Skip to content

GitLab

Unverified Commit e3bb7f5a authored by Kevin Xiang Li's avatar Kevin Xiang Li Committed by GitHub
Browse files

benchmark: enhance configurable multimodal benchmarking in bench_serving (#9812) 


Co-authored-by: default avatarXiang (Kevin) Li <lik@nvidia.com>
Co-authored-by: default avatarXinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
parent 92473e2e
Hide whitespace changes
Inline Side-by-side
Showing with 246 additions and 145 deletions
docs/developer_guide/bench_serving.md
View file @ e3bb7f5a
......@@ -59,15 +59,16 @@ Select with `--dataset-name`:
- `sharegpt` (default): loads ShareGPT-style pairs; optionally restrict with `--sharegpt-context-len` and override outputs with `--sharegpt-output-len`
- `random`: random text lengths; sampled from ShareGPT token space
- `random-ids`: random token ids (can lead to gibberish)
- `random-image`: generates random images and wraps them in chat messages; supports custom resolutions via 'heightxwidth' format
- `image`: generates images and wraps them in chat messages; supports custom resolutions, multiple formats, and different content types
- `generated-shared-prefix`: synthetic dataset with shared long system prompts and short questions
- `mmmu`: samples from MMMU (Math split) and includes images
Common dataset flags:
- `--num-prompts N`: number of requests
- `--random-input-len`, `--random-output-len`, `--random-range-ratio`: for random/random-ids/random-image
- `--random-image-num-images`, `--random-image-resolution`: for random-image dataset (supports presets 1080p/720p/360p or custom 'heightxwidth' format)
- `--random-input-len`, `--random-output-len`, `--random-range-ratio`: for random/random-ids/image
- `--image-count`: Number of images per request (for `image` dataset).
- `--apply-chat-template`: apply tokenizer chat template when constructing prompts
- `--dataset-path PATH`: file path for ShareGPT json; if blank and missing, it will be downloaded and cached
......@@ -79,14 +80,16 @@ Generated Shared Prefix flags (for `generated-shared-prefix`):
- `--gsp-question-len`
- `--gsp-output-len`
Random Image dataset flags (for `random-image`):
Image dataset flags (for `image`):
- `--random-image-num-images`: Number of images per request
- `--random-image-resolution`: Image resolution; supports presets (1080p, 720p, 360p) or custom 'heightxwidth' format (e.g., 1080x1920, 512x768)
- `--image-count`: Number of images per request
- `--image-resolution`: Image resolution; supports presets (4k, 1080p, 720p, 360p) or custom 'heightxwidth' format (e.g., 1080x1920, 512x768)
- `--image-format`: Image format (jpeg or png)
- `--image-content`: Image content type (random or blank)
### Examples
1. To benchmark random-image dataset with 3 images per request, 500 prompts, 512 input length, and 512 output length, you can run:
1. To benchmark image dataset with 3 images per request, 500 prompts, 512 input length, and 512 output length, you can run:
```bash
python -m sglang.launch_server --model-path Qwen/Qwen2.5-VL-3B-Instruct --disable-radix-cache
......@@ -95,10 +98,10 @@ python -m sglang.launch_server --model-path Qwen/Qwen2.5-VL-3B-Instruct --disabl
```bash
python -m sglang.bench_serving \
--backend sglang-oai-chat \
--dataset-name random-image \
--dataset-name image \
--num-prompts 500 \
--random-image-num-images 3 \
--random-image-resolution 720p \
--image-count 3 \
--image-resolution 720p \
--random-input-len 512 \
--random-output-len 512
```
......@@ -159,9 +162,10 @@ The script will add `Authorization: Bearer $OPENAI_API_KEY` automatically for Op
Printed after each run:
- Request throughput (req/s)
- Input token throughput (tok/s)
- Input token throughput (tok/s) - includes both text and vision tokens
- Output token throughput (tok/s)
- Total token throughput (tok/s)
- Total token throughput (tok/s) - includes both text and vision tokens
- Total input text tokens and Total input vision tokens - per-modality breakdown
- Concurrency: aggregate time of all requests divided by wall time
- End-to-End Latency (ms): mean/median/std/p99 per-request total latency
- Time to First Token (TTFT, ms): mean/median/std/p99 for streaming mode
......@@ -227,31 +231,48 @@ python3 -m sglang.bench_serving \
