Skip to content
Snippets Groups Projects
Commit 6d6d501f authored by i-robot's avatar i-robot Committed by Gitee
Browse files

!913 C3d bug fix

Merge pull request !913 from 张晓晓/master
parents d30cf1fc baf8f14d
No related branches found
No related tags found
No related merge requests found
...@@ -425,11 +425,13 @@ eval result: top_1 79.381% ...@@ -425,11 +425,13 @@ eval result: top_1 79.381%
### [Export MindIR](#contents) ### [Export MindIR](#contents)
```shell ```shell
python export.py --ckpt_file [CKPT_PATH] --file_name [FILE_NAME] --file_format [FILE_FORMAT] python export.py --ckpt_file [CKPT_PATH] --mindir_file_name [FILE_NAME] --file_format [FILE_FORMAT] --num_classes [NUM_CLASSES] --batch_size [BATCH_SIZE]
``` ```
The ckpt_file parameter is required, - `ckpt_file` parameter is mandotory.
`file_format` should be in ["AIR", "MINDIR"] - `file_format` should be in ["AIR", "MINDIR"].
- `NUM_CLASSES` Number of total classes in the dataset, 51 for HMDB51 and 101 for UCF101.
- `BATCH_SIZE` Since currently mindir does not support dynamic shapes, this network only supports inference with batch_size of 1.
### Infer on Ascend310 ### Infer on Ascend310
......
...@@ -58,5 +58,5 @@ mindir_file_name: 'C3D' # Save file path ...@@ -58,5 +58,5 @@ mindir_file_name: 'C3D' # Save file path
file_format: 'MINDIR' # Save file format file_format: 'MINDIR' # Save file format
# 310 infer # 310 infer
pre_result_path: './pre_result_path' # Mindspore ckpt file path pre_result_path: './preprocess_Result' # save preprocess result file path
post_result_path: './result_Files' # Save file path post_result_path: './result_Files' # Save postprocess result file path
...@@ -31,7 +31,6 @@ def gen_bin(data_dir): ...@@ -31,7 +31,6 @@ def gen_bin(data_dir):
image_path = os.path.join(data_dir, "image") image_path = os.path.join(data_dir, "image")
label_path = os.path.join(data_dir, "label_bs" + str(config.batch_size) + ".npy") label_path = os.path.join(data_dir, "label_bs" + str(config.batch_size) + ".npy")
os.makedirs(image_path)
label_list = [] label_list = []
for index, (input_data, label) in enumerate(dataset): for index, (input_data, label) in enumerate(dataset):
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment