From f5313fdc82e733b3b8f1f8c5846ab596612064ce Mon Sep 17 00:00:00 2001 From: Yangyang Li Date: Mon, 2 Dec 2024 14:46:33 -0600 Subject: [PATCH] update scripte --- configs/experiment/hyena.yaml | 10 +++++----- scripts/chop.sh | 28 +++++++++++++--------------- scripts/predict.sh | 9 ++++++--- 3 files changed, 24 insertions(+), 23 deletions(-) diff --git a/configs/experiment/hyena.yaml b/configs/experiment/hyena.yaml index 1caacd2..eb406a3 100644 --- a/configs/experiment/hyena.yaml +++ b/configs/experiment/hyena.yaml @@ -16,7 +16,7 @@ callbacks: early_stopping: patience: 15 -tags: ["vcap_004_300000"] +tags: ["vcap_002_300000_both"] seed: 12345 @@ -25,10 +25,10 @@ trainer: max_epochs: 60 data: - train_data_path: ${paths.root_dir}/data/600_000_both_samples/train.parquet - val_data_path: ${paths.root_dir}/data/600_000_both_samples/val.parquet - test_data_path: ${paths.root_dir}/data/600_000_both_samples/test.parquet - batch_size: 8 + train_data_path: ${paths.root_dir}/data/300_000_both_samples/train.parquet + val_data_path: ${paths.root_dir}/data/300_000_both_samples/val.parquet + test_data_path: ${paths.root_dir}/data/300_000_both_samples/test.parquet + batch_size: 12 num_workers: 63 pin_memory: False max_val_samples: 3000 diff --git a/scripts/chop.sh b/scripts/chop.sh index 82d21d4..471b5d1 100644 --- a/scripts/chop.sh +++ b/scripts/chop.sh @@ -1,22 +1,20 @@ #!/bin/bash set -euo pipefail # Combines the set commands into one line -predict_folder="vcap_caduceus" +# predict_folder="vcap_caduceus" -cargo run --bin predict -r -- \ - --pdt /projects/b1171/ylk4626/project/DeepChopper/logs/eval/runs/vcap_004_hyena/RNA004.fastq_0/predicts/0/ \ - --pdt /projects/b1171/ylk4626/project/DeepChopper/logs/eval/runs/vcap_004_hyena/RNA004.fastq_1/predicts/0/ \ - --pdt /projects/b1171/ylk4626/project/DeepChopper/logs/eval/runs/vcap_004_hyena/RNA004.fastq_2/predicts/0/ \ - --pdt /projects/b1171/ylk4626/project/DeepChopper/logs/eval/runs/vcap_004_hyena/RNA004.fastq_3/predicts/0/ \ - --pdt /projects/b1171/ylk4626/project/DeepChopper/logs/eval/runs/vcap_004_hyena/RNA004.fastq_4/predicts/0/ \ - --pdt /projects/b1171/ylk4626/project/DeepChopper/logs/eval/runs/vcap_004_hyena/RNA004.fastq_5/predicts/0/ \ - --pdt /projects/b1171/ylk4626/project/DeepChopper/logs/eval/runs/vcap_004_hyena/RNA004.fastq_6/predicts/0/ \ - --pdt /projects/b1171/ylk4626/project/DeepChopper/logs/eval/runs/vcap_004_hyena/RNA004.fastq_7/predicts/0/ \ - --pdt /projects/b1171/ylk4626/project/DeepChopper/logs/eval/runs/vcap_004_hyena/RNA004.fastq_8/predicts/0/ \ - --pdt /projects/b1171/ylk4626/project/DeepChopper/logs/eval/runs/vcap_004_hyena/RNA004.fastq_9/predicts/0/ \ - --pdt /projects/b1171/ylk4626/project/DeepChopper/logs/eval/runs/vcap_004_hyena/RNA004.fastq_10/predicts/0/ \ - --pdt /projects/b1171/ylk4626/project/DeepChopper/logs/eval/runs/vcap_004_hyena/RNA004.fastq_11/predicts/0/ \ - --fq