--apply-chat-template
```
4) Random images (VLM) with chat template:
4) Images (VLM) with chat template:
```bash
python3 -m sglang.bench_serving \
--backend sglang \
--host 127.0.0.1 --port 30000 \
--model your-vlm-model \
--dataset-name random-image \
--random-image-num-images 2 \
--random-image-resolution 720p \
--dataset-name image \
--image-count 2 \
--image-resolution 720p \
--random-input-len 128 --random-output-len 256 \
--num-prompts 200 \
--apply-chat-template
```
4a) Random images with custom resolution:
4a) Images with custom resolution:
```bash
python3 -m sglang.bench_serving \
--backend sglang \
--host 127.0.0.1 --port 30000 \
--model your-vlm-model \
--dataset-name image \
--image-count 1 \
--image-resolution 512x768 \
--random-input-len 64 --random-output-len 128 \
--num-prompts 100 \
--apply-chat-template
```
4b) 1080p images with PNG format and blank content:
```bash
python3 -m sglang.bench_serving \
--backend sglang \
--host 127.0.0.1 --port 30000 \
--model your-vlm-model \
--dataset-name random-image \
--random-image-num-images 1 \
--random-image-resolution 512x768 \
--dataset-name image \
--image-count 1 \
--image-resolution 1080p \
--image-format png \
--image-content blank \
--random-input-len 64 --random-output-len 128 \
--num-prompts 100 \
--apply-chat-template
......@@ -325,7 +346,7 @@ python3 -m sglang.bench_serving \
- All requests failed: verify `--backend`, server URL/port, `--model`, and authentication. Check warmup errors printed by the script.
- Throughput seems too low: adjust `--request-rate` and `--max-concurrency`; verify server batch size/scheduling; ensure streaming is enabled if appropriate.
- Token counts look odd: prefer chat/instruct models with proper chat templates; otherwise tokenization of gibberish may be inconsistent.
- Random-image/MMMU datasets: ensure you installed extra deps (`pillow`, `datasets`, `pybase64`).
- Image/MMMU datasets: ensure you installed extra deps (`pillow`, `datasets`, `pybase64`).
- Authentication errors (401/403): set `OPENAI_API_KEY` or disable auth on your server.
### Notes
......
python/sglang/bench_serving.py
View file @ e3bb7f5a
......@@ -35,6 +35,7 @@ import numpy as np
import requests
from tqdm.asyncio import tqdm
from transformers import (
AutoProcessor,
AutoTokenizer,
PreTrainedTokenizer,
PreTrainedTokenizerBase,
......@@ -327,8 +328,9 @@ async def async_request_openai_chat_completions(
"model": request_func_input.model,
"messages": messages,
"temperature": 0.0,
"max_tokens": request_func_input.output_len,
"max_completion_tokens": request_func_input.output_len,
"stream": not args.disable_stream,
"ignore_eos": not args.disable_ignore_eos,
**request_func_input.extra_request_body,
}
......@@ -659,7 +661,30 @@ def get_tokenizer(
)
def get_dataset(args, tokenizer):
def get_processor(
pretrained_model_name_or_path: str,
) -> Union[PreTrainedTokenizer, PreTrainedTokenizerFast]:
assert (
pretrained_model_name_or_path is not None
and pretrained_model_name_or_path != ""
)
if pretrained_model_name_or_path.endswith(
".json"
) or pretrained_model_name_or_path.endswith(".model"):
from sglang.srt.hf_transformers_utils import get_processor
return get_processor(pretrained_model_name_or_path)
if pretrained_model_name_or_path is not None and not os.path.exists(
pretrained_model_name_or_path
):
pretrained_model_name_or_path = get_model(pretrained_model_name_or_path)
return AutoProcessor.from_pretrained(
pretrained_model_name_or_path, trust_remote_code=True
)
def get_dataset(args, tokenizer, model_id=None):
tokenize_prompt = getattr(args, "tokenize_prompt", False)
if args.dataset_name == "sharegpt":
assert not tokenize_prompt
......@@ -672,7 +697,7 @@ def get_dataset(args, tokenizer):
prompt_suffix=args.prompt_suffix,
apply_chat_template=args.apply_chat_template,
)
elif args.dataset_name.startswith("random") and args.dataset_name != "random-image":
elif args.dataset_name.startswith("random"):
input_requests = sample_random_requests(
input_len=args.random_input_len,
output_len=args.random_output_len,
......@@ -683,17 +708,18 @@ def get_dataset(args, tokenizer):
random_sample=args.dataset_name == "random",
return_text=not tokenize_prompt,
)
elif args.dataset_name == "random-image":
