polish infer_rec and add ic15_dict #4
Merged
Conversation
This file contains 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
Collaborator
tink2123
commented
May 11, 2020
tink2123
commented
- polish infer_rec to support infer dir
- add ic15_dict and synchronous yml
LDOUBLEV
reviewed
May 11, 2020
train_data/gt_test.txt
Outdated
| @@ -0,0 +1,2077 @@ | |||
| test/word_1.png JOINT | |||
set_env.sh
Outdated
| ldconfig↩ | ||
| export CUDA_VISIBLE_DEVICES="0,1,2,3" | ||
| export FLAGS_fraction_of_gpu_memory_to_use=1.0 | ||
| python_bin_dir="/opt/_internal/cpython-3.7.0/bin/" |
There was a problem hiding this comment.
set_env.sh 这个文件应该不用放在repo里了
ppocr/data/rec/dataset_traversal.py
Outdated
| image_file_list = [self.infer_img] | ||
| elif os.path.isdir(self.infer_img): | ||
| for single_file in os.listdir(self.infer_img): | ||
| if single_file.endswith('png') or single_file.endswith('jpg'): |
There was a problem hiding this comment.
如果是其他图像文件是不是需要判断下，比如jpeg，bmp。如果图像是灰度图，还需要判断下并转换成彩色图
img_end = ['jpg', 'png', 'jpeg', 'JPEG', 'JPG', 'bmp']
if os.path.isfile(img_file) and img_file.split('.')[-1] in img_end:
imgs_lists.append(img_file)
img = cv2.imread(img_path)
if img.shape[-1]==1 or len(list(img.shape))==2:
img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
dyning
reviewed
May 12, 2020
| pretrain_weights: | ||
|
|
||
| pretrain_weights: | ||
| infer_img: ./infer_img |
| @@ -1,14 +1,13 @@ | |||
| TrainReader: | |||
configs/rec/rec_ic15_reader.yml
Outdated
| @@ -0,0 +1,13 @@ | |||
| TrainReader: | |||
There was a problem hiding this comment.
文件名称改为rec_icdar15_reader.yml
configs/rec/rec_ic15_train.yml
Outdated
| character_dict_path: ./ppocr/utils/ic15_dict.txt | ||
| loss_type: ctc | ||
| reader_yml: ./configs/rec/rec_ic15_reader.yml | ||
| pretrain_weights: ./pretrain_models/best_accuracy |
ppocr/data/rec/dataset_traversal.py
Outdated
| img = cv2.imread(self.infer_img) | ||
| norm_img = process_image(img, self.image_shape) | ||
| yield norm_img | ||
| image_file_list = [] |
There was a problem hiding this comment.
和infer中的函数read image list统一
ppocr/utils/ic15_dict.txt
Outdated
| @@ -0,0 +1,86 @@ | |||
| J | |||
set_env.sh
Outdated
| @@ -1,12 +1,10 @@ | |||
| #. /paddle/set_env.sh↩ | |||
dyning
approved these changes
May 12, 2020
Closed
BillDior
pushed a commit
to BillDior/PaddleOCR
that referenced
this pull request
Aug 13, 2021
test=develop
Closed
an1018
pushed a commit
to an1018/PaddleOCR
that referenced
this pull request
Aug 17, 2022
Add Travis CI
This was referenced Jan 11, 2023
Closed
mxihan
pushed a commit
to mxihan/PaddleOCR
that referenced
this pull request
Jul 4, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.