ResNet V2 50
ResNet V2 50 is Google's image to text model. A ResNet-50 V2 image classification model with improved residual connections for TensorFlow-based visual recognition.
| Specifications | |
|---|---|
google-resnet-2-50b-classification | |
| Image to Text | |
| Active | |
| Google | |
| Image | |
| Text | |
| 50B | |
Capabilities
Input1/5
Text·
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Cheapest Instances to Run It
Cloud GPU instances that can host ResNet V2 50, ranked by cheapest on-demand price. The model needs about 120 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| Standard_NP20s |  Azure | 2× AMD Alveo U250 FPGA (64GB) | 128 GB | $3.30/hr | ||
| Standard_NP40s | Azure | 4× AMD Alveo U250 FPGA (64GB) | 256 GB | $6.60/hr | ||
| Standard_NC48ads_A100_v4 | Azure | 2× NVIDIA A100 | 160 GB | $7.35/hr | ||
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| ResNet V2 50 | — | — | — | — | Current |
| ResNet V2 101 | — | — | — | — | Available |
| ResNet V2 Classification | — | — | — | — | Available |
| ResNet V2 Featurevector | — | — | — | — | Available |
| ResNet V1 101 | — | — | — | — | Available |
| ResNet V1 152 | — | — | — | — | Available |
| ResNet V1 50 | — | — | — | — | Available |
| ResNet V1 Classification | — | — | — | — | Available |
| ResNet 101 | — | — | — | — | Available |
| ResNet 152 | — | — | — | — | Available |
| ResNet 18 | — | — | — | — | Available |