assert not tokenize_prompt, "random-image does not support --tokenize-prompt"
input_requests = sample_random_image_requests(
elif args.dataset_name == "image":
processor = get_processor(model_id)
input_requests = sample_image_requests(
num_requests=args.num_prompts,
num_images=args.random_image_num_images,
image_count=args.image_count,
input_len=args.random_input_len,
output_len=args.random_output_len,
range_ratio=args.random_range_ratio,
tokenizer=tokenizer,
apply_chat_template=args.apply_chat_template,
image_resolution=args.random_image_resolution,
processor=processor,
image_content=args.image_content,
image_format=args.image_format,
image_resolution=args.image_resolution,
)
elif args.dataset_name == "generated-shared-prefix":
assert not tokenize_prompt
......@@ -707,12 +733,11 @@ def get_dataset(args, tokenizer):
args=args,
)
elif args.dataset_name == "mmmu":
assert not tokenize_prompt
processor = get_processor(model_id)
input_requests = sample_mmmu_requests(
num_requests=args.num_prompts,
tokenizer=tokenizer,
processor=processor,
fixed_output_len=args.random_output_len,
apply_chat_template=args.apply_chat_template,
random_sample=True,
)
elif args.dataset_name == "mooncake":
......@@ -757,6 +782,8 @@ ASYNC_REQUEST_FUNCS = {
class BenchmarkMetrics:
completed: int
total_input: int
total_input_text: int
total_input_vision: int
total_output: int
total_output_retokenized: int
request_throughput: float
......@@ -850,9 +877,17 @@ class DatasetRow:
prompt: str
prompt_len: int
output_len: int
text_prompt_len: Optional[int] = None
vision_prompt_len: Optional[int] = None
image_data: Optional[List[str]] = None
timestamp: Optional[float] = None
def __post_init__(self):
if self.text_prompt_len is None:
self.text_prompt_len = self.prompt_len
if self.vision_prompt_len is None:
self.vision_prompt_len = 0
async def get_mooncake_request_over_time(
input_requests: List[Dict],
......@@ -929,9 +964,8 @@ async def get_mooncake_request_over_time(
def sample_mmmu_requests(
num_requests: int,
tokenizer: PreTrainedTokenizerBase,
processor: AutoProcessor,
fixed_output_len: Optional[int] = None,
apply_chat_template: bool = True,
random_sample: bool = True,
) -> List[DatasetRow]:
"""
......@@ -1010,54 +1044,12 @@ def sample_mmmu_requests(
question = example.get("question")
# Construct the prompt
prompt = f"Question: {question}\n\nAnswer: "
if apply_chat_template:
try:
is_phi4_multimodal = (
"phi-4-multimodal" in tokenizer.name_or_path.lower()
)
if is_phi4_multimodal:
# <|endoftext10|> is the image token used in the phi-4-multimodal model.
content = prompt.replace("image 1", "<|endoftext10|>")
else:
content = [
{
"type": "image_url",
"image_url": {"url": image_data},
},
{"type": "text", "text": prompt},
]
prompt = tokenizer.apply_chat_template(
[
{
"role": "user",
"content": content,
}
],
add_generation_prompt=True,
tokenize=False,
)
except Exception as e:
# Note (Xinyuan): This is a workaround for an issue where some tokenizers do not support content as a list. (e.g. InternVL)
print(
f"Error applying chat template: {e}, fallback to <image> tag"
)
prompt = f"<image>{prompt}"
# Calculate token lengths for text only (without image data)
prompt_token_ids = tokenizer.encode(prompt)
prompt_len = len(prompt_token_ids)
text_prompt = f"Question: {question}\n\nAnswer: "
output_len = fixed_output_len if fixed_output_len is not None else 256
filtered_dataset.append(
DatasetRow(
prompt=prompt,
prompt_len=prompt_len,
output_len=output_len,
image_data=[image_data],
)
data_row = create_mm_data_row(
text_prompt, [image], [image_data], output_len, processor
)
filtered_dataset.append(data_row)
except Exception as e:
print(f"Error processing example {i}: {e}")
......@@ -1145,7 +1137,11 @@ def sample_sharegpt_requests(
continue
filtered_dataset.append(
DatasetRow(prompt=prompt, prompt_len=prompt_len, output_len=output_len)
DatasetRow(
prompt=prompt,
prompt_len=prompt_len,
output_len=output_len,
)
)
print(f"#Input tokens: {np.sum([x.prompt_len for x in filtered_dataset])}")
......@@ -1256,7 +1252,7 @@ def sample_random_requests(
return input_requests
def parse_random_image_resolution(image_resolution: str) -> Tuple[int, int]:
def parse_image_resolution(image_resolution: str) -> Tuple[int, int]:
"""Parse image resolution into (width, height).
