From 3319d815303497380ecfe5b871513b19ee913149 Mon Sep 17 00:00:00 2001 From: Andrew White Date: Mon, 27 Jul 2026 07:48:04 -0500 Subject: [PATCH] fix(readme): APEX install command uses 'cd && apex &&' (+3 more) --- README.md | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/README.md b/README.md index 348bc8d..6db5e1d 100644 --- a/README.md +++ b/README.md @@ -66,7 +66,7 @@ pip install mmsegmentation==0.18.0 pip install webdataset==0.1.103 pip install timm==0.4.12 git clone https://github.com/NVIDIA/apex -cd && apex && pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./ +cd apex && pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./ pip install opencv-python==4.4.0.46 termcolor==1.1.0 diffdist einops omegaconf pip install nltk ftfy regex tqdm ``` @@ -189,9 +189,9 @@ Then run `img2dataset` to download the image text pairs and save them in the web ``` sed -i '1s/^/caption\turl\n/' gcc3m.tsv img2dataset --url_list gcc3m.tsv --input_format "tsv" \ - --url_col "url" --caption_col "caption" --output_format webdataset\ - --output_folder local_data/gcc3m_shards - --processes_count 16 --thread_count 64 + --url_col "url" --caption_col "caption" --output_format webdataset \ + --output_folder local_data/gcc3m_shards \ + --processes_count 16 --thread_count 64 \ --image_size 512 --resize_mode keep_ratio --resize_only_if_bigger True \ --enable_wandb True --save_metadata False --oom_shard_count 6 rename -d 's/^/gcc-train-/' local_data/gcc3m_shards/* @@ -206,9 +206,9 @@ Then run `img2dataset` to download the image text pairs and save them in the web ``` sed -i '1s/^/caption\turl\n/' gcc12m.tsv img2dataset --url_list gcc12m.tsv --input_format "tsv" \ - --url_col "url" --caption_col "caption" --output_format webdataset\ + --url_col "url" --caption_col "caption" --output_format webdataset \ --output_folder local_data/gcc12m_shards \ - --processes_count 16 --thread_count 64 + --processes_count 16 --thread_count 64 \ --image_size 512 --resize_mode keep_ratio --resize_only_if_bigger True \ --enable_wandb True --save_metadata False --oom_shard_count 6 rename -d 's/^/gcc-conceptual-12m-/' local_data/gcc12m_shards/* @@ -255,11 +255,11 @@ Then run the preprocessing script and `img2dataset` to download the image text p python convert_dataset/process_redcaps.py annotations redcaps12m_meta/redcaps12m.parquet --num-split 16 img2dataset --url_list ~/data/redcaps12m/ --input_format "parquet" \ --url_col "URL" --caption_col "TEXT" --output_format webdataset \ - --output_folder local_data/recaps12m_shards - --processes_count 16 --thread_count 64 + --output_folder local_data/redcaps12m_shards \ + --processes_count 16 --thread_count 64 \ --image_size 512 --resize_mode keep_ratio --resize_only_if_bigger True \ --enable_wandb True --save_metadata False --oom_shard_count 6 -rename -d 's/^/redcap12m-/' local_data/recaps12m_shards/* +rename -d 's/^/redcap12m-/' local_data/redcaps12m_shards/* ``` ### ImageNet