet34_test')

Then to predict the class of an image:

trn_tfms, val_tfms = tfms_from_model(arch,100)
img = open_image('circle/14.png')
im = val_tfms(img)
preds = learn.predict_array(im[None])
print(np.argmax(preds))

But It gets me the error:

ValueError: Expected more than 1 value per channel when training, got input size [1, 1024]

This code works if I use learn.fit(0.01, 3) instead of learn.load(). What I really want is to avoid the training step In my application.

Answer 1

这可能是一个边缘情况，其中某些批次的批次大小等于 1。确保没有一个批次 = 1（主要是最后一批）

Answer 2

只要您的一批数据包含单个元素，就会发生此错误。

解决方案 1：在 learn.load('resnet34_test') 之后调用 learn.predict()

解决方案 2：从训练集中删除 1 个数据点。

Pytorch 问题

Fastai论坛问题描述

Answer 3

在训练中，如果您在训练集批次中有 1 个数据，您将收到此错误。

如果您使用模型来预测输出，请确保设置

learner.eval()