Supports presets '1080p', '720p', '360p' and custom 'heightxwidth' format
......@@ -1281,24 +1277,79 @@ def parse_random_image_resolution(image_resolution: str) -> Tuple[int, int]:
return (width, height)
raise ValueError(
f"Unsupported random-image resolution: {image_resolution}. "
f"Unsupported image resolution: {image_resolution}. "
"Choose from 4k, 1080p, 720p, 360p, or provide custom 'heightxwidth' (e.g., 1080x1920)."
)
def sample_random_image_requests(
def create_mm_data_row(text_prompt, images, images_base64, output_len, processor):
try:
content_items = [
{"type": "image_url", "image_url": {"url": img_url}}
for img_url in images_base64
]
content_items.append({"type": "text", "text": text_prompt})
prompt_str = processor.apply_chat_template(
[{"role": "user", "content": content_items}],
add_generation_prompt=True,
tokenize=False,
)
except Exception:
# Some tokenizers do not support list content; fall back to a placeholder in the text
prompt_str = f"<image>{text_prompt}"
# Calculate total tokens (text + vision)
prompt_len = processor(
text=[prompt_str],
images=images,
padding=False,
return_tensors="pt",
)["input_ids"].numel()
# Calculate text-only tokens
try:
# Create text-only version of the prompt
text_only_prompt = processor.apply_chat_template(
[{"role": "user", "content": text_prompt}],
add_generation_prompt=True,
tokenize=False,
)
text_prompt_len = processor(
text=[text_only_prompt],
padding=False,
return_tensors="pt",
)["input_ids"].numel()
except Exception:
# Fallback: just tokenize the text prompt directly
text_prompt_len = len(processor.tokenizer.encode(text_prompt))
# Vision tokens = total tokens - text tokens
vision_prompt_len = prompt_len - text_prompt_len
return DatasetRow(
prompt=text_prompt,
prompt_len=prompt_len,
output_len=output_len,
text_prompt_len=text_prompt_len,
vision_prompt_len=vision_prompt_len,
image_data=images_base64,
)
def sample_image_requests(
num_requests: int,
num_images: int,
image_count: int,
input_len: int,
output_len: int,
range_ratio: float,
tokenizer: PreTrainedTokenizerBase,
apply_chat_template: bool = True,
image_resolution: str = "1080p",
processor: AutoProcessor,
image_content: str,
image_format: str,
image_resolution: str,
) -> List[DatasetRow]:
"""Generate requests with random images.
"""Generate requests with images.
- Each request includes ``num_images`` random images.
- Each request includes ``image_count`` images.
- Supported resolutions: 4k (3840x2160), 1080p (1920x1080), 720p (1280x720), 360p (640x360),
or custom 'heightxwidth' (e.g., 1080x1920).
