GithubHelp home page GithubHelp logo

Comments (5)

huanghoujing avatar huanghoujing commented on August 29, 2024

Hi, thanks for your attention. These places DATASET_NAME, STRIDE, EXPERIMENT_DIRECTORY, THE_DOWNLOADED_MODEL_WEIGHT_FILE should be replaced by respective values, e.g. by market1501, 1, exp, model_weight.pth. You should specify these.

from person-reid-triplet-loss-baseline.

vismayaps avatar vismayaps commented on August 29, 2024

Hi, I tried every possible combinations to run this but I get this "unrecognised arguments error", can you please post the exact command to run ? name of my experiment directory is "test_log", and the downloaded weight file is inside the folder "market501_stride1".

from person-reid-triplet-loss-baseline.

huanghoujing avatar huanghoujing commented on August 29, 2024

You can share your full command here, and I see if there is a problem.

from person-reid-triplet-loss-baseline.

vismayaps avatar vismayaps commented on August 29, 2024

Hi,
Here is the command I am using for testing :

python script/experiment/train.py
-d '(0,)'
--only_test true
--market1501
--1
--normalize_feature false
--exp
--model_weight.pth
and I am getting the following error :
usage: train.py [-h] [-d SYS_DEVICE_IDS] [-r RUN] [--set_seed SET_SEED]
[--dataset {market1501,cuhk03,duke,combined}]
[--trainset_part {trainval,train}] [--resize_h_w RESIZE_H_W]
[--crop_prob CROP_PROB] [--crop_ratio CROP_RATIO]
[--mirror MIRROR] [--ids_per_batch IDS_PER_BATCH]
[--ims_per_id IMS_PER_ID] [--log_to_file LOG_TO_FILE]
[--steps_per_log STEPS_PER_LOG]
[--epochs_per_val EPOCHS_PER_VAL] [--last_conv_stride {1,2}]
[--normalize_feature NORMALIZE_FEATURE] [--margin MARGIN]
[--only_test ONLY_TEST] [--resume RESUME] [--exp_dir EXP_DIR]
[--model_weight_file MODEL_WEIGHT_FILE] [--base_lr BASE_LR]
[--lr_decay_type {exp,staircase}]
[--exp_decay_at_epoch EXP_DECAY_AT_EPOCH]
[--staircase_decay_at_epochs STAIRCASE_DECAY_AT_EPOCHS]
[--staircase_decay_multiply_factor STAIRCASE_DECAY_MULTIPLY_FACTOR]
[--total_epochs TOTAL_EPOCHS]
train.py: error: ambiguous option: --exp could match --exp_dir, --exp_decay_at_epoch
Thanks !!

from person-reid-triplet-loss-baseline.

huanghoujing avatar huanghoujing commented on August 29, 2024

OK, (1) you missed the trailing backslashes \ for multi-line command. (2) Some keywords are missing in your command. The modified version is as follows. You may try it.

python script/experiment/train.py \
-d '(0,)' \
--only_test true \
--dataset market1501 \
--last_conv_stride 1 \
--normalize_feature false \
--exp_dir exp \
--model_weight_file model_weight.pth

from person-reid-triplet-loss-baseline.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.