Evaluation error on COCO dataset

[ml-ai-cv]

Hello,

I am trying to use the evaluation code for prediction on COCO 2017 dataset for replicating/measuring zero-shot performance on coco2017/

Steps I followed:

1. created the DATASET folder with COCO data from https://cocodataset.org/#download in this format

val2017 DATASET/coco/val2017 DATASET/coco/annotations/instances_val2017.json

test2017 DATASET/coco/test2017 DATASET/coco/annotations/image_info_test-dev2017.json

2. created MODEL folder and downloaded these checkpoint files in it mkdir MODEL wget https://penzhanwu2bbs.blob.core.windows.net/data/GLIPv1_Open/models/swin_tiny_patch4_window7_224.pth -O swin_tiny_patch4_window7_224.pth wget https://penzhanwu2bbs.blob.core.windows.net/data/GLIPv1_Open/models/swin_large_patch4_window12_384_22k.pth -O swin_large_patch4_window12_384_22k.pth

3. Using the model zoo (table) I downloaded this checkpoint file for GLIP-L (https://penzhanwu2bbs.blob.core.windows.net/data/GLIPv1_Open/models/glip_large_model.pth) in MODEL folder

4. created output folder in GLIP folder

5. then I gave this command

python tools/test_grounding_net.py --config-file ./configs/pretrain/glip_Swin_L.yaml --weight ./MODEL/glip_large_model.pth TEST.IMS_PER_BATCH 1 MODEL.DYHEAD.SCORE_AGG "MEAN" TEST.EVAL_TASK detection MODEL.DYHEAD.FUSE_CONFIG.MLM_LOSS False OUTPUT_DIR output

After running this evaluation command I am getting this error

The combined datasets are: ('coco_2017_val',). loading annotations into memory... Done (t=0.38s) creating index... index created! coco_2017_val has the 5000 data points COCODataset 2023-04-18 22:53:06,543 maskrcnn_benchmark.inference INFO: Start evaluation on coco_2017_val dataset(5000 images). banner. blanket. branch. bridge. building-other. bush. cabinet. cage. cardboard. carpet. ceiling-other. ceiling-tile. cloth. clothes. clouds. counter. cupboard. curtain. desk-stuff. dirt. door-stuff. fence. floor-marble. floor-other. floor-stone. floor-tile. floor-wood. flower. fog. food-other. fruit. furniture-other. grass. gravel. ground-other. hill. house. leaves. light. mat. metal. mirror-stuff. moss. mountain. mud. napkin. net. paper. pavement. pillow. plant-other. plastic. platform. playingfield. railing. railroad. river. road. rock. roof. rug. salad. sand. sea. shelf. sky-other. skyscraper. snow. solid-other. stairs. stone. straw. structural-other. table. tent. textile-other. towel. tree. vegetable. wall-brick. wall-concrete. wall-other. wall-panel. wall-stone. wall-tile. wall-wood. water-other. waterdrops. window-blind. window-other. wood. other All queries ['banner. blanket. branch. bridge. building-other. bush. cabinet. cage. cardboard. carpet. ceiling-other. ceiling-tile. cloth. clothes. clouds. counter. cupboard. curtain. desk-stuff. dirt. door-stuff. fence. floor-marble. floor-other. floor-stone. floor-tile. floor-wood. flower. fog. food-other. fruit. furniture-other. grass. gravel. ground-other. hill. house. leaves. light. mat. metal. mirror-stuff. moss. mountain. mud. napkin. net. paper. pavement. pillow. plant-other. plastic. platform. playingfield. railing. railroad. river. road. rock. roof. rug. salad. sand. sea. shelf. sky-other. skyscraper. snow. solid-other. stairs. stone. straw. structural-other. table. tent. textile-other. towel. tree. vegetable. wall-brick. wall-concrete. wall-other. wall-panel. wall-stone. wall-tile. wall-wood. water-other. waterdrops. window-blind. window-other. wood. other'] 0%| | 0/5000 [00:00<?, ?it/s]huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either:

• Avoid using tokenizers before the fork if possible
• Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either:
• Avoid using tokenizers before the fork if possible
• Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either:
• Avoid using tokenizers before the fork if possible
• Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either:
• Avoid using tokenizers before the fork if possible
• Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) 0%| | 0/5000 [00:00<?, ?it/s] Traceback (most recent call last): File "tools/test_grounding_net.py", line 222, in main() File "tools/test_grounding_net.py", line 205, in main inference( File "/GLIP/maskrcnn_benchmark/engine/inference.py", line 450, in inference for i, batch in enumerate(_iterator): File "/opt/conda/lib/python3.8/site-packages/tqdm/std.py", line 1193, in iter for obj in iterable: File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 521, in next data = self._next_data() File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1203, in _next_data return self._process_data(data) File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1229, in _process_data data.reraise() File "/opt/conda/lib/python3.8/site-packages/torch/_utils.py", line 434, in reraise raise self.exc_type(msg) AttributeError: Caught AttributeError in DataLoader worker process 0. Original Traceback (most recent call last): File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop data = fetcher.fetch(index) File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 44, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/GLIP/maskrcnn_benchmark/data/datasets/coco.py", line 256, in getitem img, target = self.transforms(img, target) File "/GLIP/maskrcnn_benchmark/data/transforms/transforms.py", line 70, in call image, target = t(image, target) File "/GLIP/maskrcnn_benchmark/data/transforms/transforms.py", line 126, in call target = target.resize(new_size) File "/GLIP/maskrcnn_benchmark/structures/bounding_box.py", line 143, in resize v = v.resize(size, *args, *kwargs) File "/GLIP/maskrcnn_benchmark/structures/segmentation_mask.py", line 186, in resize scaled.append(polygon.resize(size, args, **kwargs)) File "/GLIP/maskrcnn_benchmark/structures/segmentation_mask.py", line 118, in resize p = poly.clone() AttributeError: 'str' object has no attribute 'clone'

Please let me know how to remove this error.

I appreciate your help.

[tisharSinha]

I also get the same warning and the code runs for hours with doing anything after this: huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either:

• Avoid using tokenizers before the fork if possible
• Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)

[whhong5]

I met the same error.

[sharad5]

Same Error while trying to run a COCO Formatted Custom Dataset. Did anyone find any fix to this ?