- Text lengths follow the 'random' dataset sampling rule. ``prompt_len``
......@@ -1313,12 +1364,12 @@ def sample_random_image_requests(
) from e
# Parse resolution (supports presets and 'heightxwidth')
width, height = parse_random_image_resolution(image_resolution)
width, height = parse_image_resolution(image_resolution)
# Check for potentially problematic combinations and warn user
if width * height >= 1920 * 1080 and num_images * num_requests >= 100:
if width * height >= 1920 * 1080 and image_count * num_requests >= 100:
warnings.warn(
f"High resolution ({width}x{height}) with {num_images * num_requests} total images "
f"High resolution ({width}x{height}) with {image_count * num_requests} total images "
f"may take a long time. Consider reducing resolution or image count.",
UserWarning,
stacklevel=2,
......@@ -1332,53 +1383,50 @@ def sample_random_image_requests(
int(output_len * range_ratio), output_len + 1, size=num_requests
)
def _gen_random_image_data_uri(width: int = width, height: int = height) -> str:
arr = (np.random.rand(height, width, 3) * 255).astype(np.uint8)
img = Image.fromarray(arr, mode="RGB")
def _gen_random_image_data_uri(
width: int = width, height: int = height
) -> (Image, str, int):
if image_content == "blank":
# Generate blank white image
arr = np.full((height, width, 3), 255, dtype=np.uint8)
else:
# Generate random colored image
arr = (np.random.rand(height, width, 3) * 255).astype(np.uint8)
img = Image.fromarray(arr)
buf = io.BytesIO()
img.save(buf, format="JPEG", quality=85)
img.save(buf, format=image_format, quality=85)
encoded = pybase64.b64encode(buf.getvalue()).decode("utf-8")
return f"data:image/jpeg;base64,{encoded}"
image_data = f"data:image/{image_format};base64,{encoded}"
image_bytes = len(image_data.encode("utf-8"))
return img, image_data, image_bytes
dataset: List[DatasetRow] = []
total_image_bytes = 0
for i in range(num_requests):
# Generate text prompt
text_prompt = gen_prompt(tokenizer, int(input_lens[i]))
text_prompt = gen_prompt(processor.tokenizer, int(input_lens[i]))
# Generate image list
images = [_gen_random_image_data_uri() for _ in range(num_images)]
prompt_str = text_prompt
if apply_chat_template:
try:
content_items = [
{"type": "image_url", "image_url": {"url": img_url}}
for img_url in images
]
content_items.append({"type": "text", "text": text_prompt})
prompt_str = tokenizer.apply_chat_template(
[{"role": "user", "content": content_items}],
add_generation_prompt=True,
tokenize=False,
)
except Exception:
# Some tokenizers do not support list content; fall back to a placeholder in the text
prompt_str = f"<image>{text_prompt}"
prompt_token_ids = tokenizer.encode(prompt_str)
prompt_token_len = len(prompt_token_ids)
dataset.append(
DatasetRow(
prompt=prompt_str,
prompt_len=prompt_token_len,
output_len=int(output_lens[i]),
image_data=images,
)
images, images_base64, images_bytes = zip(
*[_gen_random_image_data_uri() for _ in range(image_count)]
)
total_image_bytes += sum(list(images_bytes))
data_row = create_mm_data_row(
text_prompt,
list(images),
list(images_base64),
int(output_lens[i]),
processor,
)
dataset.append(data_row)
print(f"#Input tokens: {np.sum([x.prompt_len for x in dataset])}")
print(f"#Output tokens: {np.sum([x.output_len for x in dataset])}")
print(
f"\nCreated {len(dataset)} {image_content} {image_format} images with average {total_image_bytes//num_requests} bytes per request"
)
return dataset
......@@ -1450,7 +1498,9 @@ def sample_generated_shared_prefix_requests(
input_requests.append(
DatasetRow(
prompt=full_prompt, prompt_len=prompt_len, output_len=output_len
prompt=full_prompt,
prompt_len=prompt_len,
output_len=output_len,
)
)
total_input_tokens += prompt_len
......@@ -1532,6 +1582,8 @@ def calculate_metrics(
output_lens: List[int] = []
retokenized_output_lens: List[int] = []
total_input = 0
total_input_text = 0
total_input_vision = 0
completed = 0
itls: List[float] = []
tpots: List[float] = []
......@@ -1545,7 +1597,9 @@ def calculate_metrics(
tokenizer.encode(outputs[i].generated_text, add_special_tokens=False)
)
retokenized_output_lens.append(retokenized_output_len)
total_input += outputs[i].prompt_len
total_input += input_requests[i].prompt_len
total_input_text += input_requests[i].text_prompt_len
total_input_vision += input_requests[i].vision_prompt_len
if output_len > 1:
tpots.append((outputs[i].latency - outputs[i].ttft) / (output_len - 1))
itls += outputs[i].itl
......@@ -1567,6 +1621,8 @@ def calculate_metrics(
metrics = BenchmarkMetrics(
completed=completed,
