Open VisImage opened 2 months ago
Thank you for sharing the code.
When trying to train the model using our customised dataset, following instruction as indicated in PaddleClas/docs/en/PULC /PULC_person_attribute_en.md. I got the error as below,. lease let me know what else I need to modify. Than you
3.3 Training succeeds. python -m paddle.distributed.launch \ --gpus="0" \ tools/train.py \ -c ./ppcls/configs/PULC/person_attribute/PPLCNet_x1_0_myData.yaml
3.4 Evaluation succeeds. python tools/eval.py \ -c ./ppcls/configs/PULC/person_attribute/PPLCNet_x1_0_myData.yaml \ -o Global.pretrained_model="output/best_model/model.pdparams"
3.5 Inference failed. python tools/infer.py \ -c ./ppcls/configs/PULC/person_attribute/PPLCNet_x1_0_myData.yaml \ -o Global.pretrained_model="output/best_model/model.pdparams"
ppcls ERROR: Exception occured when parse line: deploy/images/PULC/person_attribute/090007.jpg with msg: list index out of range
The file PPLCNet_x1_0_myData.yaml is shown below, which is based ./ppcls/configs/PULC/person_attribute/PPLCNet_x1_0.yaml with a few modifications:
------------- ./ppcls/configs/PULC/person_attribute/PPLCNet_x1_0_myData.yaml -------------
Global: checkpoints: null pretrained_model: null output_dir: "./output/" device: "gpu" save_interval: 1 eval_during_train: True eval_interval: 1 epochs: 10 print_batch_step: 10 use_visualdl: False
image_shape: [3, 256, 192] save_inference_dir: "./inference" use_multilabel: True
Arch: name: "PPLCNet_x1_0" pretrained: True use_ssld: True class_num: 9
Loss: Train:
Optimizer: name: Momentum momentum: 0.9 lr: name: Cosine learning_rate: 0.01 warmup_epoch: 5 regularizer: name: 'L2' coeff: 0.0005
DataLoader: Train: dataset: name: MultiLabelDataset image_root: "dataset/myData/" cls_label_path: "dataset/myData/train_list.txt"
#cls_label_path: "dataset/pa100k/train_list.txt" label_ratio: True transform_ops: - DecodeImage: to_rgb: True channel_first: False - ResizeImage: size: [192, 256] - TimmAutoAugment: prob: 0.8 config_str: rand-m9-mstd0.5-inc1 interpolation: bicubic img_size: [192, 256] - Padv2: size: [212, 276] pad_mode: 1 fill_value: 0 - RandomCropImage: size: [192, 256] - RandFlipImage: flip_code: 1 - NormalizeImage: scale: 1.0/255.0 mean: [0.485, 0.456, 0.406] std: [0.229, 0.224, 0.225] order: '' - RandomErasing: EPSILON: 0.4 sl: 0.02 sh: 1.0/3.0 r1: 0.3 attempt: 10 use_log_aspect: True mode: pixel sampler: name: DistributedBatchSampler batch_size: 64 drop_last: True shuffle: True loader: num_workers: 4 use_shared_memory: True
Eval: dataset: name: MultiLabelDataset image_root: "dataset/myData/" cls_label_path: "dataset/myData/val_list.txt"
#cls_label_path: "dataset/pa100k/val_list.txt" label_ratio: True transform_ops: - DecodeImage: to_rgb: True channel_first: False - ResizeImage: size: [192, 256] - NormalizeImage: scale: 1.0/255.0 mean: [0.485, 0.456, 0.406] std: [0.229, 0.224, 0.225] order: '' sampler: name: DistributedBatchSampler batch_size: 64 drop_last: False shuffle: False loader: num_workers: 4 use_shared_memory: True
Infer: infer_imgs: deploy/images/PULC/person_attribute/ batch_size: 10 transforms:
Metric: Eval:
Hi,may I ask, what are the details of your yaml changes? Can you list them?
Thank you for sharing the code.
When trying to train the model using our customised dataset, following instruction as indicated in PaddleClas/docs/en/PULC /PULC_person_attribute_en.md. I got the error as below,. lease let me know what else I need to modify. Than you
3.3 Training succeeds. python -m paddle.distributed.launch \ --gpus="0" \ tools/train.py \ -c ./ppcls/configs/PULC/person_attribute/PPLCNet_x1_0_myData.yaml
3.4 Evaluation succeeds. python tools/eval.py \ -c ./ppcls/configs/PULC/person_attribute/PPLCNet_x1_0_myData.yaml \ -o Global.pretrained_model="output/best_model/model.pdparams"
3.5 Inference failed. python tools/infer.py \ -c ./ppcls/configs/PULC/person_attribute/PPLCNet_x1_0_myData.yaml \ -o Global.pretrained_model="output/best_model/model.pdparams"
ppcls ERROR: Exception occured when parse line: deploy/images/PULC/person_attribute/090007.jpg with msg: list index out of range
The file PPLCNet_x1_0_myData.yaml is shown below, which is based ./ppcls/configs/PULC/person_attribute/PPLCNet_x1_0.yaml with a few modifications:
------------- ./ppcls/configs/PULC/person_attribute/PPLCNet_x1_0_myData.yaml -------------
global configs
Global: checkpoints: null pretrained_model: null output_dir: "./output/" device: "gpu" save_interval: 1 eval_during_train: True eval_interval: 1 epochs: 10 print_batch_step: 10 use_visualdl: False
used for static mode and model export
image_shape: [3, 256, 192] save_inference_dir: "./inference" use_multilabel: True
model architecture
Arch: name: "PPLCNet_x1_0" pretrained: True use_ssld: True class_num: 9
class_num: 26
loss function config for traing/eval process
Loss: Train:
Optimizer: name: Momentum momentum: 0.9 lr: name: Cosine learning_rate: 0.01 warmup_epoch: 5 regularizer: name: 'L2' coeff: 0.0005
data loader for train and eval
DataLoader: Train: dataset: name: MultiLabelDataset image_root: "dataset/myData/" cls_label_path: "dataset/myData/train_list.txt"
image_root: "dataset/pa100k/"
Eval: dataset: name: MultiLabelDataset image_root: "dataset/myData/" cls_label_path: "dataset/myData/val_list.txt"
image_root: "dataset/pa100k/"
Infer: infer_imgs: deploy/images/PULC/person_attribute/ batch_size: 10 transforms:
glasses_threshold: 0.3 #threshold only for glasses
hold_threshold: 0.6 #threshold only for hold
Metric: Eval: