This repository was archived by the owner on Jan 24, 2024. It is now read-only.
Image classification new api markdown #542
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
daming-lu
approved these changes
Jun 8, 2018
| global step | ||
| if isinstance(event, paddle.event.EndIteration): | ||
| if isinstance(event, fluid.EndStepEvent): | ||
| if step % 1 == 0: |
Contributor
There was a problem hiding this comment.
we should change step % 1 == 0 to something more meaningful, say step % 10
Contributor
Author
There was a problem hiding this comment.
How about we remove this line? Looks like we should draw it no matter what.
| cost_ploter.plot() | ||
| step += 1 | ||
| if isinstance(event, paddle.event.EndPass): | ||
| if isinstance(event, fluid.EndEpochEvent): |
Contributor
There was a problem hiding this comment.
just curious at the last step of an epoch, will Fluid trigger both EndStepEvent and EndEpochEvent ?
Contributor
Author
There was a problem hiding this comment.
I believe the order is
EndStepEvent, and then EndEpochEvent
03.image_classification/README.cn.md
Outdated
| # 而PIL打开图片默认通道顺序为RGB,因为需要交换通道。 | ||
| im = im[(2, 1, 0),:,:] # BGR | ||
| im = im.flatten() | ||
| # The storage order of the loaded image is W(widht), |
03.image_classification/README.cn.md
Outdated
| # the CHW order, so transpose them. | ||
| im = im.transpose((2, 0, 1)) # CHW | ||
| # In the training phase, the channel order of CIFAR | ||
| # image is B(Blue), G(green), R(Red). But PIL open |
| lab = np.argsort(-probs) # probs and lab are the results of one batch data | ||
| print "Label of image/dog.png is: %d" % lab[0][0] | ||
| ``` | ||
| `Inferencer` 需要一个 `infer_func` 和 `param_path` 来设置网络和经过训练的参数。 |
Contributor
There was a problem hiding this comment.
kind of weird that we call the param name param_path but use params_dirname as the variable name 😭
param_path=params_dirname
But let's keep it as-is for now.
03.image_classification/README.md
Outdated
| Firstly, we create the model parameters according to the previous model configuration `cost`. | ||
| In the context of supervised learning, labels of training images are defined in `fluid.layers.data` as well. During training, the cross-entropy loss function is used and the loss is the output of the network. During testing, the outputs are the probabilities calculated in the classifier. | ||
|
|
||
| **NOTE:** A train program should return an array and the first return argument has to be `avg_cost`. |
Contributor
There was a problem hiding this comment.
first returned ; The trainer always implicitly uses
| global step | ||
| if isinstance(event, paddle.event.EndIteration): | ||
| if isinstance(event, fluid.EndStepEvent): | ||
| if step % 1 == 0: |
Contributor
There was a problem hiding this comment.
same here. step %10 might make more sense 😆
03.image_classification/README.md
Outdated
|
|
||
| ### Generate input data for inferring | ||
|
|
||
| `dog.png` is an example image of a dog. Turn it into an numpy array to match the data feeder format. |
03.image_classification/README.md
Outdated
| im = im.resize((32, 32), Image.ANTIALIAS) | ||
|
|
||
| im = np.array(im).astype(np.float32) | ||
| # The storage order of the loaded image is W(widht), |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Update the English and Chinese Image Classification tutorial with high level fluid API