total_input=total_input,
total_input_text=total_input_text,
total_input_vision=total_input_vision,
total_output=sum(output_lens),
total_output_retokenized=sum(retokenized_output_lens),
request_throughput=completed / dur_s,
......@@ -1815,6 +1871,10 @@ async def benchmark(
print("{:<40} {:<10}".format("Successful requests:", metrics.completed))
print("{:<40} {:<10.2f}".format("Benchmark duration (s):", benchmark_duration))
print("{:<40} {:<10}".format("Total input tokens:", metrics.total_input))
print("{:<40} {:<10}".format("Total input text tokens:", metrics.total_input_text))
print(
"{:<40} {:<10}".format("Total input vision tokens:", metrics.total_input_vision)
)
print("{:<40} {:<10}".format("Total generated tokens:", metrics.total_output))
print(
"{:<40} {:<10}".format(
......@@ -1884,6 +1944,8 @@ async def benchmark(
"duration": benchmark_duration,
"completed": metrics.completed,
"total_input_tokens": metrics.total_input,
"total_input_text_tokens": metrics.total_input_text,
"total_input_vision_tokens": metrics.total_input_vision,
"total_output_tokens": metrics.total_output,
"total_output_tokens_retokenized": metrics.total_output_retokenized,
"request_throughput": metrics.request_throughput,
......@@ -1918,11 +1980,11 @@ async def benchmark(
output_file_name = args.output_file
else:
now = datetime.now().strftime("%m%d")
if args.dataset_name == "random-image":
if args.dataset_name == "image":
output_file_name = (
f"{args.backend}_{now}_{args.num_prompts}_{args.random_input_len}_"
f"{args.random_output_len}_{args.random_image_num_images}imgs_"
f"{args.random_image_resolution}.jsonl"
f"{args.random_output_len}_{args.image_count}imgs_"
f"{args.image_resolution}.jsonl"
)
elif args.dataset_name.startswith("random"):
output_file_name = f"{args.backend}_{now}_{args.num_prompts}_{args.random_input_len}_{args.random_output_len}.jsonl"
......@@ -2098,6 +2160,12 @@ def run_benchmark(args_: argparse.Namespace):
"Because when the tokenizer counts the output tokens, if there is gibberish, it might count incorrectly.\n"
)
if args.dataset_name in ["image", "mmmu"]:
args.apply_chat_template = True
assert (
not args.tokenize_prompt
), "`--tokenize-prompt` not compatible with image dataset"
print(f"{args}\n")
# Read dataset
......@@ -2105,7 +2173,7 @@ def run_benchmark(args_: argparse.Namespace):
model_id = args.model
tokenizer_id = args.tokenizer if args.tokenizer is not None else args.model
tokenizer = get_tokenizer(tokenizer_id)
input_requests = get_dataset(args, tokenizer)
input_requests = get_dataset(args, tokenizer, model_id)
# compatible with SimpleNamespace
if not hasattr(args, "flush_cache"):
......@@ -2186,7 +2254,7 @@ if __name__ == "__main__":
"random-ids",
"generated-shared-prefix",
"mmmu",
"random-image",
"image",
"mooncake",
],
help="Name of the dataset to benchmark on.",
......@@ -2226,37 +2294,49 @@ if __name__ == "__main__":
"--random-input-len",
type=int,
default=1024,
help="Number of input tokens per request, used only for random dataset.",
help="Number of input tokens per request, used only for random and image dataset.",
)
parser.add_argument(
"--random-output-len",
default=1024,
type=int,
help="Number of output tokens per request, used only for random dataset.",
help="Number of output tokens per request, used only for random and image dataset.",
)
parser.add_argument(
"--random-range-ratio",
type=float,
default=0.0,
help="Range of sampled ratio of input/output length, "
"used only for random dataset.",
"used only for random and image dataset.",
)
# random-image dataset args
# image dataset args
parser.add_argument(
"--random-image-num-images",
"--image-count",
type=int,
default=1,
help="Number of images per request (only available with the random-image dataset)",
help="Number of images per request (only available with the image dataset)",
)
parser.add_argument(
"--random-image-resolution",
"--image-resolution",
type=str,
default="1080p",
help=(
"Resolution of random images for random-image dataset. "
"Resolution of images for image dataset. "
"Supports presets 4k/1080p/720p/360p or custom 'heightxwidth' (e.g., 1080x1920)."
),
)
parser.add_argument(
"--image-format",
type=str,
default="jpeg",
help=("Format of images for image dataset. " "Supports jpeg and png."),
)
parser.add_argument(
"--image-content",
type=str,
default="random",
help=("Content for images for image dataset. " "Supports random and blank."),
)
parser.add_argument(
"--request-rate",
type=float,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment