mirrors
/
Segment-Everything-Everywhere-All-At-Once
mirror of https://github.com/UX-Decoder/Segment-Everything-Everywhere-All-At-Once.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Update TRAIN.md

pull/139/head
Xueyan Zou 2023-10-04 22:28:14 -05:00 committed by GitHub
parent 06c933587c
commit 0ad9a89ef3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 138 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

142
assets/readmes/TRAIN.md
View File

@ -1,7 +1,7 @@
## X-Decoder
**Focal-T**
```sh
**Focal-T:**
```bash
CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 mpirun -n 8 python entry.py train \
--conf_files configs/xdecoder/focalt_unicl_lang.yaml \
--overrides \
@ -34,8 +34,8 @@ CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 mpirun -n 8 python entry.py train \
RESUME_FROM /pth/to/xdecoder_data/pretrained/focalt_in21k_yfcc_gcc_xdecoder_unicl.pt
```
**Focal-L**
```sh
**Focal-L:**
```bash
CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 mpirun -n 8 python entry.py train \
--conf_files configs/xdecoder/focall_unicl_lang.yaml \
--overrides \
@ -69,3 +69,137 @@ CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 mpirun -n 8 python entry.py train \
```
## SEEM
**Focal-T:**
```bash
CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 mpirun -n 8 python entry.py train \
--conf_files configs/seem/focalt_unicl_lang_v1.yaml \
--overrides \
FP16 True \
COCO.INPUT.IMAGE_SIZE 1024 \
MODEL.DECODER.HIDDEN_DIM 512 \
MODEL.ENCODER.CONVS_DIM 512 \
MODEL.ENCODER.MASK_DIM 512 \
TEST.BATCH_SIZE_TOTAL 8 \
TRAIN.BATCH_SIZE_TOTAL 16 \
TRAIN.BATCH_SIZE_PER_GPU 2 \
SOLVER.MAX_NUM_EPOCHS 50 \
SOLVER.BASE_LR 0.0001 \
SOLVER.FIX_PARAM.backbone True \
SOLVER.FIX_PARAM.lang_encoder True \
SOLVER.FIX_PARAM.pixel_decoder True \
MODEL.DECODER.COST_SPATIAL.CLASS_WEIGHT 5.0 \
MODEL.DECODER.COST_SPATIAL.MASK_WEIGHT 2.0 \
MODEL.DECODER.COST_SPATIAL.DICE_WEIGHT 2.0 \
MODEL.DECODER.TOP_SPATIAL_LAYERS 10 \
MODEL.DECODER.SPATIAL.ENABLED True \
MODEL.DECODER.GROUNDING.ENABLED True \
FIND_UNUSED_PARAMETERS True \
ATTENTION_ARCH.SPATIAL_MEMORIES 32 \
MODEL.DECODER.SPATIAL.MAX_ITER 5 \
ATTENTION_ARCH.QUERY_NUMBER 3 \
STROKE_SAMPLER.MAX_CANDIDATE 10 \
WEIGHT True \
RESUME_FROM /pth/to/xdecoder_data/pretrained/xdecoder_focalt_last.pt
```
**Focal-L:**
```bash
CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 mpirun -n 8 python entry.py train \
--conf_files configs/seem/focall_unicl_lang_v1.yaml \
--overrides \
FP16 True \
COCO.INPUT.IMAGE_SIZE 1024 \
MODEL.DECODER.HIDDEN_DIM 512 \
MODEL.ENCODER.CONVS_DIM 512 \
MODEL.ENCODER.MASK_DIM 512 \
TEST.BATCH_SIZE_TOTAL 8 \
TRAIN.BATCH_SIZE_TOTAL 16 \
TRAIN.BATCH_SIZE_PER_GPU 2 \
SOLVER.MAX_NUM_EPOCHS 50 \
SOLVER.BASE_LR 0.0001 \
SOLVER.FIX_PARAM.backbone True \
SOLVER.FIX_PARAM.lang_encoder True \
SOLVER.FIX_PARAM.pixel_decoder True \