data/dorado_without_trim_fqs/RNA004.fastq -t 10 -o vcap_004_hyena_all +cargo run --bin deepchopper-chop -r -- \ + --pdt /projects/b1171/ylk4626/project/DeepChopper/logs/eval/runs/vcap002_hyena_both_model_hyena/VCaP.fastq_0/predicts/0/ \ + --pdt /projects/b1171/ylk4626/project/DeepChopper/logs/eval/runs/vcap002_hyena_both_model_hyena/VCaP.fastq_1/predicts/0/ \ + --pdt /projects/b1171/ylk4626/project/DeepChopper/logs/eval/runs/vcap002_hyena_both_model_hyena/VCaP.fastq_2/predicts/0/ \ + --pdt /projects/b1171/ylk4626/project/DeepChopper/logs/eval/runs/vcap002_hyena_both_model_hyena/VCaP.fastq_3/predicts/0/ \ + --pdt /projects/b1171/ylk4626/project/DeepChopper/logs/eval/runs/vcap002_hyena_both_model_hyena/VCaP.fastq_4/predicts/0/ \ + --pdt /projects/b1171/ylk4626/project/DeepChopper/logs/eval/runs/vcap002_hyena_both_model_hyena/VCaP.fastq_5/predicts/0/ \ + --pdt /projects/b1171/ylk4626/project/DeepChopper/logs/eval/runs/vcap002_hyena_both_model_hyena/VCaP.fastq_6/predicts/0/ \ + --pdt /projects/b1171/ylk4626/project/DeepChopper/logs/eval/runs/vcap002_hyena_both_model_hyena/VCaP.fastq_7/predicts/0/ \ + --pdt /projects/b1171/ylk4626/project/DeepChopper/logs/eval/runs/vcap002_hyena_both_model_hyena/VCaP.fastq_8/predicts/0/ \ + --pdt /projects/b1171/ylk4626/project/DeepChopper/logs/eval/runs/vcap002_hyena_both_model_hyena/VCaP.fastq_9/predicts/0/ \ + --fq data/dorado_without_trim_fqs/VCaP.fastq -t 10 -o vcap002_hyena_both_model cargo run --bin predict -r -- \ --pdt /projects/b1171/ylk4626/project/DeepChopper/logs/eval/runs/vcap_004_cnn_model_cnn/RNA004.fastq_0/predicts/0/ \ diff --git a/scripts/predict.sh b/scripts/predict.sh index e6d3fc0..0fca3d1 100755 --- a/scripts/predict.sh +++ b/scripts/predict.sh @@ -2,7 +2,10 @@ set -euo pipefail # Combines the set commands into one line # Paths to checkpoint files -hyena_ckpt_path="/projects/b1171/ylk4626/project/DeepChopper/logs/train/runs/2024-04-08_23-19-20/checkpoints/epoch_005_f1_0.9933.ckpt" +# hyena_ckpt_path="/projects/b1171/ylk4626/project/DeepChopper/logs/train/runs/2024-04-08_23-19-20/checkpoints/epoch_005_f1_0.9933.ckpt" + +# train with both rna 002 data +hyena_ckpt_path="/projects/b1171/ylk4626/project/DeepChopper/logs/train/runs/2024-11-14_14-14-01/checkpoints/epoch_010_f1_0.9930.ckpt" # rna 004 only # hyena_ckpt_path="/projects/b1171/ylk4626/project/DeepChopper/logs/train/runs/2024-07-02_15-20-53/checkpoints/epoch_008_f1_0.9946.ckpt" @@ -11,8 +14,8 @@ cnn_ckpt_path="/projects/b1171/ylk4626/project/DeepChopper/logs/train/runs/2024- caduceus_ckpt_path="/projects/b1171/ylk4626/project/DeepChopper/logs/train/runs/2024-05-25_19-42-45/checkpoints/epoch_002_f1_0.9982.ckpt" # Default model selection -sample_name="MCF7_hyena_model" -data_folder="data/dorado_without_trim_fqs/MCF7.fastq_chunks" +sample_name="vcap002_hyena_both_model" +data_folder="data/dorado_without_trim_fqs/VCaP.fastq_chunks" num_workers=60 batch_size=64