MODEL.DECODER.COST_SPATIAL.CLASS_WEIGHT 5.0 \
MODEL.DECODER.COST_SPATIAL.MASK_WEIGHT 2.0 \
MODEL.DECODER.COST_SPATIAL.DICE_WEIGHT 2.0 \
MODEL.DECODER.TOP_SPATIAL_LAYERS 10 \
MODEL.DECODER.SPATIAL.ENABLED True \
MODEL.DECODER.GROUNDING.ENABLED True \
FIND_UNUSED_PARAMETERS True \
ATTENTION_ARCH.SPATIAL_MEMORIES 32 \
MODEL.DECODER.SPATIAL.MAX_ITER 5 \
ATTENTION_ARCH.QUERY_NUMBER 3 \
STROKE_SAMPLER.MAX_CANDIDATE 10 \
WEIGHT True \
RESUME_FROM /pth/to/xdecoder_data/pretrained/xdecoder_focall_last_oq101.pt
```
**SAM ViT-B:**
```bash
CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 mpirun -n 8 python entry.py train \
--conf_files configs/seem/samvitb_unicl_lang_v1.yaml \
--overrides \
FP16 True \
COCO.INPUT.IMAGE_SIZE 1024 \
MODEL.DECODER.HIDDEN_DIM 512 \
MODEL.ENCODER.CONVS_DIM 512 \
MODEL.ENCODER.MASK_DIM 512 \
TEST.BATCH_SIZE_TOTAL 8 \
TRAIN.BATCH_SIZE_TOTAL 16 \
TRAIN.BATCH_SIZE_PER_GPU 2 \
SOLVER.MAX_NUM_EPOCHS 50 \
SOLVER.BASE_LR 0.0001 \
SOLVER.FIX_PARAM.backbone True \
SOLVER.FIX_PARAM.lang_encoder True \
SOLVER.FIX_PARAM.pixel_decoder True \
MODEL.DECODER.COST_SPATIAL.CLASS_WEIGHT 5.0 \
MODEL.DECODER.COST_SPATIAL.MASK_WEIGHT 2.0 \
MODEL.DECODER.COST_SPATIAL.DICE_WEIGHT 2.0 \
MODEL.DECODER.TOP_SPATIAL_LAYERS 10 \
MODEL.DECODER.SPATIAL.ENABLED True \
MODEL.DECODER.GROUNDING.ENABLED True \
FIND_UNUSED_PARAMETERS True \
ATTENTION_ARCH.SPATIAL_MEMORIES 32 \
MODEL.DECODER.SPATIAL.MAX_ITER 5 \
ATTENTION_ARCH.QUERY_NUMBER 3 \
STROKE_SAMPLER.MAX_CANDIDATE 10 \
MODEL.BACKBONE.PRETRAINED /pth/to/xdecoder_data/pretrained/sam_vit_b_01ec64.pth \
WEIGHT True \
RESUME_FROM /pth/to/xdecoder_data/pretrained/focalb_lang_unicl.pt
```
**SAM ViT-L:**
```bash
CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 mpirun -n 8 python entry.py train \
--conf_files configs/seem/samvitl_unicl_lang_v1.yaml \
--overrides \
FP16 True \
COCO.INPUT.IMAGE_SIZE 1024 \
MODEL.DECODER.HIDDEN_DIM 512 \
MODEL.ENCODER.CONVS_DIM 512 \
MODEL.ENCODER.MASK_DIM 512 \
TEST.BATCH_SIZE_TOTAL 8 \
TRAIN.BATCH_SIZE_TOTAL 16 \
TRAIN.BATCH_SIZE_PER_GPU 2 \
SOLVER.MAX_NUM_EPOCHS 50 \
SOLVER.BASE_LR 0.0001 \
SOLVER.FIX_PARAM.backbone True \
SOLVER.FIX_PARAM.lang_encoder True \
SOLVER.FIX_PARAM.pixel_decoder True \
MODEL.DECODER.COST_SPATIAL.CLASS_WEIGHT 5.0 \
MODEL.DECODER.COST_SPATIAL.MASK_WEIGHT 2.0 \
MODEL.DECODER.COST_SPATIAL.DICE_WEIGHT 2.0 \
MODEL.DECODER.TOP_SPATIAL_LAYERS 10 \
MODEL.DECODER.SPATIAL.ENABLED True \
MODEL.DECODER.GROUNDING.ENABLED True \
FIND_UNUSED_PARAMETERS True \
ATTENTION_ARCH.SPATIAL_MEMORIES 32 \
MODEL.DECODER.SPATIAL.MAX_ITER 5 \
ATTENTION_ARCH.QUERY_NUMBER 3 \
STROKE_SAMPLER.MAX_CANDIDATE 10 \
MODEL.BACKBONE.PRETRAINED /pth/to/xdecoder_data/pretrained/sam_vit_l_0b3195.pth \
WEIGHT True \
RESUME_FROM /pth/to/xdecoder_data/pretrained/focalb_lang_unicl.pt
```